Compare commits
76
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
cdcaff184f | ||
|
|
25ec3880bb | ||
|
|
edbd8f0ca8 | ||
|
|
a4272c17a9 | ||
|
|
c8cdf218f2 | ||
|
|
b3833f2051 | ||
|
|
a272c39613 | ||
|
|
6df9b54626 | ||
|
|
156c2c2fd5 | ||
|
|
6011b96fc1 | ||
|
|
7639bb8472 | ||
|
|
c61b66b49d | ||
|
|
cf49715c66 | ||
|
|
bf8a814c58 | ||
|
|
8fadec5c2c | ||
|
|
7263fee4c7 | ||
|
|
4204c2c974 | ||
|
|
9372cfb8ca | ||
|
|
179949b289 | ||
|
|
cd3946bd11 | ||
|
|
12e374bc05 | ||
|
|
fd2fac7112 | ||
|
|
60092b378b | ||
|
|
9025af62f0 | ||
|
|
83bb18b6a7 | ||
|
|
ec759dd1dc | ||
|
|
c454fc40bb | ||
|
|
bfb42cfc24 | ||
|
|
49dd91fee0 | ||
|
|
56c1862205 | ||
|
|
dbefd30dce | ||
|
|
bc06ce5b90 | ||
|
|
b26d9fd10e | ||
|
|
909ee338d2 | ||
|
|
84e319a42f | ||
|
|
efd9c74cd3 | ||
|
|
eccdf43cd3 | ||
|
|
9e25e5b26b | ||
|
|
cee8fc05c2 | ||
|
|
9a55d45832 | ||
|
|
48de6aed8c | ||
|
|
8772271648 | ||
|
|
0cb216c2bc | ||
|
|
eb45d78c47 | ||
|
|
582aed61ec | ||
|
|
0294414d26 | ||
|
|
3a2a78e0fd | ||
|
|
245a96809a | ||
|
|
bb41b11cce | ||
|
|
af73ab9371 | ||
|
|
cba1337066 | ||
|
|
d50ed70467 | ||
|
|
f313f0873b | ||
|
|
f7a4dab707 | ||
|
|
3861246ac6 | ||
|
|
053c22bc15 | ||
|
|
bbfa2049eb | ||
|
|
0b47ffdcb6 | ||
|
|
cf91730e45 | ||
|
|
ae0768e4de | ||
|
|
ccc848f2e2 | ||
|
|
c6ccad1d18 | ||
|
|
4e8512c812 | ||
|
|
f1bcbb1543 | ||
|
|
537a2883bf | ||
|
|
72a3988e49 | ||
|
|
93b8bc48e4 | ||
|
|
19f8d76e21 | ||
|
|
772a202d6e | ||
|
|
dc16bbf8a4 | ||
|
|
028ad7e941 | ||
|
|
620858a575 | ||
|
|
0bb5f57cc6 | ||
|
|
0a4374dc8c | ||
|
|
8afa402118 | ||
|
|
1eee189a49 |
No files matched your search
@@ -1,4 +1,3 @@
|
||||
|
||||
# mindnet API (bundle)
|
||||
|
||||
This bundle provides a minimal FastAPI app for embeddings and Qdrant upserts/queries plus a Markdown importer.
|
||||
@@ -35,5 +34,5 @@ python3 scripts/import_markdown.py --vault /path/to/Obsidian
|
||||
See `scripts/quick_test.sh` for a runnable example.
|
||||
|
||||
>Anmerkung:
|
||||
Diese Datei ist veraltet
|
||||
Diese Datei ist veraltet und muss auf Stand 2.6.0 gebracht werden
|
||||
|
||||
+6
-13
@@ -1,17 +1,10 @@
|
||||
"""
|
||||
app — mindnet API package
|
||||
|
||||
Zweck:
|
||||
Markiert 'app/' als Python-Paket, damit 'from app.main import create_app'
|
||||
in Tests und Skripten funktioniert.
|
||||
Kompatibilität:
|
||||
Python 3.12+
|
||||
Version:
|
||||
0.1.0 (Erstanlage)
|
||||
Stand:
|
||||
2025-10-07
|
||||
Hinweise:
|
||||
Keine Logik – nur Paketinitialisierung.
|
||||
FILE: app/__init__.py
|
||||
DESCRIPTION: Paket-Initialisierung.
|
||||
VERSION: 0.1.0
|
||||
STATUS: Active
|
||||
DEPENDENCIES: None
|
||||
LAST_ANALYSIS: 2025-12-15
|
||||
"""
|
||||
|
||||
__version__ = "0.1.0"
|
||||
+6
-2
@@ -1,6 +1,10 @@
|
||||
"""
|
||||
app/config.py — zentrale Konfiguration
|
||||
Version: 0.4.0 (WP-06 Complete)
|
||||
FILE: app/config.py
|
||||
DESCRIPTION: Zentrale Pydantic-Konfiguration (Env-Vars für Qdrant, LLM, Retriever).
|
||||
VERSION: 0.4.0
|
||||
STATUS: Active
|
||||
DEPENDENCIES: os, functools, pathlib
|
||||
LAST_ANALYSIS: 2025-12-15
|
||||
"""
|
||||
from __future__ import annotations
|
||||
import os
|
||||
|
||||
+77
-37
@@ -1,11 +1,13 @@
|
||||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
"""
|
||||
app/core/chunk_payload.py (Mindnet V2 — types.yaml authoritative)
|
||||
- neighbors_prev / neighbors_next sind Listen ([], [id]).
|
||||
- retriever_weight / chunk_profile kommen aus types.yaml (Frontmatter wird ignoriert).
|
||||
- Fallbacks: defaults.* in types.yaml; sonst 1.0 / "default".
|
||||
- WP-11 Update: Injects 'title' into chunk payload for Discovery Service.
|
||||
FILE: app/core/chunk_payload.py
|
||||
DESCRIPTION: Baut das JSON-Objekt für 'mindnet_chunks'.
|
||||
FEATURES:
|
||||
- Inkludiert Nachbarschafts-IDs (prev/next) und Titel.
|
||||
- FIX 3: Robuste Erkennung des Inputs (Frontmatter-Dict vs. Note-Objekt), damit Overrides ankommen.
|
||||
VERSION: 2.3.0
|
||||
STATUS: Active
|
||||
DEPENDENCIES: yaml, os
|
||||
EXTERNAL_CONFIG: config/types.yaml
|
||||
"""
|
||||
from __future__ import annotations
|
||||
from typing import Any, Dict, List, Optional
|
||||
@@ -36,42 +38,48 @@ def _get_defaults(reg: dict) -> dict:
|
||||
return {}
|
||||
|
||||
def _as_float(x: Any):
|
||||
try:
|
||||
return float(x)
|
||||
except Exception:
|
||||
return None
|
||||
try: return float(x)
|
||||
except Exception: return None
|
||||
|
||||
def _resolve_chunk_profile(note_type: str, reg: dict) -> str:
|
||||
def _resolve_chunk_profile_from_config(note_type: str, reg: dict) -> Optional[str]:
|
||||
# 1. Type Level
|
||||
types = _get_types_map(reg)
|
||||
if isinstance(types, dict):
|
||||
t = types.get(note_type, {})
|
||||
if isinstance(t, dict) and isinstance(t.get("chunk_profile"), str):
|
||||
return t["chunk_profile"]
|
||||
if isinstance(t, dict):
|
||||
cp = t.get("chunking_profile") or t.get("chunk_profile")
|
||||
if isinstance(cp, str) and cp: return cp
|
||||
# 2. Defaults Level
|
||||
defs = _get_defaults(reg)
|
||||
if isinstance(defs, dict) and isinstance(defs.get("chunk_profile"), str):
|
||||
return defs["chunk_profile"]
|
||||
return "default"
|
||||
if isinstance(defs, dict):
|
||||
cp = defs.get("chunking_profile") or defs.get("chunk_profile")
|
||||
if isinstance(cp, str) and cp: return cp
|
||||
return None
|
||||
|
||||
def _resolve_retriever_weight(note_type: str, reg: dict) -> float:
|
||||
def _resolve_retriever_weight_from_config(note_type: str, reg: dict) -> float:
|
||||
"""
|
||||
Liest Weight nur aus Config (Type > Default).
|
||||
Wird aufgerufen, wenn im Frontmatter nichts steht.
|
||||
"""
|
||||
# 1. Type Level
|
||||
types = _get_types_map(reg)
|
||||
if isinstance(types, dict):
|
||||
t = types.get(note_type, {})
|
||||
if isinstance(t, dict) and (t.get("retriever_weight") is not None):
|
||||
v = _as_float(t.get("retriever_weight"))
|
||||
if v is not None:
|
||||
return float(v)
|
||||
if v is not None: return float(v)
|
||||
|
||||
# 2. Defaults Level
|
||||
defs = _get_defaults(reg)
|
||||
if isinstance(defs, dict) and (defs.get("retriever_weight") is not None):
|
||||
v = _as_float(defs.get("retriever_weight"))
|
||||
if v is not None:
|
||||
return float(v)
|
||||
if v is not None: return float(v)
|
||||
|
||||
return 1.0
|
||||
|
||||
def _as_list(x):
|
||||
if x is None:
|
||||
return []
|
||||
if isinstance(x, list):
|
||||
return x
|
||||
if x is None: return []
|
||||
if isinstance(x, list): return x
|
||||
return [x]
|
||||
|
||||
def make_chunk_payloads(note: Dict[str, Any],
|
||||
@@ -81,18 +89,49 @@ def make_chunk_payloads(note: Dict[str, Any],
|
||||
note_text: str = "",
|
||||
types_cfg: Optional[dict] = None,
|
||||
file_path: Optional[str] = None) -> List[Dict[str, Any]]:
|
||||
fm = (note or {}).get("frontmatter", {}) or {}
|
||||
"""
|
||||
Erstellt die Payloads für die Chunks.
|
||||
|
||||
Argument 'note' kann sein:
|
||||
A) Ein komplexes Objekt/Dict mit Key "frontmatter" (Legacy / Tests)
|
||||
B) Direkt das Frontmatter-Dictionary (Call aus ingestion.py)
|
||||
"""
|
||||
|
||||
# --- FIX 3: Intelligente Erkennung der Input-Daten ---
|
||||
# Wir prüfen: Ist 'note' ein Container MIT 'frontmatter', oder IST es das 'frontmatter'?
|
||||
if isinstance(note, dict) and "frontmatter" in note and isinstance(note["frontmatter"], dict):
|
||||
# Fall A: Container (wir müssen auspacken)
|
||||
fm = note["frontmatter"]
|
||||
else:
|
||||
# Fall B: Direktes Dict (so ruft ingestion.py es auf!)
|
||||
fm = note or {}
|
||||
|
||||
note_type = fm.get("type") or note.get("type") or "concept"
|
||||
|
||||
# WP-11 FIX: Title Extraction für Discovery Service
|
||||
# Wir holen den Titel aus Frontmatter oder Fallback ID/Untitled
|
||||
# Title Extraction (Fallback Chain)
|
||||
title = fm.get("title") or note.get("title") or fm.get("id") or "Untitled"
|
||||
|
||||
reg = types_cfg if isinstance(types_cfg, dict) else _load_types()
|
||||
|
||||
# types.yaml authoritative
|
||||
cp = _resolve_chunk_profile(note_type, reg)
|
||||
rw = _resolve_retriever_weight(note_type, reg)
|
||||
# --- Profil-Ermittlung ---
|
||||
# Da wir 'fm' jetzt korrekt haben, funktionieren diese lookups:
|
||||
cp = fm.get("chunking_profile") or fm.get("chunk_profile")
|
||||
|
||||
if not cp:
|
||||
cp = _resolve_chunk_profile_from_config(note_type, reg)
|
||||
if not cp:
|
||||
cp = "sliding_standard"
|
||||
|
||||
# --- Retriever Weight Ermittlung ---
|
||||
rw = fm.get("retriever_weight")
|
||||
|
||||
if rw is None:
|
||||
rw = _resolve_retriever_weight_from_config(note_type, reg)
|
||||
|
||||
try:
|
||||
rw = float(rw)
|
||||
except Exception:
|
||||
rw = 1.0
|
||||
|
||||
tags = fm.get("tags") or []
|
||||
if isinstance(tags, str):
|
||||
@@ -100,7 +139,7 @@ def make_chunk_payloads(note: Dict[str, Any],
|
||||
|
||||
out: List[Dict[str, Any]] = []
|
||||
for idx, ch in enumerate(chunks_from_chunker):
|
||||
# Attribute oder Keys (Chunk-Objekt oder Dict)
|
||||
# Attribute extrahieren
|
||||
cid = getattr(ch, "id", None) or (ch.get("id") if isinstance(ch, dict) else None)
|
||||
nid = getattr(ch, "note_id", None) or (ch.get("note_id") if isinstance(ch, dict) else fm.get("id"))
|
||||
index = getattr(ch, "index", None) or (ch.get("index") if isinstance(ch, dict) else idx)
|
||||
@@ -112,7 +151,7 @@ def make_chunk_payloads(note: Dict[str, Any],
|
||||
pl: Dict[str, Any] = {
|
||||
"note_id": nid,
|
||||
"chunk_id": cid,
|
||||
"title": title, # <--- HIER: Titel in Payload einfügen
|
||||
"title": title,
|
||||
"index": int(index),
|
||||
"ord": int(index) + 1,
|
||||
"type": note_type,
|
||||
@@ -124,10 +163,11 @@ def make_chunk_payloads(note: Dict[str, Any],
|
||||
"section": getattr(ch, "section", None) or (ch.get("section") if isinstance(ch, dict) else ""),
|
||||
"path": note_path,
|
||||
"source_path": file_path or note_path,
|
||||
"retriever_weight": float(rw),
|
||||
"chunk_profile": cp,
|
||||
"retriever_weight": float(rw),
|
||||
"chunk_profile": cp, # Jetzt endlich mit dem Override-Wert!
|
||||
}
|
||||
# Aufräumen von Alt-Feldern
|
||||
|
||||
# Cleanup
|
||||
for alias in ("chunk_num", "Chunk_Number"):
|
||||
pl.pop(alias, None)
|
||||
|
||||
|
||||
+137
-43
@@ -1,3 +1,13 @@
|
||||
"""
|
||||
FILE: app/core/chunker.py
|
||||
DESCRIPTION: Zerlegt Texte in Chunks (Sliding Window oder nach Headings). Orchestriert die Smart-Edge-Allocation via SemanticAnalyzer.
|
||||
VERSION: 2.9.0 (Feat: Hybrid Strict Splitting with Size Safety)
|
||||
STATUS: Active
|
||||
DEPENDENCIES: app.services.semantic_analyzer, app.core.derive_edges, markdown_it, yaml, asyncio
|
||||
EXTERNAL_CONFIG: config/types.yaml
|
||||
LAST_ANALYSIS: 2025-12-16
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
from dataclasses import dataclass
|
||||
from typing import List, Dict, Optional, Tuple, Any, Set
|
||||
@@ -5,8 +15,6 @@ import re
|
||||
import math
|
||||
import yaml
|
||||
from pathlib import Path
|
||||
from markdown_it import MarkdownIt
|
||||
from markdown_it.token import Token
|
||||
import asyncio
|
||||
import logging
|
||||
|
||||
@@ -93,7 +101,7 @@ class Chunk:
|
||||
suggested_edges: Optional[List[str]] = None
|
||||
|
||||
# ==========================================
|
||||
# 3. PARSING & STRATEGIES (SYNCHRON)
|
||||
# 3. PARSING & STRATEGIES
|
||||
# ==========================================
|
||||
|
||||
def parse_blocks(md_text: str) -> Tuple[List[RawBlock], str]:
|
||||
@@ -114,8 +122,14 @@ def parse_blocks(md_text: str) -> Tuple[List[RawBlock], str]:
|
||||
|
||||
for line in lines:
|
||||
stripped = line.strip()
|
||||
if stripped.startswith('# '):
|
||||
continue
|
||||
if stripped.startswith('# '):
|
||||
if buffer:
|
||||
content = "\n".join(buffer).strip()
|
||||
if content:
|
||||
blocks.append(RawBlock("paragraph", content, None, section_path, current_h2))
|
||||
buffer = []
|
||||
blocks.append(RawBlock("heading", stripped, 1, section_path, current_h2))
|
||||
|
||||
elif stripped.startswith('## '):
|
||||
if buffer:
|
||||
content = "\n".join(buffer).strip()
|
||||
@@ -125,6 +139,15 @@ def parse_blocks(md_text: str) -> Tuple[List[RawBlock], str]:
|
||||
current_h2 = stripped[3:].strip()
|
||||
section_path = f"/{current_h2}"
|
||||
blocks.append(RawBlock("heading", stripped, 2, section_path, current_h2))
|
||||
|
||||
elif stripped.startswith('### '):
|
||||
if buffer:
|
||||
content = "\n".join(buffer).strip()
|
||||
if content:
|
||||
blocks.append(RawBlock("paragraph", content, None, section_path, current_h2))
|
||||
buffer = []
|
||||
blocks.append(RawBlock("heading", stripped, 3, section_path, current_h2))
|
||||
|
||||
elif not stripped:
|
||||
if buffer:
|
||||
content = "\n".join(buffer).strip()
|
||||
@@ -141,6 +164,15 @@ def parse_blocks(md_text: str) -> Tuple[List[RawBlock], str]:
|
||||
|
||||
return blocks, h1_title
|
||||
|
||||
def _create_chunk_obj(chunks_list: List[Chunk], note_id: str, txt: str, win: str, sec: Optional[str], path: str):
|
||||
idx = len(chunks_list)
|
||||
chunks_list.append(Chunk(
|
||||
id=f"{note_id}#c{idx:02d}", note_id=note_id, index=idx,
|
||||
text=txt, window=win, token_count=estimate_tokens(txt),
|
||||
section_title=sec, section_path=path, neighbors_prev=None, neighbors_next=None,
|
||||
suggested_edges=[]
|
||||
))
|
||||
|
||||
def _strategy_sliding_window(blocks: List[RawBlock], config: Dict[str, Any], note_id: str, doc_title: str = "", context_prefix: str = "") -> List[Chunk]:
|
||||
target = config.get("target", 400)
|
||||
max_tokens = config.get("max", 600)
|
||||
@@ -148,15 +180,6 @@ def _strategy_sliding_window(blocks: List[RawBlock], config: Dict[str, Any], not
|
||||
overlap = sum(overlap_val) // 2 if isinstance(overlap_val, tuple) else overlap_val
|
||||
chunks = []; buf = []
|
||||
|
||||
def _create_chunk(txt, win, sec, path):
|
||||
idx = len(chunks)
|
||||
chunks.append(Chunk(
|
||||
id=f"{note_id}#c{idx:02d}", note_id=note_id, index=idx,
|
||||
text=txt, window=win, token_count=estimate_tokens(txt),
|
||||
section_title=sec, section_path=path, neighbors_prev=None, neighbors_next=None,
|
||||
suggested_edges=[]
|
||||
))
|
||||
|
||||
def flush_buffer():
|
||||
nonlocal buf
|
||||
if not buf: return
|
||||
@@ -164,9 +187,14 @@ def _strategy_sliding_window(blocks: List[RawBlock], config: Dict[str, Any], not
|
||||
text_body = "\n\n".join([b.text for b in buf])
|
||||
win_body = f"{context_prefix}\n{text_body}".strip() if context_prefix else text_body
|
||||
|
||||
# Basis-Info vom ersten Block im Buffer
|
||||
sec = buf[0].section_title if buf else None
|
||||
path = buf[0].section_path if buf else "/"
|
||||
|
||||
if estimate_tokens(text_body) <= max_tokens:
|
||||
_create_chunk(text_body, win_body, buf[-1].section_title, buf[-1].section_path)
|
||||
_create_chunk_obj(chunks, note_id, text_body, win_body, sec, path)
|
||||
else:
|
||||
# Fallback: Wenn Block zu groß, intern splitten (Sentence-Level)
|
||||
sentences = split_sentences(text_body)
|
||||
current_chunk_sents = []
|
||||
current_len = 0
|
||||
@@ -176,7 +204,7 @@ def _strategy_sliding_window(blocks: List[RawBlock], config: Dict[str, Any], not
|
||||
if current_len + sent_len > target and current_chunk_sents:
|
||||
c_txt = " ".join(current_chunk_sents)
|
||||
c_win = f"{context_prefix}\n{c_txt}".strip() if context_prefix else c_txt
|
||||
_create_chunk(c_txt, c_win, buf[-1].section_title, buf[-1].section_path)
|
||||
_create_chunk_obj(chunks, note_id, c_txt, c_win, sec, path)
|
||||
|
||||
overlap_sents = []
|
||||
ov_len = 0
|
||||
@@ -197,27 +225,111 @@ def _strategy_sliding_window(blocks: List[RawBlock], config: Dict[str, Any], not
|
||||
if current_chunk_sents:
|
||||
c_txt = " ".join(current_chunk_sents)
|
||||
c_win = f"{context_prefix}\n{c_txt}".strip() if context_prefix else c_txt
|
||||
_create_chunk(c_txt, c_win, buf[-1].section_title, buf[-1].section_path)
|
||||
_create_chunk_obj(chunks, note_id, c_txt, c_win, sec, path)
|
||||
|
||||
buf = []
|
||||
|
||||
for b in blocks:
|
||||
if b.kind == "heading": continue
|
||||
if b.kind == "heading":
|
||||
flush_buffer()
|
||||
|
||||
current_buf_text = "\n\n".join([x.text for x in buf])
|
||||
if estimate_tokens(current_buf_text) + estimate_tokens(b.text) >= target:
|
||||
if buf and (estimate_tokens(current_buf_text) + estimate_tokens(b.text) >= target):
|
||||
flush_buffer()
|
||||
|
||||
buf.append(b)
|
||||
if estimate_tokens(b.text) >= target:
|
||||
flush_buffer()
|
||||
|
||||
|
||||
flush_buffer()
|
||||
return chunks
|
||||
|
||||
def _strategy_by_heading(blocks: List[RawBlock], config: Dict[str, Any], note_id: str, doc_title: str = "") -> List[Chunk]:
|
||||
return _strategy_sliding_window(blocks, config, note_id, doc_title, context_prefix=f"# {doc_title}")
|
||||
"""
|
||||
MODUS: Structured / Heading Split
|
||||
- split_level: Ebene für logische Trennung (z.B. H2).
|
||||
- strict_heading_split:
|
||||
True: Trennt an jedem Header <= split_level.
|
||||
NEU v2.9: Wenn Inhalt > max_tokens, wird trotzdem gesplittet (Safety Split).
|
||||
False: Fasst zusammen bis 'target' erreicht ist.
|
||||
"""
|
||||
split_level = config.get("split_level", 2)
|
||||
target = config.get("target", 400)
|
||||
max_limit = config.get("max", 600)
|
||||
strict_mode = config.get("strict_heading_split", False)
|
||||
|
||||
chunks = []
|
||||
current_chunk_blocks = []
|
||||
|
||||
context_prefix = f"# {doc_title}"
|
||||
|
||||
def has_content(blk_list):
|
||||
return any(b.kind != "heading" for b in blk_list)
|
||||
|
||||
def flush_current_chunk():
|
||||
nonlocal current_chunk_blocks
|
||||
if not current_chunk_blocks:
|
||||
return
|
||||
|
||||
text_body = "\n\n".join([b.text for b in current_chunk_blocks])
|
||||
win_body = f"{context_prefix}\n{text_body}".strip()
|
||||
|
||||
first_b = current_chunk_blocks[0]
|
||||
sec = first_b.section_title
|
||||
path = first_b.section_path
|
||||
|
||||
_create_chunk_obj(chunks, note_id, text_body, win_body, sec, path)
|
||||
current_chunk_blocks = []
|
||||
|
||||
def get_current_size():
|
||||
txt = "\n\n".join([b.text for b in current_chunk_blocks])
|
||||
return estimate_tokens(txt)
|
||||
|
||||
for b in blocks:
|
||||
# 1. Header Logic (Struktur-Trigger)
|
||||
is_splitter = (b.kind == "heading" and b.level is not None and b.level <= split_level)
|
||||
|
||||
if is_splitter:
|
||||
is_higher_hierarchy = (b.level < split_level)
|
||||
|
||||
if strict_mode:
|
||||
# STRICT:
|
||||
# Wir splitten immer, außer der Vor-Chunk ist leer.
|
||||
if current_chunk_blocks and has_content(current_chunk_blocks):
|
||||
flush_current_chunk()
|
||||
current_chunk_blocks.append(b)
|
||||
else:
|
||||
# SOFT:
|
||||
# Split bei Hierarchie-Wechsel ODER wenn voll.
|
||||
if is_higher_hierarchy:
|
||||
flush_current_chunk()
|
||||
current_chunk_blocks.append(b)
|
||||
elif current_chunk_blocks and get_current_size() >= target:
|
||||
flush_current_chunk()
|
||||
current_chunk_blocks.append(b)
|
||||
else:
|
||||
current_chunk_blocks.append(b)
|
||||
else:
|
||||
# 2. Content Logic (Safety Trigger für Monster-Abschnitte)
|
||||
# Bevor wir den Block anhängen: Würde er das Fass zum Überlaufen bringen?
|
||||
# Wir nutzen hier 'max' als harte Grenze für den Safety-Split.
|
||||
current_size = get_current_size()
|
||||
block_size = estimate_tokens(b.text)
|
||||
|
||||
if current_chunk_blocks and (current_size + block_size > max_limit):
|
||||
# NOTBREMSE: Chunk wird zu groß.
|
||||
# Wir splitten hier, auch wenn kein Header da ist.
|
||||
# Der Kontext (Section Title) bleibt erhalten, da er aus `current_h2` kommt (siehe parse_blocks).
|
||||
flush_current_chunk()
|
||||
current_chunk_blocks.append(b)
|
||||
else:
|
||||
current_chunk_blocks.append(b)
|
||||
|
||||
# Letzten Rest flushen
|
||||
flush_current_chunk()
|
||||
|
||||
return chunks
|
||||
|
||||
# ==========================================
|
||||
# 4. ORCHESTRATION (ASYNC) - WP-15 CORE
|
||||
# 4. ORCHESTRATION (ASYNC)
|
||||
# ==========================================
|
||||
|
||||
async def assemble_chunks(note_id: str, md_text: str, note_type: str, config: Optional[Dict] = None) -> List[Chunk]:
|
||||
@@ -245,7 +357,6 @@ async def assemble_chunks(note_id: str, md_text: str, note_type: str, config: Op
|
||||
return []
|
||||
|
||||
if enable_smart_edges:
|
||||
# Hier rufen wir nun die Smart Edge Allocation auf
|
||||
chunks = await _run_smart_edge_allocation(chunks, md_text, note_id, note_type)
|
||||
|
||||
for i, ch in enumerate(chunks):
|
||||
@@ -255,56 +366,40 @@ async def assemble_chunks(note_id: str, md_text: str, note_type: str, config: Op
|
||||
return chunks
|
||||
|
||||
def _extract_all_edges_from_md(md_text: str, note_id: str, note_type: str) -> List[str]:
|
||||
"""
|
||||
Hilfsfunktion: Erstellt einen Dummy-Chunk für den gesamten Text und ruft
|
||||
den Edge-Parser auf, um ALLE Kanten der Notiz zu finden.
|
||||
"""
|
||||
# 1. Dummy Chunk erstellen, der den gesamten Text enthält
|
||||
# Das ist notwendig, da build_edges_for_note Kanten nur aus Chunks extrahiert.
|
||||
dummy_chunk = {
|
||||
"chunk_id": f"{note_id}#full",
|
||||
"text": md_text,
|
||||
"content": md_text, # Sicherstellen, dass der Parser Text findet
|
||||
"content": md_text,
|
||||
"window": md_text,
|
||||
"type": note_type
|
||||
}
|
||||
|
||||
# 2. Aufruf des Parsers (Signatur-Fix!)
|
||||
# derive_edges.py: build_edges_for_note(note_id, chunks, note_level_references=None, include_note_scope_refs=False)
|
||||
raw_edges = build_edges_for_note(
|
||||
note_id,
|
||||
[dummy_chunk],
|
||||
note_level_references=None,
|
||||
include_note_scope_refs=False
|
||||
)
|
||||
|
||||
# 3. Kanten extrahieren
|
||||
all_candidates = set()
|
||||
for e in raw_edges:
|
||||
kind = e.get("kind")
|
||||
target = e.get("target_id")
|
||||
if target and kind not in ["belongs_to", "next", "prev", "backlink"]:
|
||||
all_candidates.add(f"{kind}:{target}")
|
||||
|
||||
return list(all_candidates)
|
||||
|
||||
async def _run_smart_edge_allocation(chunks: List[Chunk], full_text: str, note_id: str, note_type: str) -> List[Chunk]:
|
||||
analyzer = get_semantic_analyzer()
|
||||
|
||||
# A. Alle potenziellen Kanten der Notiz sammeln (über den Dummy-Chunk Trick)
|
||||
candidate_list = _extract_all_edges_from_md(full_text, note_id, note_type)
|
||||
|
||||
if not candidate_list:
|
||||
return chunks
|
||||
|
||||
# B. LLM Filterung pro Chunk (Parallel)
|
||||
tasks = []
|
||||
for chunk in chunks:
|
||||
tasks.append(analyzer.assign_edges_to_chunk(chunk.text, candidate_list, note_type))
|
||||
|
||||
results_per_chunk = await asyncio.gather(*tasks)
|
||||
|
||||
# C. Injection & Fallback
|
||||
assigned_edges_global = set()
|
||||
|
||||
for i, confirmed_edges in enumerate(results_per_chunk):
|
||||
@@ -317,7 +412,6 @@ async def _run_smart_edge_allocation(chunks: List[Chunk], full_text: str, note_i
|
||||
chunk.text += injection_str
|
||||
chunk.window += injection_str
|
||||
|
||||
# D. Fallback: Unassigned Kanten überall hin
|
||||
unassigned = set(candidate_list) - assigned_edges_global
|
||||
if unassigned:
|
||||
fallback_str = "\n" + " ".join([f"[[rel:{e.split(':')[0]}|{e.split(':')[1]}]]" for e in unassigned if ':' in e])
|
||||
|
||||
@@ -1,26 +1,11 @@
|
||||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
"""
|
||||
Modul: app/core/derive_edges.py
|
||||
Zweck:
|
||||
- Bewahrt bestehende Edgelogik (belongs_to, prev/next, references, backlink)
|
||||
- Ergänzt typenbasierte Default-Kanten (edge_defaults aus config/types.yaml)
|
||||
- Unterstützt "typed inline relations":
|
||||
* [[rel:KIND | Target]]
|
||||
* [[rel:KIND Target]]
|
||||
* rel: KIND [[Target]]
|
||||
- Unterstützt Obsidian-Callouts:
|
||||
* > [!edge] KIND: [[Target]] [[Target2]] ...
|
||||
Kompatibilität:
|
||||
- build_edges_for_note(...) Signatur unverändert
|
||||
- rule_id Werte:
|
||||
* structure:belongs_to
|
||||
* structure:order
|
||||
* explicit:wikilink
|
||||
* inline:rel
|
||||
* callout:edge
|
||||
* edge_defaults:<type>:<relation>
|
||||
* derived:backlink
|
||||
FILE: app/core/derive_edges.py
|
||||
DESCRIPTION: Extrahiert Graph-Kanten aus Text. Unterstützt Wikilinks, Inline-Relations ([[rel:type|target]]) und Obsidian Callouts.
|
||||
VERSION: 2.0.0
|
||||
STATUS: Active
|
||||
DEPENDENCIES: re, os, yaml, typing
|
||||
EXTERNAL_CONFIG: config/types.yaml
|
||||
LAST_ANALYSIS: 2025-12-15
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
@@ -1,296 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
"""
|
||||
Modul: app/core/edges.py
|
||||
Version: 2.0.0 (V2‑superset, rückwärtskompatibel zu v1 vom 2025‑09‑09)
|
||||
|
||||
Zweck
|
||||
-----
|
||||
Bewahrt die bestehende Edgelogik (belongs_to, prev/next, references, backlink)
|
||||
und ergänzt V2‑Felder + Typ‑Default‑Kanten gemäß config/types.yaml (edge_defaults).
|
||||
Die Funktion ist **idempotent** und **rückwärtskompatibel** zur bisherigen Signatur.
|
||||
|
||||
Kompatibilitätsgarantien (gegenüber v1):
|
||||
- **Input**: akzeptiert identische Chunk‑Payloads wie v1:
|
||||
* `id` (Chunk‑ID), `note_id` (Owner), `neighbors.prev|next` (optional),
|
||||
`references: [{target_id: ...}]` (optional),
|
||||
alternativ: `chunk_id`, `chunk_index|ord`, `window|text`
|
||||
- **Output (v1‑Felder)**: `kind`, `source_id`, `target_id`, `scope`, `note_id`, `edge_id`
|
||||
- **Neu (v2‑Felder)**: `relation`, `src_note_id`, `src_chunk_id?`, `dst_note_id`, `dst_chunk_id?`,
|
||||
`provenance` (`explicit|rule`), `rule_id?`, `confidence?`
|
||||
|
||||
Regeln
|
||||
------
|
||||
- Deduplizierungsschlüssel: (source_id, target_id, relation, rule_id)
|
||||
- Strukturkanten:
|
||||
* belongs_to: 1× pro Chunk
|
||||
* next/prev: Sequenz der Chunks; nutzt bevorzugt neighbors; sonst ord/chunk_index
|
||||
- Explizite Referenzen:
|
||||
* aus Chunk: `references[].target_id` (falls vorhanden)
|
||||
* Fallback: Wikilinks in `window|text`: [[Some Title|some-id]] oder [[some-id]]
|
||||
- Note‑Scope:
|
||||
* backlink immer; references nur, wenn include_note_scope_refs=True
|
||||
- Typ‑Defaults (edge_defaults aus config/types.yaml des **Quell‑Notiztyps**):
|
||||
* Für jede explizite Referenz wird je default‑Relation eine Regel‑Kante erzeugt
|
||||
* rule_id: "type_default:{note_type}:{relation}:v1", provenance="rule"
|
||||
|
||||
Konfiguration
|
||||
-------------
|
||||
- ENV MINDNET_TYPES_FILE (Default: ./config/types.yaml)
|
||||
|
||||
Lizenz/Autor
|
||||
------------
|
||||
- Erstimplementierung v1 (2025‑09‑09) — Projekt Mindnet
|
||||
- Erweiterung v2 (2025‑11‑11) — kompatible Superset‑Implementierung
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import re
|
||||
from typing import Dict, Iterable, List, Optional, Tuple, Set
|
||||
|
||||
try:
|
||||
import yaml # optional, nur für types.yaml
|
||||
except Exception: # pragma: no cover
|
||||
yaml = None
|
||||
|
||||
# ------------------------------------------------------------
|
||||
# Hilfen: types.yaml laden (edge_defaults)
|
||||
# ------------------------------------------------------------
|
||||
|
||||
def _types_path() -> str:
|
||||
return os.getenv("MINDNET_TYPES_FILE") or "./config/types.yaml"
|
||||
|
||||
def _load_types() -> Dict[str, dict]:
|
||||
p = _types_path()
|
||||
if not os.path.isfile(p) or yaml is None:
|
||||
return {}
|
||||
try:
|
||||
with open(p, "r", encoding="utf-8") as f:
|
||||
data = yaml.safe_load(f) or {}
|
||||
if isinstance(data, dict) and "types" in data and isinstance(data["types"], dict):
|
||||
return data["types"]
|
||||
return data if isinstance(data, dict) else {}
|
||||
except Exception:
|
||||
return {}
|
||||
|
||||
def _edge_defaults_for(note_type: Optional[str]) -> List[str]:
|
||||
types = _load_types()
|
||||
t = (note_type or "").strip().lower()
|
||||
cfg = types.get(t) or {}
|
||||
defaults = cfg.get("edge_defaults") or []
|
||||
if isinstance(defaults, str):
|
||||
defaults = [defaults]
|
||||
return [str(x) for x in defaults if isinstance(x, (str, int, float))]
|
||||
|
||||
# ------------------------------------------------------------
|
||||
# Wikilink‑Parser (Fallback, wenn ch["references"] fehlt)
|
||||
# ------------------------------------------------------------
|
||||
|
||||
_WIKILINK_RE = re.compile(r"\[\[(?:[^\|\]]+\|)?([a-zA-Z0-9_\-#:. ]+)\]\]")
|
||||
|
||||
def _extract_wikilinks(text: str) -> List[str]:
|
||||
ids: List[str] = []
|
||||
for m in _WIKILINK_RE.finditer(text or ""):
|
||||
ids.append(m.group(1).strip())
|
||||
return ids
|
||||
|
||||
# ------------------------------------------------------------
|
||||
# Utility
|
||||
# ------------------------------------------------------------
|
||||
|
||||
def _mk_edge_id(kind: str, s: str, t: str, scope: str, rule_id: Optional[str] = None) -> str:
|
||||
base = f"{kind}:{s}->{t}#{scope}"
|
||||
if rule_id:
|
||||
base += f"|{rule_id}"
|
||||
try:
|
||||
import hashlib
|
||||
return hashlib.blake2s(base.encode("utf-8"), digest_size=12).hexdigest()
|
||||
except Exception: # pragma: no cover
|
||||
return base
|
||||
|
||||
def _dedupe(edges: List[Dict]) -> List[Dict]:
|
||||
seen: Set[Tuple[str,str,str,str]] = set()
|
||||
out: List[Dict] = []
|
||||
for e in edges:
|
||||
s = str(e.get("source_id") or "")
|
||||
t = str(e.get("target_id") or "")
|
||||
rel = str(e.get("relation") or e.get("kind") or "edge")
|
||||
rule = str(e.get("rule_id") or "")
|
||||
key = (s, t, rel, rule)
|
||||
if key in seen:
|
||||
continue
|
||||
seen.add(key)
|
||||
out.append(e)
|
||||
return out
|
||||
|
||||
def _first(v: dict, *keys, default=None):
|
||||
for k in keys:
|
||||
if k in v and v[k] is not None:
|
||||
return v[k]
|
||||
return default
|
||||
|
||||
# ------------------------------------------------------------
|
||||
# Hauptfunktion
|
||||
# ------------------------------------------------------------
|
||||
|
||||
def build_edges_for_note(
|
||||
note_id: str,
|
||||
chunk_payloads: List[Dict],
|
||||
note_level_refs: Optional[List[str]] = None,
|
||||
*,
|
||||
include_note_scope_refs: bool = False,
|
||||
) -> List[Dict]:
|
||||
edges: List[Dict] = []
|
||||
chunks = list(chunk_payloads or [])
|
||||
# Notiztyp aus erstem Chunk ableiten (kompatibel zu existierenden Payloads)
|
||||
note_type = (chunks[0].get("type") if chunks else None) or (chunks[0].get("note_type") if chunks else None)
|
||||
|
||||
# --- Strukturkanten ------------------------------------------------------
|
||||
# belongs_to
|
||||
for ch in chunks:
|
||||
cid = _first(ch, "id", "chunk_id")
|
||||
if not cid:
|
||||
continue
|
||||
owner = ch.get("note_id") or note_id
|
||||
e = {
|
||||
"edge_id": _mk_edge_id("belongs_to", cid, note_id, "chunk", "structure:belongs_to:v1"),
|
||||
"kind": "belongs_to",
|
||||
"relation": "belongs_to",
|
||||
"scope": "chunk",
|
||||
"source_id": cid,
|
||||
"target_id": note_id,
|
||||
"note_id": owner, # v1-Kompat
|
||||
# v2
|
||||
"src_note_id": owner,
|
||||
"src_chunk_id": cid,
|
||||
"dst_note_id": note_id,
|
||||
"provenance": "rule",
|
||||
"rule_id": "structure:belongs_to:v1",
|
||||
"confidence": 1.0,
|
||||
}
|
||||
edges.append(e)
|
||||
|
||||
# next/prev — bevorzugt neighbors.prev/next; sonst via ord/chunk_index
|
||||
# Map der Chunks nach Index
|
||||
ordered = list(chunks)
|
||||
def _idx(c):
|
||||
return _first(c, "chunk_index", "ord", default=0)
|
||||
ordered.sort(key=_idx)
|
||||
|
||||
for i, ch in enumerate(ordered):
|
||||
cid = _first(ch, "id", "chunk_id")
|
||||
if not cid:
|
||||
continue
|
||||
owner = ch.get("note_id") or note_id
|
||||
nb = ch.get("neighbors") or {}
|
||||
prev_id = nb.get("prev")
|
||||
next_id = nb.get("next")
|
||||
# Fallback-Reihenfolge
|
||||
if prev_id is None and i > 0:
|
||||
prev_id = _first(ordered[i-1], "id", "chunk_id")
|
||||
if next_id is None and i+1 < len(ordered):
|
||||
next_id = _first(ordered[i+1], "id", "chunk_id")
|
||||
|
||||
if prev_id:
|
||||
edges.append({
|
||||
"edge_id": _mk_edge_id("prev", cid, prev_id, "chunk", "structure:order:v1"),
|
||||
"kind": "prev", "relation": "prev", "scope": "chunk",
|
||||
"source_id": cid, "target_id": prev_id, "note_id": owner,
|
||||
"src_note_id": owner, "src_chunk_id": cid,
|
||||
"dst_note_id": owner, "dst_chunk_id": prev_id,
|
||||
"provenance": "rule", "rule_id": "structure:order:v1", "confidence": 0.95,
|
||||
})
|
||||
edges.append({
|
||||
"edge_id": _mk_edge_id("next", prev_id, cid, "chunk", "structure:order:v1"),
|
||||
"kind": "next", "relation": "next", "scope": "chunk",
|
||||
"source_id": prev_id, "target_id": cid, "note_id": owner,
|
||||
"src_note_id": owner, "src_chunk_id": prev_id,
|
||||
"dst_note_id": owner, "dst_chunk_id": cid,
|
||||
"provenance": "rule", "rule_id": "structure:order:v1", "confidence": 0.95,
|
||||
})
|
||||
|
||||
# --- Explizite Referenzen (Chunk‑Scope) ---------------------------------
|
||||
explicit_refs: List[Dict] = []
|
||||
for ch in chunks:
|
||||
cid = _first(ch, "id", "chunk_id")
|
||||
if not cid:
|
||||
continue
|
||||
owner = ch.get("note_id") or note_id
|
||||
# 1) bevorzugt vorhandene ch["references"]
|
||||
refs = ch.get("references") or []
|
||||
targets = [r.get("target_id") for r in refs if isinstance(r, dict) and r.get("target_id")]
|
||||
# 2) Fallback: Wikilinks aus Text
|
||||
if not targets:
|
||||
text = _first(ch, "window", "text", default="") or ""
|
||||
targets = _extract_wikilinks(text)
|
||||
for tid in targets:
|
||||
if not isinstance(tid, str) or not tid.strip():
|
||||
continue
|
||||
e = {
|
||||
"edge_id": _mk_edge_id("references", cid, tid, "chunk"),
|
||||
"kind": "references",
|
||||
"relation": "references",
|
||||
"scope": "chunk",
|
||||
"source_id": cid,
|
||||
"target_id": tid,
|
||||
"note_id": owner,
|
||||
# v2
|
||||
"src_note_id": owner,
|
||||
"src_chunk_id": cid,
|
||||
"dst_note_id": tid,
|
||||
"provenance": "explicit",
|
||||
"rule_id": "",
|
||||
"confidence": 1.0,
|
||||
}
|
||||
edges.append(e)
|
||||
explicit_refs.append(e)
|
||||
|
||||
# --- Note‑Scope: references (optional) + backlink (immer) ----------------
|
||||
unique_refs = []
|
||||
if note_level_refs:
|
||||
seen = set()
|
||||
for tid in note_level_refs:
|
||||
if isinstance(tid, str) and tid.strip() and tid not in seen:
|
||||
unique_refs.append(tid); seen.add(tid)
|
||||
|
||||
for tid in unique_refs:
|
||||
if include_note_scope_refs:
|
||||
edges.append({
|
||||
"edge_id": _mk_edge_id("references", note_id, tid, "note"),
|
||||
"kind": "references", "relation": "references", "scope": "note",
|
||||
"source_id": note_id, "target_id": tid, "note_id": note_id,
|
||||
"src_note_id": note_id, "dst_note_id": tid,
|
||||
"provenance": "explicit", "rule_id": "", "confidence": 1.0,
|
||||
})
|
||||
edges.append({
|
||||
"edge_id": _mk_edge_id("backlink", tid, note_id, "note", "derived:backlink:v1"),
|
||||
"kind": "backlink", "relation": "backlink", "scope": "note",
|
||||
"source_id": tid, "target_id": note_id, "note_id": note_id,
|
||||
"src_note_id": tid, "dst_note_id": note_id,
|
||||
"provenance": "rule", "rule_id": "derived:backlink:v1", "confidence": 0.9,
|
||||
})
|
||||
|
||||
# --- Type‑Defaults je expliziter Referenz --------------------------------
|
||||
defaults = [d for d in _edge_defaults_for(note_type) if d and d != "references"]
|
||||
if defaults:
|
||||
for e in explicit_refs + ([ ] if not include_note_scope_refs else []):
|
||||
# wir nutzen die bereits erzeugten explicit‑Edges als Vorlage
|
||||
src = e["source_id"]; tgt = e["target_id"]
|
||||
scope = e.get("scope", "chunk")
|
||||
s_note = e.get("src_note_id") or note_id
|
||||
s_chunk = e.get("src_chunk_id")
|
||||
t_note = e.get("dst_note_id") or tgt
|
||||
for rel in defaults:
|
||||
rule_id = f"type_default:{(note_type or 'unknown')}:{rel}:v1"
|
||||
edges.append({
|
||||
"edge_id": _mk_edge_id(rel, src, tgt, scope, rule_id),
|
||||
"kind": rel, "relation": rel, "scope": scope,
|
||||
"source_id": src, "target_id": tgt, "note_id": s_note,
|
||||
"src_note_id": s_note, "src_chunk_id": s_chunk,
|
||||
"dst_note_id": t_note,
|
||||
"provenance": "rule", "rule_id": rule_id, "confidence": 0.7,
|
||||
})
|
||||
|
||||
# --- Dedupe & Return -----------------------------------------------------
|
||||
return _dedupe(edges)
|
||||
@@ -1,94 +0,0 @@
|
||||
# app/core/edges_writer.py
|
||||
from __future__ import annotations
|
||||
import hashlib
|
||||
from typing import Dict, List, Iterable, Tuple
|
||||
|
||||
try:
|
||||
# Dein Modul mit der Schemadefinition und der Builder-Funktion
|
||||
from app.core.edges import build_edges_for_note # noqa: F401
|
||||
except Exception as e:
|
||||
raise RuntimeError("Konnte app.core.edges nicht importieren. "
|
||||
"Bitte sicherstellen, dass app/core/edges.py vorhanden ist.") from e
|
||||
|
||||
def _edge_uid(kind: str, source_id: str, target_id: str, scope: str) -> str:
|
||||
"""
|
||||
Deterministische, kurze ID für eine Edge.
|
||||
Kollisionen sind praktisch ausgeschlossen (BLAKE2s über den Kanonischen Schlüssel).
|
||||
"""
|
||||
key = f"{kind}|{source_id}|{target_id}|{scope}"
|
||||
return hashlib.blake2s(key.encode("utf-8"), digest_size=12).hexdigest()
|
||||
|
||||
def ensure_edges_collection(qdrant_client, collection: str) -> None:
|
||||
"""
|
||||
Legt die Edge-Collection an, falls sie nicht existiert.
|
||||
Minimal: 1D-Vector (Dummy), Cosine. Payload-only-Collections sind je nach Qdrant-Version heikel.
|
||||
"""
|
||||
from qdrant_client.http import models as qm
|
||||
|
||||
existing = [c.name for c in qdrant_client.get_collections().collections]
|
||||
if collection in existing:
|
||||
return
|
||||
|
||||
qdrant_client.recreate_collection(
|
||||
collection_name=collection,
|
||||
vectors_config=qm.VectorParams(size=1, distance=qm.Distance.COSINE),
|
||||
on_disk_payload=True,
|
||||
)
|
||||
|
||||
def edges_from_note(
|
||||
note_id: str,
|
||||
chunk_payloads: List[Dict],
|
||||
note_level_refs: Iterable[str] | None,
|
||||
*,
|
||||
include_note_scope_refs: bool = False,
|
||||
) -> List[Dict]:
|
||||
"""
|
||||
Ruft deinen Edge-Builder auf und gibt die (deduplizierten) Edge-Payloads zurück.
|
||||
Keine Schemaänderung – exakt das aus app/core/edges.py.
|
||||
"""
|
||||
return build_edges_for_note(
|
||||
note_id=note_id,
|
||||
chunk_payloads=chunk_payloads,
|
||||
note_level_refs=list(note_level_refs or []),
|
||||
include_note_scope_refs=include_note_scope_refs,
|
||||
)
|
||||
|
||||
def upsert_edges(
|
||||
qdrant_client,
|
||||
collection: str,
|
||||
edge_payloads: List[Dict],
|
||||
) -> Tuple[int, int]:
|
||||
"""
|
||||
Schreibt Edges als Points in Qdrant.
|
||||
- id: deterministisch aus (kind, source_id, target_id, scope)
|
||||
- vector: [0.0] Dummy
|
||||
- payload: Edge-Dict (unverändert, siehe Schema in app/core/edges.py)
|
||||
Gibt (anzahl_points, anzahl_unique_keys) zurück.
|
||||
"""
|
||||
from qdrant_client.models import PointStruct
|
||||
|
||||
if not edge_payloads:
|
||||
return 0, 0
|
||||
|
||||
points = []
|
||||
seen = set()
|
||||
for e in edge_payloads:
|
||||
key = (e.get("kind"), e.get("source_id"), e.get("target_id"), e.get("scope"))
|
||||
if key in seen:
|
||||
continue
|
||||
seen.add(key)
|
||||
eid = _edge_uid(*key)
|
||||
points.append(
|
||||
PointStruct(
|
||||
id=eid,
|
||||
vector=[0.0],
|
||||
payload=e,
|
||||
)
|
||||
)
|
||||
|
||||
if not points:
|
||||
return 0, 0
|
||||
|
||||
ensure_edges_collection(qdrant_client, collection)
|
||||
qdrant_client.upsert(collection_name=collection, points=points)
|
||||
return len(points), len(seen)
|
||||
@@ -1,82 +0,0 @@
|
||||
from __future__ import annotations
|
||||
import os, time, json
|
||||
import urllib.request
|
||||
from typing import List, Dict, Any
|
||||
|
||||
# Backend-Auswahl:
|
||||
# - EMBED_BACKEND=ollama -> EMBED_URL=/api/embeddings (Ollama), EMBED_MODEL=z.B. nomic-embed-text
|
||||
# - EMBED_BACKEND=mini -> EMBED_URL=/embed (unser MiniLM-Server), EMBED_MODEL=minilm-384
|
||||
EMBED_BACKEND = os.getenv("EMBED_BACKEND", "mini").lower()
|
||||
EMBED_URL = os.getenv("EMBED_URL", "http://127.0.0.1:8990/embed")
|
||||
EMBED_MODEL = os.getenv("EMBED_MODEL", "minilm-384")
|
||||
EMBED_BATCH = int(os.getenv("EMBED_BATCH", "64"))
|
||||
TIMEOUT = 60
|
||||
|
||||
class EmbedError(RuntimeError): ...
|
||||
|
||||
def _post_json(url: str, payload: Dict[str, Any]) -> Dict[str, Any]:
|
||||
data = json.dumps(payload).encode("utf-8")
|
||||
req = urllib.request.Request(url, data=data, headers={"Content-Type": "application/json"})
|
||||
with urllib.request.urlopen(req, timeout=TIMEOUT) as resp:
|
||||
return json.loads(resp.read().decode("utf-8"))
|
||||
|
||||
def _embed_mini(inputs: List[str], model: str, batch: int) -> List[List[float]]:
|
||||
out: List[List[float]] = []
|
||||
i = 0
|
||||
while i < len(inputs):
|
||||
chunk = inputs[i:i+batch]
|
||||
# einfache Retries
|
||||
for attempt in range(5):
|
||||
try:
|
||||
resp = _post_json(EMBED_URL, {"model": model, "inputs": chunk})
|
||||
vecs = resp.get("embeddings") or resp.get("vectors") or resp.get("data")
|
||||
if not isinstance(vecs, list):
|
||||
raise EmbedError(f"Bad embed response keys: {list(resp.keys())}")
|
||||
out.extend(vecs)
|
||||
break
|
||||
except Exception:
|
||||
if attempt == 4:
|
||||
raise
|
||||
time.sleep(1.5 * (attempt + 1))
|
||||
i += batch
|
||||
return out
|
||||
|
||||
def _embed_ollama(inputs: List[str], model: str, batch: int) -> List[List[float]]:
|
||||
# Ollama /api/embeddings akzeptiert "input" als String ODER Array.
|
||||
# Die Response enthält:
|
||||
# - für single input: {"embedding":[...], "model":"...", ...}
|
||||
# - für array input: {"embeddings":[[...],[...],...], "model":"...", ...} (je nach Version)
|
||||
# Um maximal kompatibel zu sein, rufen wir pro Text einzeln auf.
|
||||
out: List[List[float]] = []
|
||||
for text in inputs:
|
||||
# Retries
|
||||
for attempt in range(5):
|
||||
try:
|
||||
resp = _post_json(EMBED_URL, {"model": model, "input": text})
|
||||
if "embedding" in resp and isinstance(resp["embedding"], list):
|
||||
out.append(resp["embedding"])
|
||||
elif "embeddings" in resp and isinstance(resp["embeddings"], list):
|
||||
# Falls Server array zurückgibt, nimm das erste Element
|
||||
vecs = resp["embeddings"]
|
||||
out.append(vecs[0] if vecs else [])
|
||||
else:
|
||||
raise EmbedError(f"Ollama response unexpected keys: {list(resp.keys())}")
|
||||
break
|
||||
except Exception:
|
||||
if attempt == 4:
|
||||
raise
|
||||
time.sleep(1.5 * (attempt + 1))
|
||||
return out
|
||||
|
||||
def embed_texts(texts: List[str], model: str | None = None, batch_size: int | None = None) -> List[List[float]]:
|
||||
model = model or EMBED_MODEL
|
||||
batch = batch_size or EMBED_BATCH
|
||||
if not texts:
|
||||
return []
|
||||
if EMBED_BACKEND == "ollama":
|
||||
return _embed_ollama(texts, model, batch)
|
||||
# default: mini
|
||||
return _embed_mini(texts, model, batch)
|
||||
|
||||
def embed_one(text: str, model: str | None = None) -> List[float]:
|
||||
return embed_texts([text], model=model, batch_size=1)[0]
|
||||
@@ -1,103 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
"""
|
||||
Datei: app/core/env_vars.py
|
||||
Version: 1.1.0 (2025-11-08)
|
||||
|
||||
Zweck
|
||||
Einheitliche Auflösung von ENV-Variablen (Prefix, Qdrant, Embeddings, Hashing)
|
||||
mit Abwärtskompatibilität.
|
||||
|
||||
Grundsatz
|
||||
- Für Qdrant-Funktionen ist 'COLLECTION_PREFIX' der Primärschlüssel.
|
||||
- 'MINDNET_PREFIX' bleibt für App-/UI-/Exporter-Kontexte nutzbar.
|
||||
- Fallbacks sorgen dafür, dass ältere Umgebungen weiter funktionieren.
|
||||
|
||||
Wichtig
|
||||
- Lädt optional eine .env (wenn python-dotenv verfügbar ist).
|
||||
- Überschreibt keine bereits gesetzten OS-Variablen (override=False).
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
from typing import Optional, Dict
|
||||
|
||||
# Optional: .env automatisch laden (ohne Hard-Fail, falls nicht vorhanden)
|
||||
try:
|
||||
from dotenv import load_dotenv, find_dotenv # type: ignore
|
||||
_p = find_dotenv()
|
||||
if _p:
|
||||
load_dotenv(_p, override=False)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
# -------- Prefix-Auflösung --------
|
||||
|
||||
def get_collection_prefix(cli_override: Optional[str] = None) -> str:
|
||||
"""
|
||||
Für Qdrant-relevante Funktionen:
|
||||
1) CLI-Override (--prefix)
|
||||
2) ENV COLLECTION_PREFIX
|
||||
3) ENV MINDNET_PREFIX (Fallback)
|
||||
4) 'mindnet' (Default)
|
||||
"""
|
||||
if cli_override and str(cli_override).strip():
|
||||
return str(cli_override).strip()
|
||||
return (
|
||||
os.getenv("COLLECTION_PREFIX")
|
||||
or os.getenv("MINDNET_PREFIX")
|
||||
or "mindnet"
|
||||
)
|
||||
|
||||
def get_mindnet_prefix(cli_override: Optional[str] = None) -> str:
|
||||
"""
|
||||
Für App-/UI-/Exporter-Kontexte:
|
||||
1) CLI-Override (--prefix)
|
||||
2) ENV MINDNET_PREFIX
|
||||
3) ENV COLLECTION_PREFIX (Fallback)
|
||||
4) 'mindnet'
|
||||
"""
|
||||
if cli_override and str(cli_override).strip():
|
||||
return str(cli_override).strip()
|
||||
return (
|
||||
os.getenv("MINDNET_PREFIX")
|
||||
or os.getenv("COLLECTION_PREFIX")
|
||||
or "mindnet"
|
||||
)
|
||||
|
||||
def get_prefix(cli_override: Optional[str] = None, target: str = "qdrant") -> str:
|
||||
"""
|
||||
Universelle Hülle (abwärtskompatibel):
|
||||
target='qdrant' -> get_collection_prefix
|
||||
target='app' -> get_mindnet_prefix
|
||||
"""
|
||||
if target.lower() == "app":
|
||||
return get_mindnet_prefix(cli_override)
|
||||
return get_collection_prefix(cli_override)
|
||||
|
||||
# -------- Qdrant / Embeddings / Hashing --------
|
||||
|
||||
def get_qdrant_url(default: str = "http://127.0.0.1:6333") -> str:
|
||||
return os.getenv("QDRANT_URL", default)
|
||||
|
||||
def get_qdrant_api_key(default: str = "") -> str:
|
||||
return os.getenv("QDRANT_API_KEY", default)
|
||||
|
||||
def get_vector_dim(default: int = 384) -> int:
|
||||
try:
|
||||
return int(os.getenv("VECTOR_DIM", str(default)))
|
||||
except Exception:
|
||||
return default
|
||||
|
||||
def get_embed_url(default: Optional[str] = None) -> Optional[str]:
|
||||
return os.getenv("EMBED_URL", default)
|
||||
|
||||
def get_hash_env() -> Dict[str, str]:
|
||||
"""
|
||||
Liefert die Hash-Konfiguration (nur Aggregation; die Auswertung bleibt in den Skripten).
|
||||
"""
|
||||
return {
|
||||
"MINDNET_HASH_COMPARE": os.getenv("MINDNET_HASH_COMPARE", ""),
|
||||
"MINDNET_HASH_SOURCE": os.getenv("MINDNET_HASH_SOURCE", ""),
|
||||
"MINDNET_HASH_NORMALIZE": os.getenv("MINDNET_HASH_NORMALIZE", ""),
|
||||
}
|
||||
@@ -1,17 +1,10 @@
|
||||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
"""
|
||||
app/core/graph_adapter.py — Adjazenzaufbau & Subgraph-Expansion
|
||||
|
||||
Zweck:
|
||||
Baut aus Qdrant-Edges (Collection: *_edges) einen leichten In-Memory-Graph.
|
||||
|
||||
Kompatibilität:
|
||||
- WP-04a: Liefert Scores (edge_bonus, centrality).
|
||||
- WP-04b: Liefert jetzt auch Struktur-Daten für Erklärungen (Reverse-Lookup).
|
||||
|
||||
Version:
|
||||
0.4.0 (Update für WP-04b: Reverse Adjacency für Explainability)
|
||||
FILE: app/core/graph_adapter.py
|
||||
DESCRIPTION: Lädt Kanten aus Qdrant und baut einen In-Memory Subgraphen für Scoring (Centrality) und Explanation.
|
||||
VERSION: 0.4.0
|
||||
STATUS: Active
|
||||
DEPENDENCIES: qdrant_client, app.core.qdrant
|
||||
LAST_ANALYSIS: 2025-12-15
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
+110
-83
@@ -1,8 +1,12 @@
|
||||
"""
|
||||
app/core/ingestion.py
|
||||
|
||||
Zentraler Service für die Transformation von Markdown-Dateien in Qdrant-Objekte.
|
||||
Version: 2.5.2 (Full Feature: Change Detection + Robust IO + Clean Config)
|
||||
FILE: app/core/ingestion.py
|
||||
DESCRIPTION: Haupt-Ingestion-Logik.
|
||||
FIX: Korrekte Priorisierung von Frontmatter für chunk_profile und retriever_weight.
|
||||
Lade Chunk-Config basierend auf dem effektiven Profil, nicht nur dem Notiz-Typ.
|
||||
VERSION: 2.7.0 (Fix: Frontmatter Overrides & Config Loading)
|
||||
STATUS: Active
|
||||
DEPENDENCIES: app.core.parser, app.core.note_payload, app.core.chunker, app.core.derive_edges, app.core.qdrant*, app.services.embeddings_client
|
||||
EXTERNAL_CONFIG: config/types.yaml
|
||||
"""
|
||||
import os
|
||||
import logging
|
||||
@@ -52,16 +56,42 @@ def resolve_note_type(requested: Optional[str], reg: dict) -> str:
|
||||
if requested and requested in types: return requested
|
||||
return "concept"
|
||||
|
||||
def effective_chunk_profile(note_type: str, reg: dict) -> str:
|
||||
t_cfg = reg.get("types", {}).get(note_type, {})
|
||||
if t_cfg and t_cfg.get("chunk_profile"):
|
||||
return t_cfg.get("chunk_profile")
|
||||
return reg.get("defaults", {}).get("chunk_profile", "default")
|
||||
def effective_chunk_profile_name(fm: dict, note_type: str, reg: dict) -> str:
|
||||
"""
|
||||
Ermittelt den Namen des Chunk-Profils.
|
||||
Prio: 1. Frontmatter -> 2. Type-Config -> 3. Default
|
||||
"""
|
||||
# 1. Frontmatter Override
|
||||
override = fm.get("chunking_profile") or fm.get("chunk_profile")
|
||||
if override and isinstance(override, str):
|
||||
return override
|
||||
|
||||
def effective_retriever_weight(note_type: str, reg: dict) -> float:
|
||||
# 2. Type Config
|
||||
t_cfg = reg.get("types", {}).get(note_type, {})
|
||||
if t_cfg:
|
||||
cp = t_cfg.get("chunking_profile") or t_cfg.get("chunk_profile")
|
||||
if cp: return cp
|
||||
|
||||
# 3. Global Default
|
||||
return reg.get("defaults", {}).get("chunking_profile", "sliding_standard")
|
||||
|
||||
def effective_retriever_weight(fm: dict, note_type: str, reg: dict) -> float:
|
||||
"""
|
||||
Ermittelt das Retriever Weight.
|
||||
Prio: 1. Frontmatter -> 2. Type-Config -> 3. Default
|
||||
"""
|
||||
# 1. Frontmatter Override
|
||||
override = fm.get("retriever_weight")
|
||||
if override is not None:
|
||||
try: return float(override)
|
||||
except: pass
|
||||
|
||||
# 2. Type Config
|
||||
t_cfg = reg.get("types", {}).get(note_type, {})
|
||||
if t_cfg and "retriever_weight" in t_cfg:
|
||||
return float(t_cfg["retriever_weight"])
|
||||
|
||||
# 3. Global Default
|
||||
return float(reg.get("defaults", {}).get("retriever_weight", 1.0))
|
||||
|
||||
|
||||
@@ -77,12 +107,32 @@ class IngestionService:
|
||||
self.registry = load_type_registry()
|
||||
self.embedder = EmbeddingsClient()
|
||||
|
||||
# ACTIVE HASH MODE aus ENV lesen (Default: full)
|
||||
self.active_hash_mode = os.getenv("MINDNET_CHANGE_DETECTION_MODE", "full")
|
||||
|
||||
try:
|
||||
ensure_collections(self.client, self.prefix, self.dim)
|
||||
ensure_payload_indexes(self.client, self.prefix)
|
||||
except Exception as e:
|
||||
logger.warning(f"DB init warning: {e}")
|
||||
|
||||
def _get_chunk_config_by_profile(self, profile_name: str, note_type: str) -> Dict[str, Any]:
|
||||
"""
|
||||
Lädt die konkrete Config (target, max, overlap) für einen Profilnamen.
|
||||
"""
|
||||
# Suche direkt in den definierten Profilen der Registry
|
||||
profiles = self.registry.get("chunking_profiles", {})
|
||||
if profile_name in profiles:
|
||||
cfg = profiles[profile_name].copy()
|
||||
# Tuple-Fix für Overlap (wie in chunker.py)
|
||||
if "overlap" in cfg and isinstance(cfg["overlap"], list):
|
||||
cfg["overlap"] = tuple(cfg["overlap"])
|
||||
return cfg
|
||||
|
||||
# Fallback: Wenn Profilname unbekannt, nutze Standard für den Typ via Chunker
|
||||
logger.warning(f"Profile '{profile_name}' not found in registry. Falling back to type defaults.")
|
||||
return get_chunk_config(note_type)
|
||||
|
||||
async def process_file(
|
||||
self,
|
||||
file_path: str,
|
||||
@@ -91,72 +141,71 @@ class IngestionService:
|
||||
apply: bool = False,
|
||||
purge_before: bool = False,
|
||||
note_scope_refs: bool = False,
|
||||
hash_mode: str = "body",
|
||||
hash_source: str = "parsed",
|
||||
hash_normalize: str = "canonical"
|
||||
) -> Dict[str, Any]:
|
||||
"""
|
||||
Verarbeitet eine einzelne Datei (ASYNC).
|
||||
Inklusive Change Detection (Hash-Check) gegen Qdrant.
|
||||
"""
|
||||
result = {
|
||||
"path": file_path,
|
||||
"status": "skipped",
|
||||
"changed": False,
|
||||
"error": None
|
||||
}
|
||||
|
||||
result = {"path": file_path, "status": "skipped", "changed": False, "error": None}
|
||||
|
||||
# 1. Parse & Frontmatter Validation
|
||||
try:
|
||||
parsed = read_markdown(file_path)
|
||||
if not parsed:
|
||||
return {**result, "error": "Empty or unreadable file"}
|
||||
|
||||
if not parsed: return {**result, "error": "Empty or unreadable file"}
|
||||
fm = normalize_frontmatter(parsed.frontmatter)
|
||||
validate_required_frontmatter(fm)
|
||||
except Exception as e:
|
||||
logger.error(f"Validation failed for {file_path}: {e}")
|
||||
return {**result, "error": f"Validation failed: {str(e)}"}
|
||||
|
||||
# 2. Type & Config Resolution
|
||||
# 2. Type & Config Resolution (FIXED)
|
||||
# Wir ermitteln erst den Typ
|
||||
note_type = resolve_note_type(fm.get("type"), self.registry)
|
||||
fm["type"] = note_type
|
||||
fm["chunk_profile"] = effective_chunk_profile(note_type, self.registry)
|
||||
|
||||
weight = fm.get("retriever_weight")
|
||||
if weight is None:
|
||||
weight = effective_retriever_weight(note_type, self.registry)
|
||||
fm["retriever_weight"] = float(weight)
|
||||
# Dann ermitteln wir die effektiven Werte unter Berücksichtigung des Frontmatters!
|
||||
# Hier lag der Fehler: Vorher wurde einfach überschrieben.
|
||||
effective_profile = effective_chunk_profile_name(fm, note_type, self.registry)
|
||||
effective_weight = effective_retriever_weight(fm, note_type, self.registry)
|
||||
|
||||
# Wir schreiben die effektiven Werte zurück ins FM, damit note_payload sie sicher hat
|
||||
fm["chunk_profile"] = effective_profile
|
||||
fm["retriever_weight"] = effective_weight
|
||||
|
||||
# 3. Build Note Payload
|
||||
try:
|
||||
note_pl = make_note_payload(
|
||||
parsed,
|
||||
vault_root=vault_root,
|
||||
hash_mode=hash_mode,
|
||||
hash_normalize=hash_normalize,
|
||||
hash_source=hash_source,
|
||||
file_path=file_path
|
||||
)
|
||||
if not note_pl.get("fulltext"):
|
||||
note_pl["fulltext"] = getattr(parsed, "body", "") or ""
|
||||
note_pl["retriever_weight"] = fm["retriever_weight"]
|
||||
# Text Body Fallback
|
||||
if not note_pl.get("fulltext"): note_pl["fulltext"] = getattr(parsed, "body", "") or ""
|
||||
|
||||
# Update Payload with explicit effective values (Sicherheit)
|
||||
note_pl["retriever_weight"] = effective_weight
|
||||
note_pl["chunk_profile"] = effective_profile
|
||||
|
||||
note_id = note_pl["note_id"]
|
||||
except Exception as e:
|
||||
logger.error(f"Payload build failed: {e}")
|
||||
return {**result, "error": f"Payload build failed: {str(e)}"}
|
||||
|
||||
# 4. Change Detection (Das fehlende Stück!)
|
||||
# 4. Change Detection
|
||||
old_payload = None
|
||||
if not force_replace:
|
||||
old_payload = self._fetch_note_payload(note_id)
|
||||
|
||||
has_old = old_payload is not None
|
||||
key_current = f"{hash_mode}:{hash_source}:{hash_normalize}"
|
||||
old_hash = (old_payload or {}).get("hashes", {}).get(key_current)
|
||||
new_hash = note_pl.get("hashes", {}).get(key_current)
|
||||
check_key = f"{self.active_hash_mode}:{hash_source}:{hash_normalize}"
|
||||
|
||||
old_hashes = (old_payload or {}).get("hashes")
|
||||
if isinstance(old_hashes, dict): old_hash = old_hashes.get(check_key)
|
||||
elif isinstance(old_hashes, str) and self.active_hash_mode == "body": old_hash = old_hashes
|
||||
else: old_hash = None
|
||||
|
||||
new_hash = note_pl.get("hashes", {}).get(check_key)
|
||||
hash_changed = (old_hash != new_hash)
|
||||
chunks_missing, edges_missing = self._artifacts_missing(note_id)
|
||||
|
||||
@@ -168,18 +217,19 @@ class IngestionService:
|
||||
if not apply:
|
||||
return {**result, "status": "dry-run", "changed": True, "note_id": note_id}
|
||||
|
||||
# 5. Processing (Chunking, Embedding, Edges)
|
||||
# 5. Processing
|
||||
try:
|
||||
body_text = getattr(parsed, "body", "") or ""
|
||||
|
||||
# --- Config Loading (Clean) ---
|
||||
chunk_config = get_chunk_config(note_type)
|
||||
# Hier greift die Logik aus types.yaml (smart=True/False)
|
||||
# FIX: Wir laden jetzt die Config für das SPEZIFISCHE Profil
|
||||
# (z.B. wenn User "sliding_short" wollte, laden wir dessen Params)
|
||||
chunk_config = self._get_chunk_config_by_profile(effective_profile, note_type)
|
||||
|
||||
chunks = await assemble_chunks(fm["id"], body_text, fm["type"], config=chunk_config)
|
||||
|
||||
# chunk_payloads werden mit den aktualisierten FM-Werten gebaut
|
||||
chunk_pls = make_chunk_payloads(fm, note_pl["path"], chunks, note_text=body_text)
|
||||
|
||||
# Embedding
|
||||
vecs = []
|
||||
if chunk_pls:
|
||||
texts = [c.get("window") or c.get("text") or "" for c in chunk_pls]
|
||||
@@ -194,7 +244,6 @@ class IngestionService:
|
||||
logger.error(f"Embedding failed: {e}")
|
||||
raise RuntimeError(f"Embedding failed: {e}")
|
||||
|
||||
# Edges
|
||||
try:
|
||||
edges = build_edges_for_note(
|
||||
note_id,
|
||||
@@ -209,7 +258,7 @@ class IngestionService:
|
||||
logger.error(f"Processing failed: {e}", exc_info=True)
|
||||
return {**result, "error": f"Processing failed: {str(e)}"}
|
||||
|
||||
# 6. Upsert Action
|
||||
# 6. Upsert
|
||||
try:
|
||||
if purge_before and has_old:
|
||||
self._purge_artifacts(note_id)
|
||||
@@ -236,9 +285,8 @@ class IngestionService:
|
||||
except Exception as e:
|
||||
logger.error(f"Upsert failed: {e}", exc_info=True)
|
||||
return {**result, "error": f"DB Upsert failed: {e}"}
|
||||
|
||||
# --- Qdrant Helper (Restored) ---
|
||||
|
||||
|
||||
# ... (Restliche Methoden wie _fetch_note_payload bleiben unverändert) ...
|
||||
def _fetch_note_payload(self, note_id: str) -> Optional[dict]:
|
||||
from qdrant_client.http import models as rest
|
||||
col = f"{self.prefix}_notes"
|
||||
@@ -268,38 +316,17 @@ class IngestionService:
|
||||
self.client.delete(collection_name=f"{self.prefix}_{suffix}", points_selector=selector)
|
||||
except Exception: pass
|
||||
|
||||
async def create_from_text(
|
||||
self,
|
||||
markdown_content: str,
|
||||
filename: str,
|
||||
vault_root: str,
|
||||
folder: str = "00_Inbox"
|
||||
) -> Dict[str, Any]:
|
||||
"""
|
||||
WP-11 Persistence API Entrypoint.
|
||||
"""
|
||||
target_dir = os.path.join(vault_root, folder)
|
||||
os.makedirs(target_dir, exist_ok=True)
|
||||
|
||||
file_path = os.path.join(target_dir, filename)
|
||||
|
||||
try:
|
||||
# Robust Write: Ensure Flush & Sync
|
||||
with open(file_path, "w", encoding="utf-8") as f:
|
||||
f.write(markdown_content)
|
||||
f.flush()
|
||||
os.fsync(f.fileno())
|
||||
|
||||
await asyncio.sleep(0.1)
|
||||
|
||||
logger.info(f"Written file to {file_path}")
|
||||
except Exception as e:
|
||||
return {"status": "error", "error": f"Disk write failed: {str(e)}"}
|
||||
|
||||
return await self.process_file(
|
||||
file_path=file_path,
|
||||
vault_root=vault_root,
|
||||
apply=True,
|
||||
force_replace=True,
|
||||
purge_before=True
|
||||
)
|
||||
async def create_from_text(self, markdown_content: str, filename: str, vault_root: str, folder: str = "00_Inbox") -> Dict[str, Any]:
|
||||
target_dir = os.path.join(vault_root, folder)
|
||||
os.makedirs(target_dir, exist_ok=True)
|
||||
file_path = os.path.join(target_dir, filename)
|
||||
try:
|
||||
with open(file_path, "w", encoding="utf-8") as f:
|
||||
f.write(markdown_content)
|
||||
f.flush()
|
||||
os.fsync(f.fileno())
|
||||
await asyncio.sleep(0.1)
|
||||
logger.info(f"Written file to {file_path}")
|
||||
except Exception as e:
|
||||
return {"status": "error", "error": f"Disk write failed: {str(e)}"}
|
||||
return await self.process_file(file_path=file_path, vault_root=vault_root, apply=True, force_replace=True, purge_before=True)
|
||||
+82
-50
@@ -1,17 +1,13 @@
|
||||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
"""
|
||||
Modul: app/core/note_payload.py
|
||||
Version: 2.1.0 (WP-11 Update: Aliases support)
|
||||
|
||||
Zweck
|
||||
-----
|
||||
Erzeugt ein robustes Note-Payload. Werte wie `retriever_weight`, `chunk_profile`
|
||||
und `edge_defaults` werden in folgender Priorität bestimmt:
|
||||
1) Frontmatter (Note)
|
||||
2) Typ-Registry (config/types.yaml: types.<type>.*)
|
||||
3) Registry-Defaults (config/types.yaml: defaults.*)
|
||||
4) ENV-Defaults (MINDNET_DEFAULT_RETRIEVER_WEIGHT / MINDNET_DEFAULT_CHUNK_PROFILE)
|
||||
FILE: app/core/note_payload.py
|
||||
DESCRIPTION: Baut das JSON-Objekt.
|
||||
FEATURES:
|
||||
1. Multi-Hash: Berechnet immer 'body' AND 'full' Hashes für flexible Change Detection.
|
||||
2. Config-Fix: Liest korrekt 'chunking_profile' aus types.yaml (statt Legacy 'chunk_profile').
|
||||
VERSION: 2.3.0
|
||||
STATUS: Active
|
||||
DEPENDENCIES: yaml, os, json, pathlib, hashlib
|
||||
EXTERNAL_CONFIG: config/types.yaml
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
@@ -20,6 +16,7 @@ from typing import Any, Dict, Tuple, Optional
|
||||
import os
|
||||
import json
|
||||
import pathlib
|
||||
import hashlib
|
||||
|
||||
try:
|
||||
import yaml # type: ignore
|
||||
@@ -37,7 +34,6 @@ def _as_dict(x) -> Dict[str, Any]:
|
||||
return dict(x)
|
||||
|
||||
out: Dict[str, Any] = {}
|
||||
# bekannte Attribute übernehmen, sofern vorhanden
|
||||
for attr in (
|
||||
"frontmatter",
|
||||
"body",
|
||||
@@ -56,7 +52,6 @@ def _as_dict(x) -> Dict[str, Any]:
|
||||
if val is not None:
|
||||
out[attr] = val
|
||||
|
||||
# Fallback: wenn immer noch leer, raw speichern
|
||||
if not out:
|
||||
out["raw"] = str(x)
|
||||
|
||||
@@ -64,14 +59,12 @@ def _as_dict(x) -> Dict[str, Any]:
|
||||
|
||||
|
||||
def _pick_args(*args, **kwargs) -> Tuple[Optional[str], Optional[dict]]:
|
||||
"""Extrahiert optionale Zusatzargumente wie path und types_cfg."""
|
||||
path = kwargs.get("path") or (args[0] if args else None)
|
||||
types_cfg = kwargs.get("types_cfg") or kwargs.get("types") or None
|
||||
return path, types_cfg
|
||||
|
||||
|
||||
def _env_float(name: str, default: float) -> float:
|
||||
"""Liest einen Float-Wert aus der Umgebung, mit robustem Fallback."""
|
||||
try:
|
||||
return float(os.environ.get(name, default))
|
||||
except Exception:
|
||||
@@ -79,7 +72,6 @@ def _env_float(name: str, default: float) -> float:
|
||||
|
||||
|
||||
def _ensure_list(x) -> list:
|
||||
"""Garantiert eine String-Liste."""
|
||||
if x is None:
|
||||
return []
|
||||
if isinstance(x, list):
|
||||
@@ -88,13 +80,44 @@ def _ensure_list(x) -> list:
|
||||
return [str(i) for i in x]
|
||||
return [str(x)]
|
||||
|
||||
# --- Hash Logic ---
|
||||
def _compute_hash(content: str) -> str:
|
||||
"""Berechnet einen SHA-256 Hash für den gegebenen String."""
|
||||
if not content:
|
||||
return ""
|
||||
return hashlib.sha256(content.encode("utf-8")).hexdigest()
|
||||
|
||||
def _get_hash_source_content(n: Dict[str, Any], mode: str) -> str:
|
||||
"""
|
||||
Stellt den String zusammen, der gehasht werden soll.
|
||||
"""
|
||||
body = str(n.get("body") or "")
|
||||
|
||||
if mode == "body":
|
||||
return body
|
||||
|
||||
if mode == "full":
|
||||
fm = n.get("frontmatter") or {}
|
||||
# Wichtig: Sortierte Keys für deterministisches Verhalten!
|
||||
# Wir nehmen alle steuernden Metadaten auf
|
||||
meta_parts = []
|
||||
# Hier checken wir keys, die eine Neu-Indizierung rechtfertigen würden
|
||||
for k in sorted(["title", "type", "status", "tags", "chunking_profile", "chunk_profile", "retriever_weight"]):
|
||||
val = fm.get(k)
|
||||
if val is not None:
|
||||
meta_parts.append(f"{k}:{val}")
|
||||
|
||||
meta_str = "|".join(meta_parts)
|
||||
return f"{meta_str}||{body}"
|
||||
|
||||
return body
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Type-Registry laden
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def _load_types_config(explicit_cfg: Optional[dict] = None) -> dict:
|
||||
"""Lädt die Type-Registry aus YAML/JSON oder nutzt ein explizit übergebenes Dict."""
|
||||
if explicit_cfg and isinstance(explicit_cfg, dict):
|
||||
return explicit_cfg
|
||||
|
||||
@@ -111,7 +134,6 @@ def _load_types_config(explicit_cfg: Optional[dict] = None) -> dict:
|
||||
|
||||
|
||||
def _cfg_for_type(note_type: str, reg: dict) -> dict:
|
||||
"""Liefert die Konfiguration für einen konkreten Notiztyp aus der Registry."""
|
||||
if not isinstance(reg, dict):
|
||||
return {}
|
||||
types = reg.get("types") if isinstance(reg.get("types"), dict) else reg
|
||||
@@ -119,7 +141,6 @@ def _cfg_for_type(note_type: str, reg: dict) -> dict:
|
||||
|
||||
|
||||
def _cfg_defaults(reg: dict) -> dict:
|
||||
"""Liefert den Default-Block aus der Registry (defaults/global)."""
|
||||
if not isinstance(reg, dict):
|
||||
return {}
|
||||
for key in ("defaults", "default", "global"):
|
||||
@@ -136,20 +157,15 @@ def _cfg_defaults(reg: dict) -> dict:
|
||||
def make_note_payload(note: Any, *args, **kwargs) -> Dict[str, Any]:
|
||||
"""
|
||||
Baut das Note-Payload für mindnet_notes auf.
|
||||
|
||||
Erwartete Felder im Payload:
|
||||
- note_id: stabile ID aus Frontmatter (id) oder Note-Objekt
|
||||
- title: Titel der Notiz
|
||||
- type: Notiztyp (z. B. concept, project, journal, ...)
|
||||
- path: Pfad im Vault
|
||||
- retriever_weight: effektives Gewicht für den Retriever
|
||||
- chunk_profile: Profil für Chunking (short|medium|long|default|...)
|
||||
- edge_defaults: Liste von Kanten-Typen, die als Defaults gelten
|
||||
- aliases: Liste von Synonymen (WP-11)
|
||||
Inkludiert Hash-Berechnung (Body & Full) und korrigierte Config-Lookups.
|
||||
"""
|
||||
n = _as_dict(note)
|
||||
path_arg, types_cfg_explicit = _pick_args(*args, **kwargs)
|
||||
reg = _load_types_config(types_cfg_explicit)
|
||||
|
||||
# Hash Config (Parameter für Source/Normalize, Mode ist hardcoded auf 'beide')
|
||||
hash_source = kwargs.get("hash_source", "parsed")
|
||||
hash_normalize = kwargs.get("hash_normalize", "canonical")
|
||||
|
||||
fm = n.get("frontmatter") or {}
|
||||
fm_type = fm.get("type") or n.get("type") or "concept"
|
||||
@@ -158,7 +174,7 @@ def make_note_payload(note: Any, *args, **kwargs) -> Dict[str, Any]:
|
||||
cfg_type = _cfg_for_type(note_type, reg)
|
||||
cfg_def = _cfg_defaults(reg)
|
||||
|
||||
# --- retriever_weight: Frontmatter > Typ-Config > Registry-Defaults > ENV ---
|
||||
# --- retriever_weight ---
|
||||
default_rw = _env_float("MINDNET_DEFAULT_RETRIEVER_WEIGHT", 1.0)
|
||||
retriever_weight = fm.get("retriever_weight")
|
||||
if retriever_weight is None:
|
||||
@@ -171,20 +187,23 @@ def make_note_payload(note: Any, *args, **kwargs) -> Dict[str, Any]:
|
||||
except Exception:
|
||||
retriever_weight = default_rw
|
||||
|
||||
# --- chunk_profile: Frontmatter > Typ-Config > Registry-Defaults > ENV ---
|
||||
chunk_profile = fm.get("chunk_profile")
|
||||
# --- chunk_profile (FIXED LOGIC) ---
|
||||
# 1. Frontmatter Override (beide Schreibweisen erlaubt)
|
||||
chunk_profile = fm.get("chunking_profile") or fm.get("chunk_profile")
|
||||
|
||||
# 2. Type Config (Korrekter Key 'chunking_profile' aus types.yaml)
|
||||
if chunk_profile is None:
|
||||
chunk_profile = cfg_type.get(
|
||||
"chunk_profile",
|
||||
cfg_def.get(
|
||||
"chunk_profile",
|
||||
os.environ.get("MINDNET_DEFAULT_CHUNK_PROFILE", "medium"),
|
||||
),
|
||||
)
|
||||
if not isinstance(chunk_profile, str):
|
||||
chunk_profile = "medium"
|
||||
chunk_profile = cfg_type.get("chunking_profile")
|
||||
|
||||
# --- edge_defaults: Frontmatter > Typ-Config > Registry-Defaults ---
|
||||
# 3. Default Config (Fallback auf sliding_standard statt medium)
|
||||
if chunk_profile is None:
|
||||
chunk_profile = cfg_def.get("chunking_profile", "sliding_standard")
|
||||
|
||||
# 4. Safety Fallback
|
||||
if not isinstance(chunk_profile, str) or not chunk_profile:
|
||||
chunk_profile = "sliding_standard"
|
||||
|
||||
# --- edge_defaults ---
|
||||
edge_defaults = fm.get("edge_defaults")
|
||||
if edge_defaults is None:
|
||||
edge_defaults = cfg_type.get(
|
||||
@@ -193,7 +212,7 @@ def make_note_payload(note: Any, *args, **kwargs) -> Dict[str, Any]:
|
||||
)
|
||||
edge_defaults = _ensure_list(edge_defaults)
|
||||
|
||||
# --- Basis-Metadaten (IDs, Titel, Pfad) ---
|
||||
# --- Basis-Metadaten ---
|
||||
note_id = n.get("note_id") or n.get("id") or fm.get("id")
|
||||
title = n.get("title") or fm.get("title") or ""
|
||||
path = n.get("path") or path_arg
|
||||
@@ -208,29 +227,42 @@ def make_note_payload(note: Any, *args, **kwargs) -> Dict[str, Any]:
|
||||
"retriever_weight": retriever_weight,
|
||||
"chunk_profile": chunk_profile,
|
||||
"edge_defaults": edge_defaults,
|
||||
"hashes": {} # Init Hash Dict
|
||||
}
|
||||
|
||||
# --- MULTI-HASH CALCULATION (Strategy Decoupling) ---
|
||||
# Wir berechnen immer BEIDE Strategien und speichern sie.
|
||||
# ingestion.py entscheidet dann anhand der ENV-Variable, welcher verglichen wird.
|
||||
modes_to_calc = ["body", "full"]
|
||||
|
||||
for mode in modes_to_calc:
|
||||
content_to_hash = _get_hash_source_content(n, mode)
|
||||
computed_hash = _compute_hash(content_to_hash)
|
||||
# Key Schema: mode:source:normalize (z.B. "full:parsed:canonical")
|
||||
key = f"{mode}:{hash_source}:{hash_normalize}"
|
||||
payload["hashes"][key] = computed_hash
|
||||
|
||||
# Tags / Keywords übernehmen
|
||||
# Tags / Keywords
|
||||
tags = fm.get("tags") or fm.get("keywords") or n.get("tags")
|
||||
if tags:
|
||||
payload["tags"] = _ensure_list(tags)
|
||||
|
||||
# WP-11: Aliases übernehmen (für Discovery Service)
|
||||
# Aliases
|
||||
aliases = fm.get("aliases")
|
||||
if aliases:
|
||||
payload["aliases"] = _ensure_list(aliases)
|
||||
|
||||
# Zeitliche Metadaten (sofern vorhanden)
|
||||
# Zeit
|
||||
for k in ("created", "modified", "date"):
|
||||
v = fm.get(k) or n.get(k)
|
||||
if v:
|
||||
payload[k] = str(v)
|
||||
|
||||
# Fulltext (Fallback, falls body im Input)
|
||||
# Fulltext
|
||||
if "body" in n and n["body"]:
|
||||
payload["fulltext"] = str(n["body"])
|
||||
|
||||
# JSON-Roundtrip zur harten Validierung (ASCII beibehalten)
|
||||
# JSON Validation
|
||||
json.loads(json.dumps(payload, ensure_ascii=False))
|
||||
|
||||
return payload
|
||||
+6
-39
@@ -1,43 +1,10 @@
|
||||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
"""
|
||||
Modul: app/core/parser.py
|
||||
Version: 1.7.1 (fault-tolerant, API-kompatibel)
|
||||
Datum: 2025-10-01
|
||||
|
||||
Zweck
|
||||
-----
|
||||
Fehlertolerantes Einlesen von Markdown-Dateien mit YAML-Frontmatter.
|
||||
Kompatibel zur bisherigen Parser-API, aber robust gegenüber Nicht-UTF-8-Dateien:
|
||||
- Versucht nacheinander: utf-8 → utf-8-sig → cp1252 → latin-1.
|
||||
- Bei Fallback wird ein JSON-Warnhinweis auf stdout ausgegeben; der Import bricht NICHT ab.
|
||||
- YAML-Frontmatter wird mit '---' am Anfang und '---' als Abschluss erkannt.
|
||||
- extract_wikilinks() normalisiert [[id#anchor|label]] → 'id'.
|
||||
|
||||
Öffentliche API (kompatibel):
|
||||
- class ParsedNote(frontmatter: dict, body: str, path: str)
|
||||
- read_markdown(path) -> ParsedNote | None
|
||||
- normalize_frontmatter(fm) -> dict
|
||||
- validate_required_frontmatter(fm, required: tuple[str,...]=("id","title")) -> None
|
||||
- extract_wikilinks(text) -> list[str]
|
||||
- FRONTMATTER_RE (Kompatibilitäts-Konstante; Regex für '---'-Zeilen)
|
||||
|
||||
Beispiele
|
||||
---------
|
||||
from app.core.parser import read_markdown, normalize_frontmatter, validate_required_frontmatter
|
||||
parsed = read_markdown("./vault/30_projects/project-demo.md")
|
||||
fm = normalize_frontmatter(parsed.frontmatter)
|
||||
validate_required_frontmatter(fm)
|
||||
body = parsed.body
|
||||
|
||||
from app.core.parser import extract_wikilinks
|
||||
links = extract_wikilinks(body)
|
||||
|
||||
Abhängigkeiten
|
||||
--------------
|
||||
- PyYAML (yaml)
|
||||
|
||||
Lizenz: MIT (projektintern)
|
||||
FILE: app/core/parser.py
|
||||
DESCRIPTION: Liest Markdown-Dateien fehlertolerant (Encoding-Fallback). Trennt Frontmatter (YAML) vom Body.
|
||||
VERSION: 1.7.1
|
||||
STATUS: Active
|
||||
DEPENDENCIES: yaml, re, dataclasses, json, io, os
|
||||
LAST_ANALYSIS: 2025-12-15
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
|
||||
+6
-24
@@ -1,28 +1,10 @@
|
||||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
"""
|
||||
app/core/qdrant.py
|
||||
Version: 2.2.0 (2025-11-11)
|
||||
|
||||
Aufgabe
|
||||
-------
|
||||
- Zentraler Qdrant-Zugriff (Client, Config)
|
||||
- Collection-Anlage (notes/chunks/edges)
|
||||
- **Payload-Indizes sicherstellen** (idempotent)
|
||||
|
||||
Hinweis
|
||||
-------
|
||||
Diese Datei ist als Drop-in-Ersatz gedacht, falls in deinem Projekt noch keine
|
||||
robuste ensure_payload_indexes()-Implementierung vorliegt. Die Signaturen
|
||||
bleiben kompatibel zu scripts.import_markdown und scripts.reset_qdrant.
|
||||
|
||||
API-Notizen
|
||||
-----------
|
||||
- Payload-Indizes werden mit `create_payload_index` angelegt.
|
||||
- Typen stammen aus `qdrant_client.http.models.PayloadSchemaType`:
|
||||
KEYWORD | TEXT | INTEGER | FLOAT | BOOL | GEO | DATETIME
|
||||
- Für häufige Filterfelder (note_id, kind, scope, type, tags, ...) legen wir
|
||||
Indizes an. Das ist laut Qdrant-Doku Best Practice für performante Filter.
|
||||
FILE: app/core/qdrant.py
|
||||
DESCRIPTION: Qdrant-Client Factory und Schema-Management. Erstellt Collections und Payload-Indizes.
|
||||
VERSION: 2.2.0
|
||||
STATUS: Active
|
||||
DEPENDENCIES: qdrant_client, dataclasses, os
|
||||
LAST_ANALYSIS: 2025-12-15
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
|
||||
@@ -1,18 +1,10 @@
|
||||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
"""
|
||||
app/core/qdrant_points.py - robust points helpers for Qdrant
|
||||
|
||||
- Single source of truth for building PointStruct for notes/chunks/edges
|
||||
- Backward-compatible payloads for edges
|
||||
- Handles both Single-Vector and Named-Vector collections
|
||||
- Deterministic overrides via ENV to avoid auto-detection traps:
|
||||
* NOTES_VECTOR_NAME, CHUNKS_VECTOR_NAME, EDGES_VECTOR_NAME
|
||||
* MINDNET_VECTOR_NAME (fallback)
|
||||
> Set to a concrete name (e.g. "text") to force Named-Vector with that name
|
||||
> Set to "__single__" (or "single") to force Single-Vector
|
||||
|
||||
Version: 1.5.0 (2025-11-08)
|
||||
FILE: app/core/qdrant_points.py
|
||||
DESCRIPTION: Object-Mapper für Qdrant. Konvertiert JSON-Payloads (Notes, Chunks, Edges) in PointStructs und generiert deterministische UUIDs.
|
||||
VERSION: 1.5.0
|
||||
STATUS: Active
|
||||
DEPENDENCIES: qdrant_client, uuid, os
|
||||
LAST_ANALYSIS: 2025-12-15
|
||||
"""
|
||||
from __future__ import annotations
|
||||
import os
|
||||
|
||||
@@ -1,56 +0,0 @@
|
||||
"""
|
||||
app/core/ranking.py — Kombiniertes Scoring (WP-04)
|
||||
|
||||
Zweck:
|
||||
Zusammenführen von semantischem Score (normalisiert), Edge-Bonus und
|
||||
Centrality-Bonus in einen Gesamtscore für die Ergebnisreihung.
|
||||
Kompatibilität:
|
||||
Python 3.12+
|
||||
Version:
|
||||
0.1.0 (Erstanlage)
|
||||
Stand:
|
||||
2025-10-07
|
||||
Bezug:
|
||||
WP-04 Ranking-Formel (w_sem, w_edge, w_cent)
|
||||
Nutzung:
|
||||
from app.core.ranking import combine_scores
|
||||
Änderungsverlauf:
|
||||
0.1.0 (2025-10-07) – Erstanlage.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
from typing import List, Tuple, Dict
|
||||
|
||||
|
||||
def normalize_scores(values: List[float]) -> List[float]:
|
||||
"""Min-Max-Normalisierung über die Kandidatenmenge (Fallback 0.5 bei Konstanz)."""
|
||||
if not values:
|
||||
return values
|
||||
lo, hi = min(values), max(values)
|
||||
if hi - lo < 1e-9:
|
||||
return [0.5] * len(values)
|
||||
return [(v - lo) / (hi - lo) for v in values]
|
||||
|
||||
|
||||
def combine_scores(
|
||||
hits: List[Tuple[str, float, dict]], # (id, semantic_score, payload)
|
||||
edge_bonus_map: Dict[str, float],
|
||||
centrality_map: Dict[str, float],
|
||||
w_sem: float = 0.70,
|
||||
w_edge: float = 0.25,
|
||||
w_cent: float = 0.05,
|
||||
) -> List[Tuple[str, float, float, float, float]]:
|
||||
"""
|
||||
Liefert Liste von (point_id, total_score, edge_bonus, centrality_bonus, raw_semantic_score),
|
||||
absteigend nach total_score sortiert.
|
||||
"""
|
||||
sem = [h[1] for h in hits]
|
||||
sem_n = normalize_scores(sem)
|
||||
out = []
|
||||
for (pid, s, payload), s_norm in zip(hits, sem_n):
|
||||
e = edge_bonus_map.get(pid, 0.0)
|
||||
c = centrality_map.get(pid, 0.0)
|
||||
total = w_sem * s_norm + w_edge * e + w_cent * c
|
||||
out.append((pid, total, e, c, s))
|
||||
out.sort(key=lambda t: t[1], reverse=True)
|
||||
return out
|
||||
@@ -1,8 +1,10 @@
|
||||
"""
|
||||
app/core/retriever.py — Hybrider Such-Algorithmus
|
||||
|
||||
Version:
|
||||
0.5.3 (WP-06 Fix: Populate 'payload' in QueryHit for meta-data access)
|
||||
FILE: app/core/retriever.py
|
||||
DESCRIPTION: Implementiert die Hybrid-Suche (Vektor + Graph-Expansion) und das Scoring-Modell (Explainability).
|
||||
VERSION: 0.5.3
|
||||
STATUS: Active
|
||||
DEPENDENCIES: app.config, app.models.dto, app.core.qdrant*, app.services.embeddings_client, app.core.graph_adapter
|
||||
LAST_ANALYSIS: 2025-12-15
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
|
||||
@@ -1,116 +0,0 @@
|
||||
"""app/core/retriever_config.py
|
||||
---------------------------------
|
||||
Zentrale Konfiguration für den mindnet-Retriever (WP-04).
|
||||
|
||||
Zweck:
|
||||
- Lädt config/retriever.yaml (falls vorhanden) oder nutzt sinnvolle Defaults.
|
||||
- Bietet einen gecachten Zugriff auf die Retriever-Config für
|
||||
andere Module (z. B. graph_adapter, retriever).
|
||||
|
||||
Hinweis zur Weiterentwicklung (Selbstjustierung):
|
||||
- Die hier definierten Parameter sind so gewählt, dass sie später
|
||||
durch ein Feedback-/Learning-to-Rank-Modell überschrieben werden
|
||||
können, ohne die restliche Architektur anzupassen.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
from dataclasses import dataclass
|
||||
from functools import lru_cache
|
||||
from pathlib import Path
|
||||
from typing import Dict
|
||||
|
||||
try:
|
||||
import yaml # type: ignore
|
||||
except Exception: # pragma: no cover - Fallback, falls PyYAML nicht installiert ist.
|
||||
yaml = None # type: ignore
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class RetrieverConfig:
|
||||
semantic_scale: float
|
||||
edge_scale: float
|
||||
centrality_scale: float
|
||||
edge_weights: Dict[str, float]
|
||||
|
||||
@lru_cache
|
||||
def get_retriever_config() -> RetrieverConfig:
|
||||
"""Lädt die Retriever-Konfiguration (YAML + Defaults).
|
||||
|
||||
Reihenfolge:
|
||||
1. Defaults (sinnvoll gewählte Startwerte).
|
||||
2. Optional: config/retriever.yaml bzw. Pfad aus ENV
|
||||
MINDNET_RETRIEVER_CONFIG überschreibt die Defaults.
|
||||
|
||||
Die Funktion ist bewusst gecached, da sich die Konfiguration zur
|
||||
Laufzeit üblicherweise nicht ändert. Für dynamisches Nachladen
|
||||
könnte der Cache explizit geleert werden.
|
||||
"""
|
||||
|
||||
# 1) Defaults – bewusst konservativ gewählt.
|
||||
semantic_scale = 1.0
|
||||
edge_scale = 1.0
|
||||
centrality_scale = 1.0
|
||||
|
||||
edge_weights: Dict[str, float] = {
|
||||
# Wissens-Kanten
|
||||
"depends_on": 1.0,
|
||||
"related_to": 0.7,
|
||||
"similar_to": 0.7,
|
||||
"references": 0.5,
|
||||
# Struktur-Kanten
|
||||
"belongs_to": 0.2,
|
||||
"next": 0.1,
|
||||
"prev": 0.1,
|
||||
# Sonstige / technische Kanten
|
||||
"backlink": 0.2,
|
||||
"references_at": 0.2,
|
||||
}
|
||||
|
||||
# 2) Optional: YAML-Konfiguration laden
|
||||
cfg_path_env = os.getenv("MINDNET_RETRIEVER_CONFIG")
|
||||
if cfg_path_env:
|
||||
cfg_path = Path(cfg_path_env)
|
||||
else:
|
||||
# Project-Root = zwei Ebenen über app/core/
|
||||
cfg_path = Path(__file__).resolve().parents[2] / "config" / "retriever.yaml"
|
||||
|
||||
if yaml is not None and cfg_path.exists():
|
||||
try:
|
||||
data = yaml.safe_load(cfg_path.read_text(encoding="utf-8")) or {}
|
||||
except Exception:
|
||||
data = {}
|
||||
|
||||
retr = data.get("retriever") or {}
|
||||
|
||||
# Skalenwerte überschreiben, falls angegeben
|
||||
try:
|
||||
semantic_scale = float(retr.get("semantic_scale", semantic_scale))
|
||||
except (TypeError, ValueError):
|
||||
pass
|
||||
|
||||
try:
|
||||
edge_scale = float(retr.get("edge_scale", edge_scale))
|
||||
except (TypeError, ValueError):
|
||||
pass
|
||||
|
||||
try:
|
||||
centrality_scale = float(retr.get("centrality_scale", centrality_scale))
|
||||
except (TypeError, ValueError):
|
||||
pass
|
||||
|
||||
# Edge-Gewichte je Kanten-Typ
|
||||
ew_cfg = retr.get("edge_weights") or {}
|
||||
if isinstance(ew_cfg, dict):
|
||||
for k, v in ew_cfg.items():
|
||||
try:
|
||||
edge_weights[str(k)] = float(v)
|
||||
except (TypeError, ValueError):
|
||||
continue
|
||||
|
||||
return RetrieverConfig(
|
||||
semantic_scale=semantic_scale,
|
||||
edge_scale=edge_scale,
|
||||
centrality_scale=centrality_scale,
|
||||
edge_weights=edge_weights,
|
||||
)
|
||||
@@ -1,22 +0,0 @@
|
||||
from __future__ import annotations
|
||||
import json
|
||||
import os
|
||||
from functools import lru_cache
|
||||
from jsonschema import Draft202012Validator, RefResolver
|
||||
|
||||
SCHEMAS_DIR = os.getenv("SCHEMAS_DIR", os.path.join(os.path.dirname(os.path.dirname(__file__)), "..", "schemas"))
|
||||
|
||||
@lru_cache(maxsize=16)
|
||||
def load_schema(name: str) -> dict:
|
||||
# name: "note.schema.json" | "chunk.schema.json" | "edge.schema.json"
|
||||
path = os.path.join(SCHEMAS_DIR, name)
|
||||
if not os.path.isfile(path):
|
||||
raise FileNotFoundError(f"Schema not found: {path}")
|
||||
with open(path, "r", encoding="utf-8") as f:
|
||||
return json.load(f)
|
||||
|
||||
@lru_cache(maxsize=16)
|
||||
def get_validator(name: str) -> Draft202012Validator:
|
||||
schema = load_schema(name)
|
||||
resolver = RefResolver.from_schema(schema)
|
||||
return Draft202012Validator(schema, resolver=resolver)
|
||||
@@ -1,30 +1,11 @@
|
||||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
"""
|
||||
Modul: app/core/type_registry.py
|
||||
Version: 1.0.0
|
||||
Datum: 2025-11-08
|
||||
|
||||
Zweck
|
||||
-----
|
||||
Lädt eine optionale Typ-Registry (config/types.yaml) und stellt
|
||||
komfortable Zugriffsfunktionen bereit. Die Registry ist *optional*:
|
||||
- Fehlt die Datei oder ist das YAML defekt, wird ein konservativer
|
||||
Default (Typ "concept") verwendet und es wird eine Warnung ausgegeben.
|
||||
- Änderungen an der Datei greifen nach einem Neustart des Prozesses.
|
||||
|
||||
Öffentliche API
|
||||
---------------
|
||||
- load_type_registry(path: str = "config/types.yaml") -> dict
|
||||
- get_type_config(note_type: str, reg: dict) -> dict
|
||||
- resolve_note_type(fm_type: str | None, reg: dict) -> str
|
||||
- effective_chunk_profile(note_type: str, reg: dict) -> str | None
|
||||
- profile_overlap(profile: str | None) -> tuple[int,int] # nur Overlap-Empfehlung
|
||||
|
||||
Hinweis
|
||||
-------
|
||||
Die Registry steuert KEINE Breaking Changes. Ohne Datei/Typ bleibt das
|
||||
Verhalten exakt wie im Release-Stand 20251105.
|
||||
FILE: app/core/type_registry.py
|
||||
DESCRIPTION: Loader für types.yaml. Achtung: Wird in der aktuellen Pipeline meist durch lokale Loader in 'ingestion.py' oder 'note_payload.py' umgangen.
|
||||
VERSION: 1.0.0
|
||||
STATUS: Deprecated (Redundant)
|
||||
DEPENDENCIES: yaml, os, functools
|
||||
EXTERNAL_CONFIG: config/types.yaml
|
||||
LAST_ANALYSIS: 2025-12-15
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
|
||||
@@ -1,16 +0,0 @@
|
||||
from __future__ import annotations
|
||||
from typing import Dict
|
||||
from jsonschema import ValidationError
|
||||
from .schema_loader import get_validator
|
||||
|
||||
NOTE_SCHEMA_NAME = "note.schema.json"
|
||||
|
||||
def validate_note_payload(payload: Dict) -> None:
|
||||
validator = get_validator(NOTE_SCHEMA_NAME)
|
||||
errors = sorted(validator.iter_errors(payload), key=lambda e: e.path)
|
||||
if errors:
|
||||
msgs = []
|
||||
for e in errors:
|
||||
loc = ".".join([str(x) for x in e.path]) or "<root>"
|
||||
msgs.append(f"{loc}: {e.message}")
|
||||
raise ValidationError(" | ".join(msgs))
|
||||
@@ -1,40 +0,0 @@
|
||||
"""
|
||||
Version 1
|
||||
"""
|
||||
from __future__ import annotations
|
||||
from fastapi import FastAPI, HTTPException
|
||||
from pydantic import BaseModel
|
||||
from typing import List, Optional
|
||||
from sentence_transformers import SentenceTransformer
|
||||
|
||||
app = FastAPI(title="mindnet-embed", version="1.0")
|
||||
|
||||
MODEL_NAME = "sentence-transformers/all-MiniLM-L6-v2" # 384-dim
|
||||
_model: SentenceTransformer | None = None
|
||||
|
||||
class EmbedIn(BaseModel):
|
||||
model: Optional[str] = None
|
||||
inputs: List[str]
|
||||
|
||||
class EmbedOut(BaseModel):
|
||||
embeddings: List[List[float]]
|
||||
|
||||
@app.on_event("startup")
|
||||
def _load_model():
|
||||
global _model
|
||||
_model = SentenceTransformer(MODEL_NAME)
|
||||
|
||||
@app.get("/health")
|
||||
def health():
|
||||
return {"ok": True, "model": MODEL_NAME, "dim": 384}
|
||||
|
||||
@app.post("/embed", response_model=EmbedOut)
|
||||
def embed(payload: EmbedIn) -> EmbedOut:
|
||||
if _model is None:
|
||||
raise HTTPException(status_code=503, detail="Model not loaded")
|
||||
if not payload.inputs:
|
||||
return EmbedOut(embeddings=[])
|
||||
vecs = _model.encode(payload.inputs, normalize_embeddings=False).tolist()
|
||||
if any(len(v) != 384 for v in vecs):
|
||||
raise HTTPException(status_code=500, detail="Embedding size mismatch (expected 384)")
|
||||
return EmbedOut(embeddings=vecs)
|
||||
+6
-2
@@ -1,6 +1,10 @@
|
||||
"""
|
||||
Version 0.1
|
||||
|
||||
FILE: app/embeddings.py
|
||||
DESCRIPTION: Lokaler Wrapper für SentenceTransformer Embeddings.
|
||||
VERSION: 0.1.0
|
||||
STATUS: Active (Bestätigung durch Aufrufer erforderlich)
|
||||
DEPENDENCIES: app.config, sentence_transformers
|
||||
LAST_ANALYSIS: 2025-12-15
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
+43
-517
@@ -1,533 +1,59 @@
|
||||
"""
|
||||
FILE: app/frontend/ui.py
|
||||
DESCRIPTION: Main Entrypoint für Streamlit. Router, der basierend auf Sidebar-Auswahl die Module (Chat, Editor, Graph) lädt.
|
||||
VERSION: 2.6.0
|
||||
STATUS: Active
|
||||
DEPENDENCIES: streamlit, ui_config, ui_sidebar, ui_chat, ui_editor, ui_graph_service, ui_graph*, ui_graph_cytoscape
|
||||
LAST_ANALYSIS: 2025-12-15
|
||||
"""
|
||||
|
||||
import streamlit as st
|
||||
import requests
|
||||
import uuid
|
||||
import os
|
||||
import json
|
||||
import re
|
||||
import yaml
|
||||
import unicodedata
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
from dotenv import load_dotenv
|
||||
|
||||
# --- CONFIGURATION ---
|
||||
load_dotenv()
|
||||
API_BASE_URL = os.getenv("MINDNET_API_URL", "http://localhost:8002")
|
||||
CHAT_ENDPOINT = f"{API_BASE_URL}/chat"
|
||||
FEEDBACK_ENDPOINT = f"{API_BASE_URL}/feedback"
|
||||
INGEST_ANALYZE_ENDPOINT = f"{API_BASE_URL}/ingest/analyze"
|
||||
INGEST_SAVE_ENDPOINT = f"{API_BASE_URL}/ingest/save"
|
||||
HISTORY_FILE = Path("data/logs/search_history.jsonl")
|
||||
|
||||
# Timeout Strategy
|
||||
timeout_setting = os.getenv("MINDNET_API_TIMEOUT") or os.getenv("MINDNET_LLM_TIMEOUT")
|
||||
API_TIMEOUT = float(timeout_setting) if timeout_setting else 300.0
|
||||
|
||||
# --- PAGE SETUP ---
|
||||
st.set_page_config(page_title="mindnet v2.5", page_icon="🧠", layout="wide")
|
||||
|
||||
# --- CSS STYLING ---
|
||||
# --- CONFIG & STYLING ---
|
||||
st.set_page_config(page_title="mindnet v2.6", page_icon="🧠", layout="wide")
|
||||
st.markdown("""
|
||||
<style>
|
||||
.block-container { padding-top: 2rem; max_width: 1000px; margin: auto; }
|
||||
|
||||
.intent-badge {
|
||||
background-color: #e8f0fe; color: #1a73e8;
|
||||
padding: 4px 10px; border-radius: 12px;
|
||||
font-size: 0.8rem; font-weight: 600;
|
||||
border: 1px solid #d2e3fc; display: inline-block; margin-bottom: 0.5rem;
|
||||
}
|
||||
|
||||
.draft-box {
|
||||
border: 1px solid #d0d7de;
|
||||
border-radius: 6px;
|
||||
padding: 16px;
|
||||
background-color: #f6f8fa;
|
||||
margin-top: 10px;
|
||||
margin-bottom: 10px;
|
||||
}
|
||||
|
||||
.preview-box {
|
||||
border: 1px solid #e0e0e0;
|
||||
border-radius: 6px;
|
||||
padding: 24px;
|
||||
background-color: white;
|
||||
font-family: -apple-system,BlinkMacSystemFont,"Segoe UI",Helvetica,Arial,sans-serif;
|
||||
}
|
||||
.block-container { padding-top: 2rem; max_width: 1200px; margin: auto; }
|
||||
.intent-badge { background-color: #e8f0fe; color: #1a73e8; padding: 4px 10px; border-radius: 12px; font-size: 0.8rem; font-weight: 600; border: 1px solid #d2e3fc; display: inline-block; margin-bottom: 0.5rem; }
|
||||
.draft-box { border: 1px solid #d0d7de; border-radius: 6px; padding: 16px; background-color: #f6f8fa; margin: 10px 0; }
|
||||
.preview-box { border: 1px solid #e0e0e0; border-radius: 6px; padding: 24px; background-color: white; }
|
||||
</style>
|
||||
""", unsafe_allow_html=True)
|
||||
|
||||
# --- MODULE IMPORTS ---
|
||||
try:
|
||||
from ui_config import QDRANT_URL, QDRANT_KEY, COLLECTION_PREFIX
|
||||
from ui_graph_service import GraphExplorerService
|
||||
|
||||
# Komponenten
|
||||
from ui_sidebar import render_sidebar
|
||||
from ui_chat import render_chat_interface
|
||||
from ui_editor import render_manual_editor
|
||||
|
||||
# Die beiden Graph-Engines
|
||||
from ui_graph import render_graph_explorer as render_graph_agraph
|
||||
from ui_graph_cytoscape import render_graph_explorer_cytoscape # <-- Import
|
||||
|
||||
except ImportError as e:
|
||||
st.error(f"Import Error: {e}. Bitte stelle sicher, dass alle UI-Dateien im Ordner liegen und 'streamlit-cytoscapejs' installiert ist.")
|
||||
st.stop()
|
||||
|
||||
# --- SESSION STATE ---
|
||||
if "messages" not in st.session_state: st.session_state.messages = []
|
||||
if "user_id" not in st.session_state: st.session_state.user_id = str(uuid.uuid4())
|
||||
|
||||
# --- HELPER FUNCTIONS ---
|
||||
# --- SERVICE INIT ---
|
||||
graph_service = GraphExplorerService(QDRANT_URL, QDRANT_KEY, COLLECTION_PREFIX)
|
||||
|
||||
def slugify(value):
|
||||
if not value: return ""
|
||||
value = str(value).lower()
|
||||
replacements = {'ä': 'ae', 'ö': 'oe', 'ü': 'ue', 'ß': 'ss', '&': 'und', '+': 'und'}
|
||||
for k, v in replacements.items():
|
||||
value = value.replace(k, v)
|
||||
|
||||
value = unicodedata.normalize('NFKD', value).encode('ascii', 'ignore').decode('ascii')
|
||||
value = re.sub(r'[^\w\s-]', '', value).strip()
|
||||
return re.sub(r'[-\s]+', '-', value)
|
||||
|
||||
def normalize_meta_and_body(meta, body):
|
||||
ALLOWED_KEYS = {"title", "type", "status", "tags", "id", "created", "updated", "aliases", "lang"}
|
||||
clean_meta = {}
|
||||
extra_content = []
|
||||
|
||||
if "titel" in meta and "title" not in meta:
|
||||
meta["title"] = meta.pop("titel")
|
||||
|
||||
tag_candidates = ["tags", "emotionale_keywords", "keywords", "schluesselwoerter"]
|
||||
all_tags = []
|
||||
for key in tag_candidates:
|
||||
if key in meta:
|
||||
val = meta[key]
|
||||
if isinstance(val, list): all_tags.extend(val)
|
||||
elif isinstance(val, str): all_tags.extend([t.strip() for t in val.split(",")])
|
||||
|
||||
for key, val in meta.items():
|
||||
if key in ALLOWED_KEYS:
|
||||
clean_meta[key] = val
|
||||
elif key in tag_candidates:
|
||||
pass
|
||||
else:
|
||||
if val and isinstance(val, str):
|
||||
header = key.replace("_", " ").title()
|
||||
extra_content.append(f"## {header}\n{val}\n")
|
||||
|
||||
if all_tags:
|
||||
clean_tags = []
|
||||
for t in all_tags:
|
||||
t_clean = str(t).replace("#", "").strip()
|
||||
if t_clean: clean_tags.append(t_clean)
|
||||
clean_meta["tags"] = list(set(clean_tags))
|
||||
|
||||
if extra_content:
|
||||
new_section = "\n".join(extra_content)
|
||||
final_body = f"{new_section}\n{body}"
|
||||
else:
|
||||
final_body = body
|
||||
|
||||
return clean_meta, final_body
|
||||
|
||||
def parse_markdown_draft(full_text):
|
||||
"""
|
||||
HEALING PARSER: Repariert kaputten LLM Output (z.B. fehlendes schließendes '---').
|
||||
"""
|
||||
clean_text = full_text.strip()
|
||||
|
||||
# 1. Code-Block Wrapper entfernen
|
||||
pattern_block = r"```(?:markdown|md|yaml)?\s*(.*?)\s*```"
|
||||
match_block = re.search(pattern_block, clean_text, re.DOTALL | re.IGNORECASE)
|
||||
if match_block:
|
||||
clean_text = match_block.group(1).strip()
|
||||
|
||||
meta = {}
|
||||
body = clean_text
|
||||
yaml_str = ""
|
||||
|
||||
# 2. Versuch A: Standard Split (Idealfall)
|
||||
parts = re.split(r"^---+\s*$", clean_text, maxsplit=2, flags=re.MULTILINE)
|
||||
|
||||
if len(parts) >= 3:
|
||||
yaml_str = parts[1]
|
||||
body = parts[2]
|
||||
|
||||
# 3. Versuch B: Healing (Wenn LLM das schließende --- vergessen hat)
|
||||
elif clean_text.startswith("---"):
|
||||
# Wir suchen die erste Überschrift '#', da Frontmatter davor sein muss
|
||||
# Pattern: Suche --- am Anfang, dann nimm alles bis zum ersten # am Zeilenanfang
|
||||
fallback_match = re.search(r"^---\s*(.*?)(?=\n#)", clean_text, re.DOTALL | re.MULTILINE)
|
||||
if fallback_match:
|
||||
yaml_str = fallback_match.group(1)
|
||||
# Der Body ist alles NACH dem YAML String (inklusive dem #)
|
||||
body = clean_text.replace(f"---{yaml_str}", "", 1).strip()
|
||||
|
||||
# 4. YAML Parsing
|
||||
if yaml_str:
|
||||
yaml_str_clean = yaml_str.replace("#", "") # Tags cleanen
|
||||
try:
|
||||
parsed = yaml.safe_load(yaml_str_clean)
|
||||
if isinstance(parsed, dict):
|
||||
meta = parsed
|
||||
except Exception as e:
|
||||
print(f"YAML Parsing Warning: {e}")
|
||||
|
||||
# Fallback: Titel aus H1
|
||||
if not meta.get("title"):
|
||||
h1_match = re.search(r"^#\s+(.*)$", body, re.MULTILINE)
|
||||
if h1_match:
|
||||
meta["title"] = h1_match.group(1).strip()
|
||||
|
||||
# Correction: type/status swap
|
||||
if meta.get("type") == "draft":
|
||||
meta["status"] = "draft"
|
||||
meta["type"] = "experience"
|
||||
|
||||
return normalize_meta_and_body(meta, body)
|
||||
|
||||
def build_markdown_doc(meta, body):
|
||||
"""Baut das finale Dokument zusammen."""
|
||||
if "id" not in meta or meta["id"] == "generated_on_save":
|
||||
raw_title = meta.get('title', 'note')
|
||||
clean_slug = slugify(raw_title)[:50] or "note"
|
||||
meta["id"] = f"{datetime.now().strftime('%Y%m%d')}-{clean_slug}"
|
||||
|
||||
meta["updated"] = datetime.now().strftime("%Y-%m-%d")
|
||||
|
||||
ordered_meta = {}
|
||||
prio_keys = ["id", "type", "title", "status", "tags"]
|
||||
for k in prio_keys:
|
||||
if k in meta: ordered_meta[k] = meta.pop(k)
|
||||
ordered_meta.update(meta)
|
||||
|
||||
try:
|
||||
yaml_str = yaml.dump(ordered_meta, default_flow_style=None, sort_keys=False, allow_unicode=True).strip()
|
||||
except:
|
||||
yaml_str = "error: generating_yaml"
|
||||
|
||||
return f"---\n{yaml_str}\n---\n\n{body}"
|
||||
|
||||
def load_history_from_logs(limit=10):
|
||||
queries = []
|
||||
if HISTORY_FILE.exists():
|
||||
try:
|
||||
with open(HISTORY_FILE, "r", encoding="utf-8") as f:
|
||||
lines = f.readlines()
|
||||
for line in reversed(lines):
|
||||
try:
|
||||
entry = json.loads(line)
|
||||
q = entry.get("query_text")
|
||||
if q and q not in queries:
|
||||
queries.append(q)
|
||||
if len(queries) >= limit: break
|
||||
except: continue
|
||||
except: pass
|
||||
return queries
|
||||
|
||||
# --- API CLIENT ---
|
||||
|
||||
def send_chat_message(message: str, top_k: int, explain: bool):
|
||||
try:
|
||||
response = requests.post(
|
||||
CHAT_ENDPOINT,
|
||||
json={"message": message, "top_k": top_k, "explain": explain},
|
||||
timeout=API_TIMEOUT
|
||||
)
|
||||
response.raise_for_status()
|
||||
return response.json()
|
||||
except Exception as e:
|
||||
return {"error": str(e)}
|
||||
|
||||
def analyze_draft_text(text: str, n_type: str):
|
||||
try:
|
||||
response = requests.post(
|
||||
INGEST_ANALYZE_ENDPOINT,
|
||||
json={"text": text, "type": n_type},
|
||||
timeout=15
|
||||
)
|
||||
response.raise_for_status()
|
||||
return response.json()
|
||||
except Exception as e:
|
||||
return {"error": str(e)}
|
||||
|
||||
def save_draft_to_vault(markdown_content: str, filename: str = None):
|
||||
try:
|
||||
response = requests.post(
|
||||
INGEST_SAVE_ENDPOINT,
|
||||
json={"markdown_content": markdown_content, "filename": filename},
|
||||
timeout=API_TIMEOUT
|
||||
)
|
||||
response.raise_for_status()
|
||||
return response.json()
|
||||
except Exception as e:
|
||||
return {"error": str(e)}
|
||||
|
||||
def submit_feedback(query_id, node_id, score, comment=None):
|
||||
try:
|
||||
requests.post(FEEDBACK_ENDPOINT, json={"query_id": query_id, "node_id": node_id, "score": score, "comment": comment}, timeout=2)
|
||||
st.toast(f"Feedback ({score}) gesendet!")
|
||||
except: pass
|
||||
|
||||
# --- UI COMPONENTS ---
|
||||
|
||||
def render_sidebar():
|
||||
with st.sidebar:
|
||||
st.title("🧠 mindnet")
|
||||
st.caption("v2.5 | Healing Parser")
|
||||
mode = st.radio("Modus", ["💬 Chat", "📝 Manueller Editor"], index=0)
|
||||
st.divider()
|
||||
st.subheader("⚙️ Settings")
|
||||
top_k = st.slider("Quellen (Top-K)", 1, 10, 5)
|
||||
explain = st.toggle("Explanation Layer", True)
|
||||
st.divider()
|
||||
st.subheader("🕒 Verlauf")
|
||||
for q in load_history_from_logs(8):
|
||||
if st.button(f"🔎 {q[:25]}...", key=f"hist_{q}", use_container_width=True):
|
||||
st.session_state.messages.append({"role": "user", "content": q})
|
||||
st.rerun()
|
||||
return mode, top_k, explain
|
||||
|
||||
def render_draft_editor(msg):
|
||||
if "query_id" not in msg or not msg["query_id"]:
|
||||
msg["query_id"] = str(uuid.uuid4())
|
||||
|
||||
qid = msg["query_id"]
|
||||
key_base = f"draft_{qid}"
|
||||
|
||||
# State Keys
|
||||
data_meta_key = f"{key_base}_data_meta"
|
||||
data_sugg_key = f"{key_base}_data_suggestions"
|
||||
widget_body_key = f"{key_base}_widget_body"
|
||||
data_body_key = f"{key_base}_data_body"
|
||||
|
||||
# --- 1. INIT STATE ---
|
||||
if f"{key_base}_init" not in st.session_state:
|
||||
meta, body = parse_markdown_draft(msg["content"])
|
||||
if "type" not in meta: meta["type"] = "default"
|
||||
if "title" not in meta: meta["title"] = ""
|
||||
tags = meta.get("tags", [])
|
||||
meta["tags_str"] = ", ".join(tags) if isinstance(tags, list) else str(tags)
|
||||
|
||||
# Persistent Data
|
||||
st.session_state[data_meta_key] = meta
|
||||
st.session_state[data_sugg_key] = []
|
||||
st.session_state[data_body_key] = body.strip()
|
||||
|
||||
# Init Widgets Keys
|
||||
st.session_state[f"{key_base}_wdg_title"] = meta["title"]
|
||||
st.session_state[f"{key_base}_wdg_type"] = meta["type"]
|
||||
st.session_state[f"{key_base}_wdg_tags"] = meta["tags_str"]
|
||||
|
||||
st.session_state[f"{key_base}_init"] = True
|
||||
|
||||
# --- 2. RESURRECTION ---
|
||||
if widget_body_key not in st.session_state and data_body_key in st.session_state:
|
||||
st.session_state[widget_body_key] = st.session_state[data_body_key]
|
||||
|
||||
# --- CALLBACKS ---
|
||||
def _sync_meta():
|
||||
meta = st.session_state[data_meta_key]
|
||||
meta["title"] = st.session_state.get(f"{key_base}_wdg_title", "")
|
||||
meta["type"] = st.session_state.get(f"{key_base}_wdg_type", "default")
|
||||
meta["tags_str"] = st.session_state.get(f"{key_base}_wdg_tags", "")
|
||||
st.session_state[data_meta_key] = meta
|
||||
|
||||
def _sync_body():
|
||||
st.session_state[data_body_key] = st.session_state[widget_body_key]
|
||||
|
||||
def _insert_text(text_to_insert):
|
||||
current = st.session_state.get(widget_body_key, "")
|
||||
new_text = f"{current}\n\n{text_to_insert}"
|
||||
st.session_state[widget_body_key] = new_text
|
||||
st.session_state[data_body_key] = new_text
|
||||
|
||||
def _remove_text(text_to_remove):
|
||||
current = st.session_state.get(widget_body_key, "")
|
||||
new_text = current.replace(text_to_remove, "").strip()
|
||||
st.session_state[widget_body_key] = new_text
|
||||
st.session_state[data_body_key] = new_text
|
||||
|
||||
# --- UI LAYOUT ---
|
||||
st.markdown(f'<div class="draft-box">', unsafe_allow_html=True)
|
||||
st.markdown("### 📝 Entwurf bearbeiten")
|
||||
|
||||
meta_ref = st.session_state[data_meta_key]
|
||||
c1, c2 = st.columns([2, 1])
|
||||
with c1:
|
||||
st.text_input("Titel", key=f"{key_base}_wdg_title", on_change=_sync_meta)
|
||||
|
||||
with c2:
|
||||
known_types = ["concept", "project", "decision", "experience", "journal", "value", "goal", "principle", "risk", "belief"]
|
||||
curr_type = st.session_state.get(f"{key_base}_wdg_type", meta_ref["type"])
|
||||
if curr_type not in known_types: known_types.append(curr_type)
|
||||
st.selectbox("Typ", known_types, key=f"{key_base}_wdg_type", on_change=_sync_meta)
|
||||
|
||||
st.text_input("Tags", key=f"{key_base}_wdg_tags", on_change=_sync_meta)
|
||||
|
||||
tab_edit, tab_intel, tab_view = st.tabs(["✏️ Inhalt", "🧠 Intelligence", "👁️ Vorschau"])
|
||||
|
||||
# --- TAB 1: EDITOR ---
|
||||
with tab_edit:
|
||||
st.text_area(
|
||||
"Body",
|
||||
key=widget_body_key,
|
||||
height=500,
|
||||
on_change=_sync_body,
|
||||
label_visibility="collapsed"
|
||||
)
|
||||
|
||||
# --- TAB 2: INTELLIGENCE ---
|
||||
with tab_intel:
|
||||
st.info("Klicke auf 'Analysieren', um Verknüpfungen für den AKTUELLEN Text zu finden.")
|
||||
|
||||
if st.button("🔍 Analyse starten", key=f"{key_base}_analyze"):
|
||||
st.session_state[data_sugg_key] = []
|
||||
|
||||
text_to_analyze = st.session_state.get(widget_body_key, st.session_state.get(data_body_key, ""))
|
||||
current_doc_type = st.session_state.get(f"{key_base}_wdg_type", "concept")
|
||||
|
||||
with st.spinner("Analysiere..."):
|
||||
analysis = analyze_draft_text(text_to_analyze, current_doc_type)
|
||||
|
||||
if "error" in analysis:
|
||||
st.error(f"Fehler: {analysis['error']}")
|
||||
else:
|
||||
suggestions = analysis.get("suggestions", [])
|
||||
st.session_state[data_sugg_key] = suggestions
|
||||
if not suggestions:
|
||||
st.warning("Keine Vorschläge gefunden.")
|
||||
else:
|
||||
st.success(f"{len(suggestions)} Vorschläge gefunden.")
|
||||
|
||||
suggestions = st.session_state[data_sugg_key]
|
||||
if suggestions:
|
||||
current_text_state = st.session_state.get(widget_body_key, "")
|
||||
|
||||
for idx, sugg in enumerate(suggestions):
|
||||
link_text = sugg.get('suggested_markdown', '')
|
||||
is_inserted = link_text in current_text_state
|
||||
|
||||
bg_color = "#e6fffa" if is_inserted else "#ffffff"
|
||||
border = "3px solid #28a745" if is_inserted else "3px solid #1a73e8"
|
||||
|
||||
st.markdown(f"""
|
||||
<div style="border-left: {border}; background-color: {bg_color}; padding: 10px; margin-bottom: 8px; border-radius: 4px; box-shadow: 0 1px 3px rgba(0,0,0,0.1);">
|
||||
<b>{sugg.get('target_title')}</b> <small>({sugg.get('type')})</small><br>
|
||||
<i>{sugg.get('reason')}</i><br>
|
||||
<code>{link_text}</code>
|
||||
</div>
|
||||
""", unsafe_allow_html=True)
|
||||
|
||||
if is_inserted:
|
||||
st.button("❌ Entfernen", key=f"del_{idx}_{key_base}", on_click=_remove_text, args=(link_text,))
|
||||
else:
|
||||
st.button("➕ Einfügen", key=f"add_{idx}_{key_base}", on_click=_insert_text, args=(link_text,))
|
||||
|
||||
# --- TAB 3: SAVE ---
|
||||
final_tags_str = st.session_state.get(f"{key_base}_wdg_tags", "")
|
||||
final_tags = [t.strip() for t in final_tags_str.split(",") if t.strip()]
|
||||
|
||||
final_meta = {
|
||||
"id": "generated_on_save",
|
||||
"type": st.session_state.get(f"{key_base}_wdg_type", "default"),
|
||||
"title": st.session_state.get(f"{key_base}_wdg_title", "").strip(),
|
||||
"status": "draft",
|
||||
"tags": final_tags
|
||||
}
|
||||
|
||||
final_body = st.session_state.get(widget_body_key, st.session_state[data_body_key])
|
||||
|
||||
if not final_meta["title"]:
|
||||
h1_match = re.search(r"^#\s+(.*)$", final_body, re.MULTILINE)
|
||||
if h1_match:
|
||||
final_meta["title"] = h1_match.group(1).strip()
|
||||
|
||||
final_doc = build_markdown_doc(final_meta, final_body)
|
||||
|
||||
with tab_view:
|
||||
st.markdown('<div class="preview-box">', unsafe_allow_html=True)
|
||||
st.markdown(final_doc)
|
||||
st.markdown('</div>', unsafe_allow_html=True)
|
||||
|
||||
st.markdown("---")
|
||||
|
||||
b1, b2 = st.columns([1, 1])
|
||||
with b1:
|
||||
if st.button("💾 Speichern & Indizieren", type="primary", key=f"{key_base}_save"):
|
||||
with st.spinner("Speichere im Vault..."):
|
||||
|
||||
raw_title = final_meta.get("title", "")
|
||||
if not raw_title:
|
||||
clean_body = re.sub(r"[#*_\[\]()]", "", final_body).strip()
|
||||
raw_title = clean_body[:40] if clean_body else "draft"
|
||||
|
||||
safe_title = slugify(raw_title)[:60] or "draft"
|
||||
fname = f"{datetime.now().strftime('%Y%m%d')}-{safe_title}.md"
|
||||
|
||||
result = save_draft_to_vault(final_doc, filename=fname)
|
||||
if "error" in result:
|
||||
st.error(f"Fehler: {result['error']}")
|
||||
else:
|
||||
st.success(f"Gespeichert: {result.get('file_path')}")
|
||||
st.balloons()
|
||||
with b2:
|
||||
if st.button("📋 Code anzeigen", key=f"{key_base}_btn_copy"):
|
||||
st.code(final_doc, language="markdown")
|
||||
|
||||
st.markdown("</div>", unsafe_allow_html=True)
|
||||
|
||||
|
||||
def render_chat_interface(top_k, explain):
|
||||
for idx, msg in enumerate(st.session_state.messages):
|
||||
with st.chat_message(msg["role"]):
|
||||
if msg["role"] == "assistant":
|
||||
intent = msg.get("intent", "UNKNOWN")
|
||||
src = msg.get("intent_source", "?")
|
||||
icon = {"EMPATHY":"❤️", "DECISION":"⚖️", "CODING":"💻", "FACT":"📚", "INTERVIEW":"📝"}.get(intent, "🧠")
|
||||
st.markdown(f'<div class="intent-badge">{icon} Intent: {intent} <span style="opacity:0.6; font-size:0.8em">({src})</span></div>', unsafe_allow_html=True)
|
||||
|
||||
with st.expander("🐞 Debug Raw Payload", expanded=False):
|
||||
st.json(msg)
|
||||
|
||||
if intent == "INTERVIEW":
|
||||
render_draft_editor(msg)
|
||||
else:
|
||||
st.markdown(msg["content"])
|
||||
|
||||
if "sources" in msg and msg["sources"]:
|
||||
for hit in msg["sources"]:
|
||||
with st.expander(f"📄 {hit.get('note_id', '?')} ({hit.get('total_score', 0):.2f})"):
|
||||
st.markdown(f"_{hit.get('source', {}).get('text', '')[:300]}..._")
|
||||
if hit.get('explanation'):
|
||||
st.caption(f"Grund: {hit['explanation']['reasons'][0]['message']}")
|
||||
def _cb(qid=msg.get("query_id"), nid=hit.get('node_id')):
|
||||
val = st.session_state.get(f"fb_src_{qid}_{nid}")
|
||||
if val is not None: submit_feedback(qid, nid, val+1)
|
||||
st.feedback("faces", key=f"fb_src_{msg.get('query_id')}_{hit.get('node_id')}", on_change=_cb)
|
||||
|
||||
if "query_id" in msg:
|
||||
qid = msg["query_id"]
|
||||
st.feedback("stars", key=f"fb_glob_{qid}", on_change=lambda: submit_feedback(qid, "generated_answer", st.session_state[f"fb_glob_{qid}"]+1))
|
||||
else:
|
||||
st.markdown(msg["content"])
|
||||
|
||||
if prompt := st.chat_input("Frage Mindnet..."):
|
||||
st.session_state.messages.append({"role": "user", "content": prompt})
|
||||
st.rerun()
|
||||
|
||||
if len(st.session_state.messages) > 0 and st.session_state.messages[-1]["role"] == "user":
|
||||
with st.chat_message("assistant"):
|
||||
with st.spinner("Thinking..."):
|
||||
resp = send_chat_message(st.session_state.messages[-1]["content"], top_k, explain)
|
||||
if "error" in resp:
|
||||
st.error(resp["error"])
|
||||
else:
|
||||
st.session_state.messages.append({
|
||||
"role": "assistant",
|
||||
"content": resp.get("answer"),
|
||||
"intent": resp.get("intent", "FACT"),
|
||||
"intent_source": resp.get("intent_source", "Unknown"),
|
||||
"sources": resp.get("sources", []),
|
||||
"query_id": resp.get("query_id")
|
||||
})
|
||||
st.rerun()
|
||||
|
||||
def render_manual_editor():
|
||||
mock_msg = {
|
||||
"content": "---\ntype: concept\ntitle: Neue Notiz\nstatus: draft\ntags: []\n---\n# Titel\n",
|
||||
"query_id": "manual_mode_v2"
|
||||
}
|
||||
render_draft_editor(mock_msg)
|
||||
|
||||
# --- MAIN ---
|
||||
# --- MAIN ROUTING ---
|
||||
mode, top_k, explain = render_sidebar()
|
||||
|
||||
if mode == "💬 Chat":
|
||||
render_chat_interface(top_k, explain)
|
||||
else:
|
||||
render_manual_editor()
|
||||
elif mode == "📝 Manueller Editor":
|
||||
render_manual_editor()
|
||||
elif mode == "🕸️ Graph (Agraph)":
|
||||
render_graph_agraph(graph_service)
|
||||
elif mode == "🕸️ Graph (Cytoscape)":
|
||||
render_graph_explorer_cytoscape(graph_service)
|
||||
@@ -0,0 +1,46 @@
|
||||
"""
|
||||
FILE: app/frontend/ui_api.py
|
||||
DESCRIPTION: Wrapper für Backend-Calls (Chat, Ingest, Feedback). Kapselt requests und Error-Handling.
|
||||
VERSION: 2.6.0
|
||||
STATUS: Active
|
||||
DEPENDENCIES: requests, streamlit, ui_config
|
||||
LAST_ANALYSIS: 2025-12-15
|
||||
"""
|
||||
|
||||
import requests
|
||||
import streamlit as st
|
||||
from ui_config import CHAT_ENDPOINT, INGEST_ANALYZE_ENDPOINT, INGEST_SAVE_ENDPOINT, FEEDBACK_ENDPOINT, API_TIMEOUT
|
||||
|
||||
def send_chat_message(message: str, top_k: int, explain: bool):
|
||||
try:
|
||||
response = requests.post(
|
||||
CHAT_ENDPOINT,
|
||||
json={"message": message, "top_k": top_k, "explain": explain},
|
||||
timeout=API_TIMEOUT
|
||||
)
|
||||
response.raise_for_status()
|
||||
return response.json()
|
||||
except Exception as e:
|
||||
return {"error": str(e)}
|
||||
|
||||
def analyze_draft_text(text: str, n_type: str):
|
||||
try:
|
||||
response = requests.post(INGEST_ANALYZE_ENDPOINT, json={"text": text, "type": n_type}, timeout=15)
|
||||
response.raise_for_status()
|
||||
return response.json()
|
||||
except Exception as e:
|
||||
return {"error": str(e)}
|
||||
|
||||
def save_draft_to_vault(markdown_content: str, filename: str = None):
|
||||
try:
|
||||
response = requests.post(INGEST_SAVE_ENDPOINT, json={"markdown_content": markdown_content, "filename": filename}, timeout=API_TIMEOUT)
|
||||
response.raise_for_status()
|
||||
return response.json()
|
||||
except Exception as e:
|
||||
return {"error": str(e)}
|
||||
|
||||
def submit_feedback(query_id, node_id, score, comment=None):
|
||||
try:
|
||||
requests.post(FEEDBACK_ENDPOINT, json={"query_id": query_id, "node_id": node_id, "score": score, "comment": comment}, timeout=2)
|
||||
st.toast(f"Feedback ({score}) gesendet!")
|
||||
except: pass
|
||||
@@ -0,0 +1,70 @@
|
||||
"""
|
||||
FILE: app/frontend/ui_callbacks.py
|
||||
DESCRIPTION: Event-Handler für UI-Interaktionen. Implementiert den Übergang vom Graphen zum Editor (State Transfer).
|
||||
VERSION: 2.6.0
|
||||
STATUS: Active
|
||||
DEPENDENCIES: streamlit, os, ui_utils
|
||||
LAST_ANALYSIS: 2025-12-15
|
||||
"""
|
||||
|
||||
import streamlit as st
|
||||
import os
|
||||
from ui_utils import build_markdown_doc
|
||||
|
||||
def switch_to_editor_callback(note_payload):
|
||||
"""
|
||||
Callback für den 'Bearbeiten'-Button im Graphen.
|
||||
Versucht, die Datei direkt aus dem Vault (Dateisystem) zu lesen.
|
||||
Das garantiert, dass Frontmatter und Inhalt vollständig sind (Single Source of Truth).
|
||||
"""
|
||||
# 1. Pfad ermitteln (Priorität auf 'path' aus Qdrant)
|
||||
origin_fname = note_payload.get('path')
|
||||
|
||||
# Fallback für Legacy-Datenfelder
|
||||
if not origin_fname:
|
||||
origin_fname = note_payload.get('file_path') or note_payload.get('filename')
|
||||
|
||||
content = ""
|
||||
file_loaded = False
|
||||
|
||||
# 2. Versuch: Direkt von der Festplatte lesen
|
||||
# Wir prüfen, ob der Pfad existiert und lesen den aktuellen Stand der Datei.
|
||||
if origin_fname and os.path.exists(origin_fname):
|
||||
try:
|
||||
with open(origin_fname, "r", encoding="utf-8") as f:
|
||||
content = f.read()
|
||||
file_loaded = True
|
||||
except Exception as e:
|
||||
# Fehler im Terminal loggen, aber UI nicht crashen lassen
|
||||
print(f"Fehler beim Lesen von {origin_fname}: {e}")
|
||||
|
||||
# 3. Fallback: Inhalt aus Qdrant nehmen (wenn Datei nicht zugreifbar)
|
||||
if not file_loaded:
|
||||
# Wir nehmen 'fulltext' aus dem Payload
|
||||
content = note_payload.get('fulltext', '')
|
||||
|
||||
if not content:
|
||||
# Letzter Ausweg: Metadaten nehmen und Dummy-Content bauen
|
||||
content = build_markdown_doc(note_payload, "Inhalt konnte nicht geladen werden (Datei nicht gefunden).")
|
||||
else:
|
||||
# Check: Hat der Text ein Frontmatter? Wenn nein, rekonstruieren wir es.
|
||||
if not content.strip().startswith("---"):
|
||||
content = build_markdown_doc(note_payload, content)
|
||||
|
||||
# Notfall-Pfad Konstruktion (falls gar kein Pfad im System ist)
|
||||
if not origin_fname and 'note_id' in note_payload:
|
||||
origin_fname = f"{note_payload['note_id']}.md"
|
||||
|
||||
# 4. Daten an den Editor übergeben
|
||||
# Wir nutzen den Chat-Verlauf als Transportmittel für den State
|
||||
st.session_state.messages.append({
|
||||
"role": "assistant",
|
||||
"intent": "INTERVIEW",
|
||||
"content": content,
|
||||
"query_id": f"edit_{note_payload.get('note_id', 'unknown')}", # Trigger für den Editor
|
||||
"origin_filename": origin_fname,
|
||||
"origin_note_id": note_payload.get('note_id')
|
||||
})
|
||||
|
||||
# 5. Modus umschalten (wechselt den Tab beim nächsten Rerun)
|
||||
st.session_state["sidebar_mode_selection"] = "📝 Manueller Editor"
|
||||
@@ -0,0 +1,87 @@
|
||||
"""
|
||||
FILE: app/frontend/ui_chat.py
|
||||
DESCRIPTION: Chat-UI. Rendert Nachrichtenverlauf, Quellen-Expanders mit Feedback-Buttons und delegiert bei Bedarf an den Editor.
|
||||
VERSION: 2.6.0
|
||||
STATUS: Active
|
||||
DEPENDENCIES: streamlit, ui_api, ui_editor
|
||||
LAST_ANALYSIS: 2025-12-15
|
||||
"""
|
||||
|
||||
import streamlit as st
|
||||
from ui_api import send_chat_message, submit_feedback
|
||||
from ui_editor import render_draft_editor
|
||||
|
||||
def render_chat_interface(top_k, explain):
|
||||
"""
|
||||
Rendert das Chat-Interface.
|
||||
Zeigt Nachrichten an und behandelt User-Input.
|
||||
"""
|
||||
# 1. Verlauf anzeigen
|
||||
for idx, msg in enumerate(st.session_state.messages):
|
||||
with st.chat_message(msg["role"]):
|
||||
if msg["role"] == "assistant":
|
||||
# Intent Badge
|
||||
intent = msg.get("intent", "UNKNOWN")
|
||||
st.markdown(f'<div class="intent-badge">Intent: {intent}</div>', unsafe_allow_html=True)
|
||||
|
||||
# Debugging (optional, gut für Entwicklung)
|
||||
with st.expander("🐞 Payload", expanded=False):
|
||||
st.json(msg)
|
||||
|
||||
# Unterscheidung: Normaler Text oder Editor-Modus (Interview)
|
||||
if intent == "INTERVIEW":
|
||||
render_draft_editor(msg)
|
||||
else:
|
||||
st.markdown(msg["content"])
|
||||
|
||||
# Quellen anzeigen
|
||||
if "sources" in msg and msg["sources"]:
|
||||
for hit in msg["sources"]:
|
||||
score = hit.get('total_score', 0)
|
||||
# Wenn score None ist, 0.0 annehmen
|
||||
if score is None: score = 0.0
|
||||
|
||||
with st.expander(f"📄 {hit.get('note_id', '?')} ({score:.2f})"):
|
||||
st.markdown(f"_{hit.get('source', {}).get('text', '')[:300]}..._")
|
||||
|
||||
# Explanation Layer
|
||||
if hit.get('explanation'):
|
||||
st.caption(f"Grund: {hit['explanation']['reasons'][0]['message']}")
|
||||
|
||||
# Feedback Buttons pro Source
|
||||
def _cb(qid=msg.get("query_id"), nid=hit.get('node_id')):
|
||||
val = st.session_state.get(f"fb_src_{qid}_{nid}")
|
||||
if val is not None: submit_feedback(qid, nid, val+1)
|
||||
|
||||
st.feedback("faces", key=f"fb_src_{msg.get('query_id')}_{hit.get('node_id')}", on_change=_cb)
|
||||
|
||||
# Globales Feedback für die Antwort
|
||||
if "query_id" in msg:
|
||||
qid = msg["query_id"]
|
||||
st.feedback("stars", key=f"fb_glob_{qid}", on_change=lambda: submit_feedback(qid, "generated_answer", st.session_state[f"fb_glob_{qid}"]+1))
|
||||
else:
|
||||
# User Nachricht
|
||||
st.markdown(msg["content"])
|
||||
|
||||
# 2. Input Feld
|
||||
if prompt := st.chat_input("Frage Mindnet..."):
|
||||
st.session_state.messages.append({"role": "user", "content": prompt})
|
||||
st.rerun()
|
||||
|
||||
# 3. Antwort generieren (wenn letzte Nachricht vom User ist)
|
||||
if len(st.session_state.messages) > 0 and st.session_state.messages[-1]["role"] == "user":
|
||||
with st.chat_message("assistant"):
|
||||
with st.spinner("Thinking..."):
|
||||
resp = send_chat_message(st.session_state.messages[-1]["content"], top_k, explain)
|
||||
|
||||
if "error" in resp:
|
||||
st.error(resp["error"])
|
||||
else:
|
||||
st.session_state.messages.append({
|
||||
"role": "assistant",
|
||||
"content": resp.get("answer"),
|
||||
"intent": resp.get("intent", "FACT"),
|
||||
"sources": resp.get("sources", []),
|
||||
"query_id": resp.get("query_id")
|
||||
})
|
||||
st.rerun()
|
||||
@@ -0,0 +1,88 @@
|
||||
"""
|
||||
FILE: app/frontend/ui_config.py
|
||||
DESCRIPTION: Zentrale Konfiguration für das Frontend. Definiert API-Endpoints, Timeouts und Graph-Styles (Farben).
|
||||
VERSION: 2.6.0
|
||||
STATUS: Active
|
||||
DEPENDENCIES: os, hashlib, dotenv, pathlib
|
||||
LAST_ANALYSIS: 2025-12-15
|
||||
"""
|
||||
|
||||
import os
|
||||
import hashlib
|
||||
from dotenv import load_dotenv
|
||||
from pathlib import Path
|
||||
|
||||
load_dotenv()
|
||||
|
||||
# --- API & PORTS ---
|
||||
API_BASE_URL = os.getenv("MINDNET_API_URL", "http://localhost:8002")
|
||||
CHAT_ENDPOINT = f"{API_BASE_URL}/chat"
|
||||
FEEDBACK_ENDPOINT = f"{API_BASE_URL}/feedback"
|
||||
INGEST_ANALYZE_ENDPOINT = f"{API_BASE_URL}/ingest/analyze"
|
||||
INGEST_SAVE_ENDPOINT = f"{API_BASE_URL}/ingest/save"
|
||||
|
||||
# --- QDRANT ---
|
||||
QDRANT_URL = os.getenv("QDRANT_URL", "http://localhost:6333")
|
||||
QDRANT_KEY = os.getenv("QDRANT_API_KEY", None)
|
||||
if QDRANT_KEY == "": QDRANT_KEY = None
|
||||
COLLECTION_PREFIX = os.getenv("COLLECTION_PREFIX", "mindnet")
|
||||
|
||||
# --- FILES & TIMEOUTS ---
|
||||
HISTORY_FILE = Path("data/logs/search_history.jsonl")
|
||||
timeout_setting = os.getenv("MINDNET_API_TIMEOUT") or os.getenv("MINDNET_LLM_TIMEOUT")
|
||||
API_TIMEOUT = float(timeout_setting) if timeout_setting else 300.0
|
||||
|
||||
# --- STYLING CONSTANTS ---
|
||||
|
||||
# Basierend auf types.yaml
|
||||
GRAPH_COLORS = {
|
||||
# Kerntypen
|
||||
"experience": "#feca57", # Gelb/Orange
|
||||
"project": "#ff9f43", # Dunkleres Orange
|
||||
"decision": "#5f27cd", # Lila
|
||||
|
||||
# Persönlichkeit
|
||||
"value": "#00d2d3", # Cyan
|
||||
"principle": "#0abde3", # Dunkles Cyan
|
||||
"belief": "#48dbfb", # Helles Blau
|
||||
"profile": "#1dd1a1", # Grün
|
||||
|
||||
# Strategie & Risiko
|
||||
"goal": "#ff9ff3", # Pink
|
||||
"risk": "#ff6b6b", # Rot
|
||||
|
||||
# Basis
|
||||
"concept": "#54a0ff", # Blau
|
||||
"task": "#8395a7", # Grau-Blau
|
||||
"journal": "#c8d6e5", # Hellgrau
|
||||
"source": "#576574", # Dunkelgrau
|
||||
"glossary": "#222f3e", # Sehr dunkel
|
||||
|
||||
"default": "#8395a7" # Fallback
|
||||
}
|
||||
|
||||
# System-Kanten, die wir NICHT im Graphen sehen wollen, um Rauschen zu reduzieren
|
||||
SYSTEM_EDGES = ["prev", "next", "belongs_to"]
|
||||
|
||||
def get_edge_color(kind: str) -> str:
|
||||
"""Generiert eine deterministische Farbe basierend auf dem Edge-Typ."""
|
||||
if not kind: return "#bdc3c7"
|
||||
|
||||
# Einige feste Farben für wichtige semantische Typen
|
||||
fixed_colors = {
|
||||
"depends_on": "#ff6b6b", # Rot (Blocker/Abhängigkeit)
|
||||
"blocks": "#ee5253", # Dunkelrot
|
||||
"caused_by": "#ff9ff3", # Pink
|
||||
"related_to": "#c8d6e5", # Hellgrau (Hintergrund)
|
||||
"references": "#bdc3c7", # Grau
|
||||
"derived_from": "#1dd1a1" # Grün
|
||||
}
|
||||
|
||||
if kind in fixed_colors:
|
||||
return fixed_colors[kind]
|
||||
|
||||
# Fallback: Hash-basierte Farbe für dynamische Typen
|
||||
# Wir nutzen einen Pastell-Generator, damit es nicht zu grell wird
|
||||
hash_obj = hashlib.md5(kind.encode())
|
||||
hue = int(hash_obj.hexdigest(), 16) % 360
|
||||
return f"hsl({hue}, 60%, 50%)"
|
||||
@@ -0,0 +1,223 @@
|
||||
"""
|
||||
FILE: app/frontend/ui_editor.py
|
||||
DESCRIPTION: Markdown-Editor mit Live-Vorschau.
|
||||
Refactored für WP-14: Asynchrones Feedback-Handling (Queued State).
|
||||
VERSION: 2.7.0 (Fix: Async Save UI)
|
||||
STATUS: Active
|
||||
DEPENDENCIES: streamlit, uuid, re, datetime, ui_utils, ui_api
|
||||
"""
|
||||
import streamlit as st
|
||||
import uuid
|
||||
import re
|
||||
from datetime import datetime
|
||||
|
||||
from ui_utils import parse_markdown_draft, build_markdown_doc, slugify
|
||||
from ui_api import save_draft_to_vault, analyze_draft_text
|
||||
|
||||
def render_draft_editor(msg):
|
||||
"""
|
||||
Rendert den Markdown-Editor.
|
||||
Nutzt 'origin_filename' aus der Message, um zwischen Update und Neu zu unterscheiden.
|
||||
"""
|
||||
if "query_id" not in msg or not msg["query_id"]:
|
||||
msg["query_id"] = str(uuid.uuid4())
|
||||
|
||||
qid = msg["query_id"]
|
||||
key_base = f"draft_{qid}"
|
||||
|
||||
# State Keys
|
||||
data_meta_key = f"{key_base}_data_meta"
|
||||
data_sugg_key = f"{key_base}_data_suggestions"
|
||||
widget_body_key = f"{key_base}_widget_body"
|
||||
data_body_key = f"{key_base}_data_body"
|
||||
|
||||
# --- INIT STATE ---
|
||||
if f"{key_base}_init" not in st.session_state:
|
||||
meta, body = parse_markdown_draft(msg["content"])
|
||||
if "type" not in meta: meta["type"] = "default"
|
||||
if "title" not in meta: meta["title"] = ""
|
||||
tags = meta.get("tags", [])
|
||||
meta["tags_str"] = ", ".join(tags) if isinstance(tags, list) else str(tags)
|
||||
|
||||
st.session_state[data_meta_key] = meta
|
||||
st.session_state[data_sugg_key] = []
|
||||
st.session_state[data_body_key] = body.strip()
|
||||
|
||||
st.session_state[f"{key_base}_wdg_title"] = meta["title"]
|
||||
st.session_state[f"{key_base}_wdg_type"] = meta["type"]
|
||||
st.session_state[f"{key_base}_wdg_tags"] = meta["tags_str"]
|
||||
|
||||
# Pfad übernehmen (Source of Truth)
|
||||
st.session_state[f"{key_base}_origin_filename"] = msg.get("origin_filename")
|
||||
st.session_state[f"{key_base}_init"] = True
|
||||
|
||||
# --- RESURRECTION ---
|
||||
if widget_body_key not in st.session_state and data_body_key in st.session_state:
|
||||
st.session_state[widget_body_key] = st.session_state[data_body_key]
|
||||
|
||||
# --- SYNC HELPER ---
|
||||
def _sync_meta():
|
||||
meta = st.session_state[data_meta_key]
|
||||
meta["title"] = st.session_state.get(f"{key_base}_wdg_title", "")
|
||||
meta["type"] = st.session_state.get(f"{key_base}_wdg_type", "default")
|
||||
meta["tags_str"] = st.session_state.get(f"{key_base}_wdg_tags", "")
|
||||
st.session_state[data_meta_key] = meta
|
||||
|
||||
def _sync_body():
|
||||
st.session_state[data_body_key] = st.session_state[widget_body_key]
|
||||
|
||||
def _insert_text(t):
|
||||
st.session_state[widget_body_key] = f"{st.session_state.get(widget_body_key, '')}\n\n{t}"
|
||||
st.session_state[data_body_key] = st.session_state[widget_body_key]
|
||||
|
||||
def _remove_text(t):
|
||||
st.session_state[widget_body_key] = st.session_state.get(widget_body_key, '').replace(t, "").strip()
|
||||
st.session_state[data_body_key] = st.session_state[widget_body_key]
|
||||
|
||||
# --- UI LAYOUT ---
|
||||
|
||||
origin_fname = st.session_state.get(f"{key_base}_origin_filename")
|
||||
|
||||
if origin_fname:
|
||||
display_name = str(origin_fname).split("/")[-1]
|
||||
st.success(f"📂 **Update-Modus**: `{display_name}`")
|
||||
with st.expander("Dateipfad Details", expanded=False):
|
||||
st.code(origin_fname)
|
||||
st.markdown(f'<div class="draft-box" style="border-left: 5px solid #ff9f43;">', unsafe_allow_html=True)
|
||||
else:
|
||||
st.info("✨ **Erstell-Modus**: Neue Datei wird angelegt.")
|
||||
st.markdown(f'<div class="draft-box">', unsafe_allow_html=True)
|
||||
|
||||
st.markdown("### Editor")
|
||||
|
||||
# Meta Felder
|
||||
meta_ref = st.session_state[data_meta_key]
|
||||
c1, c2 = st.columns([2, 1])
|
||||
with c1:
|
||||
st.text_input("Titel", key=f"{key_base}_wdg_title", on_change=_sync_meta)
|
||||
with c2:
|
||||
known_types = ["concept", "project", "decision", "experience", "journal", "value", "goal", "principle", "risk", "belief"]
|
||||
curr_type = st.session_state.get(f"{key_base}_wdg_type", meta_ref["type"])
|
||||
if curr_type not in known_types: known_types.append(curr_type)
|
||||
st.selectbox("Typ", known_types, key=f"{key_base}_wdg_type", on_change=_sync_meta)
|
||||
|
||||
st.text_input("Tags", key=f"{key_base}_wdg_tags", on_change=_sync_meta)
|
||||
|
||||
# Tabs
|
||||
tab_edit, tab_intel, tab_view = st.tabs(["✏️ Inhalt", "🧠 Intelligence", "👁️ Vorschau"])
|
||||
|
||||
with tab_edit:
|
||||
st.text_area("Body", key=widget_body_key, height=600, on_change=_sync_body, label_visibility="collapsed")
|
||||
|
||||
with tab_intel:
|
||||
st.info("Analysiert den Text auf Verknüpfungsmöglichkeiten.")
|
||||
if st.button("🔍 Analyse starten", key=f"{key_base}_analyze"):
|
||||
st.session_state[data_sugg_key] = []
|
||||
text_to_analyze = st.session_state.get(widget_body_key, st.session_state.get(data_body_key, ""))
|
||||
with st.spinner("Analysiere..."):
|
||||
analysis = analyze_draft_text(text_to_analyze, st.session_state.get(f"{key_base}_wdg_type", "concept"))
|
||||
if "error" in analysis:
|
||||
st.error(f"Fehler: {analysis['error']}")
|
||||
else:
|
||||
suggestions = analysis.get("suggestions", [])
|
||||
st.session_state[data_sugg_key] = suggestions
|
||||
if not suggestions: st.warning("Keine Vorschläge.")
|
||||
else: st.success(f"{len(suggestions)} Vorschläge gefunden.")
|
||||
|
||||
suggestions = st.session_state[data_sugg_key]
|
||||
if suggestions:
|
||||
current_text = st.session_state.get(widget_body_key, "")
|
||||
for idx, sugg in enumerate(suggestions):
|
||||
link_text = sugg.get('suggested_markdown', '')
|
||||
is_inserted = link_text in current_text
|
||||
bg_color = "#e6fffa" if is_inserted else "#ffffff"
|
||||
border = "3px solid #28a745" if is_inserted else "3px solid #1a73e8"
|
||||
st.markdown(f"<div style='border-left: {border}; background-color: {bg_color}; padding: 10px; margin-bottom: 8px;'><b>{sugg.get('target_title')}</b> <small>({sugg.get('type')})</small><br><i>{sugg.get('reason')}</i><br><code>{link_text}</code></div>", unsafe_allow_html=True)
|
||||
if is_inserted:
|
||||
st.button("❌ Entfernen", key=f"del_{idx}_{key_base}", on_click=_remove_text, args=(link_text,))
|
||||
else:
|
||||
st.button("➕ Einfügen", key=f"add_{idx}_{key_base}", on_click=_insert_text, args=(link_text,))
|
||||
|
||||
# Save Logic Preparation
|
||||
final_tags = [t.strip() for t in st.session_state.get(f"{key_base}_wdg_tags", "").split(",") if t.strip()]
|
||||
final_meta = {
|
||||
"id": "generated_on_save",
|
||||
"type": st.session_state.get(f"{key_base}_wdg_type", "default"),
|
||||
"title": st.session_state.get(f"{key_base}_wdg_title", "").strip(),
|
||||
"status": "draft",
|
||||
"tags": final_tags
|
||||
}
|
||||
if "origin_note_id" in msg:
|
||||
final_meta["id"] = msg["origin_note_id"]
|
||||
|
||||
final_body = st.session_state.get(widget_body_key, st.session_state[data_body_key])
|
||||
if not final_meta["title"]:
|
||||
h1_match = re.search(r"^#\s+(.*)$", final_body, re.MULTILINE)
|
||||
if h1_match: final_meta["title"] = h1_match.group(1).strip()
|
||||
|
||||
final_doc = build_markdown_doc(final_meta, final_body)
|
||||
|
||||
with tab_view:
|
||||
st.markdown('<div class="preview-box">', unsafe_allow_html=True)
|
||||
st.markdown(final_doc)
|
||||
st.markdown('</div>', unsafe_allow_html=True)
|
||||
|
||||
st.markdown("---")
|
||||
|
||||
# Save Actions
|
||||
b1, b2 = st.columns([1, 1])
|
||||
with b1:
|
||||
save_label = "💾 Update speichern" if origin_fname else "💾 Neu anlegen & Indizieren"
|
||||
|
||||
if st.button(save_label, type="primary", key=f"{key_base}_save"):
|
||||
with st.spinner("Sende an Backend..."):
|
||||
if origin_fname:
|
||||
target_file = origin_fname
|
||||
else:
|
||||
raw_title = final_meta.get("title", "draft")
|
||||
target_file = f"{datetime.now().strftime('%Y%m%d')}-{slugify(raw_title)[:60]}.md"
|
||||
|
||||
result = save_draft_to_vault(final_doc, filename=target_file)
|
||||
|
||||
# --- WP-14 CHANGE START: Handling Async Response ---
|
||||
if "error" in result:
|
||||
st.error(f"Fehler: {result['error']}")
|
||||
else:
|
||||
status = result.get("status", "success")
|
||||
file_path = result.get("file_path", "unbekannt")
|
||||
|
||||
if status == "queued":
|
||||
# Neuer Status für Async Processing
|
||||
st.info(f"✅ **Eingereiht:** Datei `{file_path}` wurde gespeichert.")
|
||||
st.caption("Die KI-Analyse und Indizierung läuft im Hintergrund. Du kannst weiterarbeiten.")
|
||||
else:
|
||||
# Legacy / Synchroner Fall
|
||||
st.success(f"Gespeichert: {file_path}")
|
||||
|
||||
st.balloons()
|
||||
# --- WP-14 CHANGE END ---
|
||||
|
||||
with b2:
|
||||
if st.button("📋 Code anzeigen", key=f"{key_base}_btn_copy"):
|
||||
st.code(final_doc, language="markdown")
|
||||
|
||||
st.markdown("</div>", unsafe_allow_html=True)
|
||||
|
||||
def render_manual_editor():
|
||||
"""
|
||||
Rendert den manuellen Editor.
|
||||
"""
|
||||
target_msg = None
|
||||
if st.session_state.messages:
|
||||
last_msg = st.session_state.messages[-1]
|
||||
qid = str(last_msg.get("query_id", ""))
|
||||
if qid.startswith("edit_"):
|
||||
target_msg = last_msg
|
||||
|
||||
if not target_msg:
|
||||
target_msg = {
|
||||
"content": "---\ntype: concept\ntitle: Neue Notiz\nstatus: draft\ntags: []\n---\n# Titel\n",
|
||||
"query_id": f"manual_{uuid.uuid4()}"
|
||||
}
|
||||
|
||||
render_draft_editor(target_msg)
|
||||
@@ -0,0 +1,162 @@
|
||||
"""
|
||||
FILE: app/frontend/ui_graph.py
|
||||
DESCRIPTION: Legacy Graph-Explorer (Streamlit-Agraph). Implementiert Physik-Simulation (BarnesHut) und direkten Editor-Sprung.
|
||||
VERSION: 2.6.0
|
||||
STATUS: Maintenance (Active Fallback)
|
||||
DEPENDENCIES: streamlit, streamlit_agraph, qdrant_client, ui_config, ui_callbacks
|
||||
LAST_ANALYSIS: 2025-12-15
|
||||
"""
|
||||
|
||||
import streamlit as st
|
||||
from streamlit_agraph import agraph, Config
|
||||
from qdrant_client import models
|
||||
from ui_config import COLLECTION_PREFIX, GRAPH_COLORS
|
||||
from ui_callbacks import switch_to_editor_callback
|
||||
|
||||
def render_graph_explorer(graph_service):
|
||||
st.header("🕸️ Graph Explorer")
|
||||
|
||||
# Session State initialisieren
|
||||
if "graph_center_id" not in st.session_state:
|
||||
st.session_state.graph_center_id = None
|
||||
|
||||
# Defaults für View & Physik setzen
|
||||
st.session_state.setdefault("graph_depth", 2)
|
||||
st.session_state.setdefault("graph_show_labels", True)
|
||||
# Höhere Default-Werte für Abstand
|
||||
st.session_state.setdefault("graph_spacing", 250)
|
||||
st.session_state.setdefault("graph_gravity", -4000)
|
||||
|
||||
col_ctrl, col_graph = st.columns([1, 4])
|
||||
|
||||
# --- LINKE SPALTE: CONTROLS ---
|
||||
with col_ctrl:
|
||||
st.subheader("Fokus")
|
||||
|
||||
# Sucheingabe
|
||||
search_term = st.text_input("Suche Notiz", placeholder="Titel eingeben...")
|
||||
|
||||
# Suchlogik Qdrant
|
||||
if search_term:
|
||||
hits, _ = graph_service.client.scroll(
|
||||
collection_name=f"{COLLECTION_PREFIX}_notes",
|
||||
scroll_filter=models.Filter(must=[models.FieldCondition(key="title", match=models.MatchText(text=search_term))]),
|
||||
limit=10
|
||||
)
|
||||
options = {h.payload['title']: h.payload['note_id'] for h in hits}
|
||||
|
||||
if options:
|
||||
selected_title = st.selectbox("Ergebnisse:", list(options.keys()))
|
||||
if st.button("Laden", use_container_width=True):
|
||||
st.session_state.graph_center_id = options[selected_title]
|
||||
st.rerun()
|
||||
|
||||
st.divider()
|
||||
|
||||
# Layout & Physik Einstellungen
|
||||
with st.expander("👁️ Ansicht & Layout", expanded=True):
|
||||
st.session_state.graph_depth = st.slider("Tiefe (Tier)", 1, 3, st.session_state.graph_depth)
|
||||
st.session_state.graph_show_labels = st.checkbox("Kanten-Beschriftung", st.session_state.graph_show_labels)
|
||||
|
||||
st.markdown("**Physik (BarnesHut)**")
|
||||
st.session_state.graph_spacing = st.slider("Federlänge (Abstand)", 50, 800, st.session_state.graph_spacing)
|
||||
st.session_state.graph_gravity = st.slider("Abstoßung (Gravity)", -20000, -500, st.session_state.graph_gravity)
|
||||
|
||||
if st.button("Reset Layout"):
|
||||
st.session_state.graph_spacing = 250
|
||||
st.session_state.graph_gravity = -4000
|
||||
st.rerun()
|
||||
|
||||
st.divider()
|
||||
st.caption("Legende (Top Typen)")
|
||||
for k, v in list(GRAPH_COLORS.items())[:8]:
|
||||
st.markdown(f"<span style='color:{v}'>●</span> {k}", unsafe_allow_html=True)
|
||||
|
||||
# --- RECHTE SPALTE: GRAPH & ACTION BAR ---
|
||||
with col_graph:
|
||||
center_id = st.session_state.graph_center_id
|
||||
|
||||
if center_id:
|
||||
# Action Container oben fixieren (Layout Fix)
|
||||
action_container = st.container()
|
||||
|
||||
# Graph und Daten laden
|
||||
with st.spinner(f"Lade Graph..."):
|
||||
nodes, edges = graph_service.get_ego_graph(
|
||||
center_id,
|
||||
depth=st.session_state.graph_depth,
|
||||
show_labels=st.session_state.graph_show_labels
|
||||
)
|
||||
|
||||
# WICHTIG: Daten für Editor holen (inkl. Pfad)
|
||||
note_data = graph_service.get_note_with_full_content(center_id)
|
||||
|
||||
# Action Bar rendern
|
||||
with action_container:
|
||||
c1, c2 = st.columns([3, 1])
|
||||
with c1:
|
||||
st.caption(f"Aktives Zentrum: **{center_id}**")
|
||||
with c2:
|
||||
if note_data:
|
||||
st.button("📝 Bearbeiten",
|
||||
use_container_width=True,
|
||||
on_click=switch_to_editor_callback,
|
||||
args=(note_data,))
|
||||
else:
|
||||
st.error("Datenfehler: Note nicht gefunden")
|
||||
|
||||
# Debug Inspector
|
||||
with st.expander("🕵️ Data Inspector", expanded=False):
|
||||
if note_data:
|
||||
st.json(note_data)
|
||||
if 'path' in note_data:
|
||||
st.success(f"Pfad OK: {note_data['path']}")
|
||||
else:
|
||||
st.error("Pfad fehlt!")
|
||||
else:
|
||||
st.info("Leer.")
|
||||
|
||||
if not nodes:
|
||||
st.warning("Keine Daten gefunden.")
|
||||
else:
|
||||
# --- CONFIGURATION (BarnesHut) ---
|
||||
# Height-Trick für Re-Render (da key-Parameter manchmal crasht)
|
||||
dyn_height = 800 + (abs(st.session_state.graph_gravity) % 5)
|
||||
|
||||
config = Config(
|
||||
width=1000,
|
||||
height=dyn_height,
|
||||
directed=True,
|
||||
physics={
|
||||
"enabled": True,
|
||||
"solver": "barnesHut",
|
||||
"barnesHut": {
|
||||
"gravitationalConstant": st.session_state.graph_gravity,
|
||||
"centralGravity": 0.005, # Extrem wichtig für die Ausbreitung!
|
||||
"springLength": st.session_state.graph_spacing,
|
||||
"springConstant": 0.04,
|
||||
"damping": 0.09,
|
||||
"avoidOverlap": 0.1
|
||||
},
|
||||
"stabilization": {"enabled": True, "iterations": 600}
|
||||
},
|
||||
hierarchical=False,
|
||||
nodeHighlightBehavior=True,
|
||||
highlightColor="#F7A7A6",
|
||||
collapsible=False
|
||||
)
|
||||
|
||||
return_value = agraph(nodes=nodes, edges=edges, config=config)
|
||||
|
||||
# Interaktions-Logik (Klick auf Node)
|
||||
if return_value:
|
||||
if return_value != center_id:
|
||||
# Navigation: Neues Zentrum setzen
|
||||
st.session_state.graph_center_id = return_value
|
||||
st.rerun()
|
||||
else:
|
||||
# Klick auf das Zentrum selbst
|
||||
st.toast(f"Zentrum: {return_value}")
|
||||
|
||||
else:
|
||||
st.info("👈 Bitte wähle links eine Notiz aus, um den Graphen zu starten.")
|
||||
@@ -0,0 +1,334 @@
|
||||
"""
|
||||
FILE: app/frontend/ui_graph_cytoscape.py
|
||||
DESCRIPTION: Moderner Graph-Explorer (Cytoscape.js). Features: COSE-Layout, Deep-Linking (URL Params), Active Inspector Pattern (CSS-Styling ohne Re-Render).
|
||||
VERSION: 2.6.0
|
||||
STATUS: Active
|
||||
DEPENDENCIES: streamlit, st_cytoscape, qdrant_client, ui_config, ui_callbacks
|
||||
LAST_ANALYSIS: 2025-12-15
|
||||
"""
|
||||
|
||||
import streamlit as st
|
||||
from st_cytoscape import cytoscape
|
||||
from qdrant_client import models
|
||||
from ui_config import COLLECTION_PREFIX, GRAPH_COLORS
|
||||
from ui_callbacks import switch_to_editor_callback
|
||||
|
||||
def update_url_params():
|
||||
"""Callback: Schreibt Slider-Werte in die URL und synchronisiert den State."""
|
||||
# Werte aus den Slider-Keys in die Logik-Variablen übertragen
|
||||
if "cy_depth_slider" in st.session_state:
|
||||
st.session_state.cy_depth = st.session_state.cy_depth_slider
|
||||
if "cy_len_slider" in st.session_state:
|
||||
st.session_state.cy_ideal_edge_len = st.session_state.cy_len_slider
|
||||
if "cy_rep_slider" in st.session_state:
|
||||
st.session_state.cy_node_repulsion = st.session_state.cy_rep_slider
|
||||
|
||||
# In URL schreiben
|
||||
st.query_params["depth"] = st.session_state.cy_depth
|
||||
st.query_params["len"] = st.session_state.cy_ideal_edge_len
|
||||
st.query_params["rep"] = st.session_state.cy_node_repulsion
|
||||
|
||||
def render_graph_explorer_cytoscape(graph_service):
|
||||
st.header("🕸️ Graph Explorer (Cytoscape)")
|
||||
|
||||
# ---------------------------------------------------------
|
||||
# 1. STATE & PERSISTENZ
|
||||
# ---------------------------------------------------------
|
||||
if "graph_center_id" not in st.session_state:
|
||||
st.session_state.graph_center_id = None
|
||||
|
||||
if "graph_inspected_id" not in st.session_state:
|
||||
st.session_state.graph_inspected_id = None
|
||||
|
||||
# Lade Einstellungen aus der URL (falls vorhanden), sonst Defaults
|
||||
params = st.query_params
|
||||
|
||||
# Helper um sicher int zu parsen
|
||||
def get_param(key, default):
|
||||
try: return int(params.get(key, default))
|
||||
except: return default
|
||||
|
||||
# Initialisiere Session State Variablen, falls noch nicht vorhanden
|
||||
if "cy_depth" not in st.session_state:
|
||||
st.session_state.cy_depth = get_param("depth", 2)
|
||||
|
||||
if "cy_ideal_edge_len" not in st.session_state:
|
||||
st.session_state.cy_ideal_edge_len = get_param("len", 150)
|
||||
|
||||
if "cy_node_repulsion" not in st.session_state:
|
||||
st.session_state.cy_node_repulsion = get_param("rep", 1000000)
|
||||
|
||||
col_ctrl, col_graph = st.columns([1, 4])
|
||||
|
||||
# ---------------------------------------------------------
|
||||
# 2. LINKES PANEL (Steuerung)
|
||||
# ---------------------------------------------------------
|
||||
with col_ctrl:
|
||||
st.subheader("Fokus")
|
||||
|
||||
search_term = st.text_input("Suche Notiz", placeholder="Titel eingeben...", key="cy_search")
|
||||
|
||||
if search_term:
|
||||
hits, _ = graph_service.client.scroll(
|
||||
collection_name=f"{COLLECTION_PREFIX}_notes",
|
||||
limit=10,
|
||||
scroll_filter=models.Filter(must=[models.FieldCondition(key="title", match=models.MatchText(text=search_term))])
|
||||
)
|
||||
options = {h.payload['title']: h.payload['note_id'] for h in hits}
|
||||
|
||||
if options:
|
||||
selected_title = st.selectbox("Ergebnisse:", list(options.keys()), key="cy_select")
|
||||
if st.button("Laden", use_container_width=True, key="cy_load"):
|
||||
new_id = options[selected_title]
|
||||
st.session_state.graph_center_id = new_id
|
||||
st.session_state.graph_inspected_id = new_id
|
||||
st.rerun()
|
||||
|
||||
st.divider()
|
||||
|
||||
# LAYOUT EINSTELLUNGEN (Mit URL Sync)
|
||||
with st.expander("👁️ Layout Einstellungen", expanded=True):
|
||||
st.slider("Tiefe (Tier)", 1, 3,
|
||||
value=st.session_state.cy_depth,
|
||||
key="cy_depth_slider",
|
||||
on_change=update_url_params)
|
||||
|
||||
st.markdown("**COSE Layout**")
|
||||
st.slider("Kantenlänge", 50, 600,
|
||||
value=st.session_state.cy_ideal_edge_len,
|
||||
key="cy_len_slider",
|
||||
on_change=update_url_params)
|
||||
|
||||
st.slider("Knoten-Abstoßung", 100000, 5000000, step=100000,
|
||||
value=st.session_state.cy_node_repulsion,
|
||||
key="cy_rep_slider",
|
||||
on_change=update_url_params)
|
||||
|
||||
if st.button("Neu berechnen", key="cy_rerun"):
|
||||
st.rerun()
|
||||
|
||||
st.divider()
|
||||
st.caption("Legende")
|
||||
for k, v in list(GRAPH_COLORS.items())[:8]:
|
||||
st.markdown(f"<span style='color:{v}'>●</span> {k}", unsafe_allow_html=True)
|
||||
# ---------------------------------------------------------
|
||||
# 3. RECHTES PANEL (GRAPH & INSPECTOR)
|
||||
# ---------------------------------------------------------
|
||||
with col_graph:
|
||||
center_id = st.session_state.graph_center_id
|
||||
|
||||
# Fallback Init
|
||||
if not center_id and st.session_state.graph_inspected_id:
|
||||
center_id = st.session_state.graph_inspected_id
|
||||
st.session_state.graph_center_id = center_id
|
||||
|
||||
if center_id:
|
||||
# Sync Inspection
|
||||
if not st.session_state.graph_inspected_id:
|
||||
st.session_state.graph_inspected_id = center_id
|
||||
|
||||
inspected_id = st.session_state.graph_inspected_id
|
||||
|
||||
# --- DATEN LADEN ---
|
||||
with st.spinner(f"Lade Graph (Tiefe {st.session_state.cy_depth})..."):
|
||||
# 1. Graph Daten
|
||||
nodes_data, edges_data = graph_service.get_ego_graph(
|
||||
center_id,
|
||||
depth=st.session_state.cy_depth
|
||||
)
|
||||
# 2. Detail Daten (Inspector)
|
||||
inspected_data = graph_service.get_note_with_full_content(inspected_id)
|
||||
|
||||
# --- ACTION BAR ---
|
||||
action_container = st.container()
|
||||
with action_container:
|
||||
c1, c2, c3 = st.columns([2, 1, 1])
|
||||
|
||||
with c1:
|
||||
title_show = inspected_data.get('title', inspected_id) if inspected_data else inspected_id
|
||||
st.info(f"**Ausgewählt:** {title_show}")
|
||||
|
||||
with c2:
|
||||
# NAVIGATION
|
||||
if inspected_id != center_id:
|
||||
if st.button("🎯 Als Zentrum setzen", use_container_width=True, key="cy_nav_btn"):
|
||||
st.session_state.graph_center_id = inspected_id
|
||||
st.rerun()
|
||||
else:
|
||||
st.caption("_(Ist aktuelles Zentrum)_")
|
||||
|
||||
with c3:
|
||||
# EDITIEREN
|
||||
if inspected_data:
|
||||
st.button("📝 Bearbeiten",
|
||||
use_container_width=True,
|
||||
on_click=switch_to_editor_callback,
|
||||
args=(inspected_data,),
|
||||
key="cy_edit_btn")
|
||||
|
||||
# --- DATA INSPECTOR ---
|
||||
with st.expander("🕵️ Data Inspector (Details)", expanded=False):
|
||||
if inspected_data:
|
||||
col_i1, col_i2 = st.columns(2)
|
||||
with col_i1:
|
||||
st.markdown(f"**ID:** `{inspected_data.get('note_id')}`")
|
||||
st.markdown(f"**Typ:** `{inspected_data.get('type')}`")
|
||||
with col_i2:
|
||||
st.markdown(f"**Tags:** {', '.join(inspected_data.get('tags', []))}")
|
||||
path_check = "✅" if inspected_data.get('path') else "❌"
|
||||
st.markdown(f"**Pfad:** {path_check}")
|
||||
|
||||
st.caption("Inhalt (Vorschau):")
|
||||
st.text_area("Content Preview", inspected_data.get('fulltext', '')[:1000], height=200, disabled=True, label_visibility="collapsed")
|
||||
|
||||
with st.expander("📄 Raw JSON anzeigen"):
|
||||
st.json(inspected_data)
|
||||
else:
|
||||
st.warning("Keine Daten geladen.")
|
||||
|
||||
# --- GRAPH ELEMENTS ---
|
||||
cy_elements = []
|
||||
|
||||
for n in nodes_data:
|
||||
is_center = (n.id == center_id)
|
||||
is_inspected = (n.id == inspected_id)
|
||||
|
||||
tooltip_text = n.title if n.title else n.label
|
||||
display_label = n.label
|
||||
if len(display_label) > 15 and " " in display_label:
|
||||
display_label = display_label.replace(" ", "\n", 1)
|
||||
|
||||
cy_node = {
|
||||
"data": {
|
||||
"id": n.id,
|
||||
"label": display_label,
|
||||
"bg_color": n.color,
|
||||
"tooltip": tooltip_text
|
||||
},
|
||||
# Wir steuern das Aussehen rein über Klassen (.inspected / .center)
|
||||
"classes": " ".join([c for c in ["center" if is_center else "", "inspected" if is_inspected else ""] if c]),
|
||||
"selected": False
|
||||
}
|
||||
cy_elements.append(cy_node)
|
||||
|
||||
for e in edges_data:
|
||||
target_id = getattr(e, "to", getattr(e, "target", None))
|
||||
if target_id:
|
||||
cy_edge = {
|
||||
"data": {
|
||||
"source": e.source,
|
||||
"target": target_id,
|
||||
"label": e.label,
|
||||
"line_color": e.color
|
||||
}
|
||||
}
|
||||
cy_elements.append(cy_edge)
|
||||
|
||||
# --- STYLESHEET ---
|
||||
stylesheet = [
|
||||
{
|
||||
"selector": "node",
|
||||
"style": {
|
||||
"label": "data(label)",
|
||||
"width": "30px", "height": "30px",
|
||||
"background-color": "data(bg_color)",
|
||||
"color": "#333", "font-size": "12px",
|
||||
"text-valign": "center", "text-halign": "center",
|
||||
"text-wrap": "wrap", "text-max-width": "90px",
|
||||
"border-width": 2, "border-color": "#fff",
|
||||
"title": "data(tooltip)"
|
||||
}
|
||||
},
|
||||
# Inspiziert (Gelber Rahmen)
|
||||
{
|
||||
"selector": ".inspected",
|
||||
"style": {
|
||||
"border-width": 6,
|
||||
"border-color": "#FFC300",
|
||||
"width": "50px", "height": "50px",
|
||||
"font-weight": "bold",
|
||||
"z-index": 999
|
||||
}
|
||||
},
|
||||
# Zentrum (Roter Rahmen)
|
||||
{
|
||||
"selector": ".center",
|
||||
"style": {
|
||||
"border-width": 4,
|
||||
"border-color": "#FF5733",
|
||||
"width": "40px", "height": "40px"
|
||||
}
|
||||
},
|
||||
# Mix
|
||||
{
|
||||
"selector": ".center.inspected",
|
||||
"style": {
|
||||
"border-width": 6,
|
||||
"border-color": "#FF5733",
|
||||
"width": "55px", "height": "55px"
|
||||
}
|
||||
},
|
||||
# Default Selection unterdrücken
|
||||
{
|
||||
"selector": "node:selected",
|
||||
"style": {
|
||||
"border-width": 0,
|
||||
"overlay-opacity": 0
|
||||
}
|
||||
},
|
||||
{
|
||||
"selector": "edge",
|
||||
"style": {
|
||||
"width": 2,
|
||||
"line-color": "data(line_color)",
|
||||
"target-arrow-color": "data(line_color)",
|
||||
"target-arrow-shape": "triangle",
|
||||
"curve-style": "bezier",
|
||||
"label": "data(label)",
|
||||
"font-size": "10px", "color": "#666",
|
||||
"text-background-opacity": 0.8, "text-background-color": "#fff"
|
||||
}
|
||||
}
|
||||
]
|
||||
|
||||
# --- RENDER ---
|
||||
graph_key = f"cy_{center_id}_{st.session_state.cy_depth}_{st.session_state.cy_ideal_edge_len}"
|
||||
|
||||
clicked_elements = cytoscape(
|
||||
elements=cy_elements,
|
||||
stylesheet=stylesheet,
|
||||
layout={
|
||||
"name": "cose",
|
||||
"idealEdgeLength": st.session_state.cy_ideal_edge_len,
|
||||
"nodeOverlap": 20,
|
||||
"refresh": 20,
|
||||
"fit": True,
|
||||
"padding": 50,
|
||||
"randomize": False,
|
||||
"componentSpacing": 100,
|
||||
"nodeRepulsion": st.session_state.cy_node_repulsion,
|
||||
"edgeElasticity": 100,
|
||||
"nestingFactor": 5,
|
||||
"gravity": 80,
|
||||
"numIter": 1000,
|
||||
"initialTemp": 200,
|
||||
"coolingFactor": 0.95,
|
||||
"minTemp": 1.0,
|
||||
"animate": False
|
||||
},
|
||||
key=graph_key,
|
||||
height="700px"
|
||||
)
|
||||
|
||||
# --- EVENT HANDLING ---
|
||||
if clicked_elements:
|
||||
clicked_nodes = clicked_elements.get("nodes", [])
|
||||
if clicked_nodes:
|
||||
clicked_id = clicked_nodes[0]
|
||||
|
||||
if clicked_id != st.session_state.graph_inspected_id:
|
||||
st.session_state.graph_inspected_id = clicked_id
|
||||
st.rerun()
|
||||
|
||||
else:
|
||||
st.info("👈 Bitte wähle links eine Notiz aus.")
|
||||
@@ -0,0 +1,321 @@
|
||||
"""
|
||||
FILE: app/frontend/ui_graph_service.py
|
||||
DESCRIPTION: Data Layer für den Graphen. Greift direkt auf Qdrant zu (Performance), um Knoten/Kanten zu laden und Texte zu rekonstruieren ("Stitching").
|
||||
VERSION: 2.6.0
|
||||
STATUS: Active
|
||||
DEPENDENCIES: qdrant_client, streamlit_agraph, ui_config, re
|
||||
LAST_ANALYSIS: 2025-12-15
|
||||
"""
|
||||
|
||||
import re
|
||||
from qdrant_client import QdrantClient, models
|
||||
from streamlit_agraph import Node, Edge
|
||||
from ui_config import GRAPH_COLORS, get_edge_color, SYSTEM_EDGES
|
||||
|
||||
class GraphExplorerService:
|
||||
def __init__(self, url, api_key=None, prefix="mindnet"):
|
||||
self.client = QdrantClient(url=url, api_key=api_key)
|
||||
self.prefix = prefix
|
||||
self.notes_col = f"{prefix}_notes"
|
||||
self.chunks_col = f"{prefix}_chunks"
|
||||
self.edges_col = f"{prefix}_edges"
|
||||
self._note_cache = {}
|
||||
|
||||
def get_note_with_full_content(self, note_id):
|
||||
"""
|
||||
Lädt die Metadaten der Note und rekonstruiert den gesamten Text
|
||||
aus den Chunks (Stitching). Wichtig für den Editor-Fallback.
|
||||
"""
|
||||
# 1. Metadaten holen
|
||||
meta = self._fetch_note_cached(note_id)
|
||||
if not meta: return None
|
||||
|
||||
# 2. Volltext aus Chunks bauen
|
||||
full_text = self._fetch_full_text_stitched(note_id)
|
||||
|
||||
# 3. Ergebnis kombinieren (Wir überschreiben das 'fulltext' Feld mit dem frischen Stitching)
|
||||
# Wir geben eine Kopie zurück, um den Cache nicht zu verfälschen
|
||||
complete_note = meta.copy()
|
||||
if full_text:
|
||||
complete_note['fulltext'] = full_text
|
||||
|
||||
return complete_note
|
||||
|
||||
def get_ego_graph(self, center_note_id: str, depth=2, show_labels=True):
|
||||
"""
|
||||
Erstellt den Ego-Graphen um eine zentrale Notiz.
|
||||
Lädt Volltext für das Zentrum und Snippets für Nachbarn.
|
||||
"""
|
||||
nodes_dict = {}
|
||||
unique_edges = {}
|
||||
|
||||
# 1. Center Note laden
|
||||
center_note = self._fetch_note_cached(center_note_id)
|
||||
if not center_note: return [], []
|
||||
self._add_node_to_dict(nodes_dict, center_note, level=0)
|
||||
|
||||
# Initialset für Suche
|
||||
level_1_ids = {center_note_id}
|
||||
|
||||
# Suche Kanten für Center (L1)
|
||||
l1_edges = self._find_connected_edges([center_note_id], center_note.get("title"))
|
||||
|
||||
for edge_data in l1_edges:
|
||||
src_id, tgt_id = self._process_edge(edge_data, nodes_dict, unique_edges, current_depth=1)
|
||||
if src_id: level_1_ids.add(src_id)
|
||||
if tgt_id: level_1_ids.add(tgt_id)
|
||||
|
||||
# Level 2 Suche (begrenzt für Performance)
|
||||
if depth > 1 and len(level_1_ids) > 1 and len(level_1_ids) < 80:
|
||||
l1_subset = list(level_1_ids - {center_note_id})
|
||||
if l1_subset:
|
||||
l2_edges = self._find_connected_edges_batch(l1_subset)
|
||||
for edge_data in l2_edges:
|
||||
self._process_edge(edge_data, nodes_dict, unique_edges, current_depth=2)
|
||||
|
||||
# --- SMART CONTENT LOADING ---
|
||||
|
||||
# A. Fulltext für Center Node holen (Chunks zusammenfügen)
|
||||
center_text = self._fetch_full_text_stitched(center_note_id)
|
||||
if center_note_id in nodes_dict:
|
||||
orig_title = nodes_dict[center_note_id].title
|
||||
clean_full = self._clean_markdown(center_text[:2000])
|
||||
# Wir packen den Text in den Tooltip (title attribute)
|
||||
nodes_dict[center_note_id].title = f"{orig_title}\n\n📄 INHALT:\n{clean_full}..."
|
||||
|
||||
# B. Previews für alle Nachbarn holen (Batch)
|
||||
all_ids = list(nodes_dict.keys())
|
||||
previews = self._fetch_previews_for_nodes(all_ids)
|
||||
|
||||
for nid, node_obj in nodes_dict.items():
|
||||
if nid != center_note_id:
|
||||
prev_raw = previews.get(nid, "Kein Vorschau-Text.")
|
||||
clean_prev = self._clean_markdown(prev_raw[:600])
|
||||
node_obj.title = f"{node_obj.title}\n\n🔍 VORSCHAU:\n{clean_prev}..."
|
||||
|
||||
# Graphen bauen (Nodes & Edges finalisieren)
|
||||
final_edges = []
|
||||
for (src, tgt), data in unique_edges.items():
|
||||
kind = data['kind']
|
||||
prov = data['provenance']
|
||||
color = get_edge_color(kind)
|
||||
is_smart = (prov != "explicit" and prov != "rule")
|
||||
|
||||
# Label Logik
|
||||
label_text = kind if show_labels else " "
|
||||
|
||||
final_edges.append(Edge(
|
||||
source=src, target=tgt, label=label_text, color=color, dashes=is_smart,
|
||||
title=f"Relation: {kind}\nProvenance: {prov}"
|
||||
))
|
||||
|
||||
return list(nodes_dict.values()), final_edges
|
||||
|
||||
def _clean_markdown(self, text):
|
||||
"""Entfernt Markdown-Sonderzeichen für saubere Tooltips im Browser."""
|
||||
if not text: return ""
|
||||
# Entferne Header Marker (## )
|
||||
text = re.sub(r'#+\s', '', text)
|
||||
# Entferne Bold/Italic (** oder *)
|
||||
text = re.sub(r'\*\*|__|\*|_', '', text)
|
||||
# Entferne Links [Text](Url) -> Text
|
||||
text = re.sub(r'\[([^\]]+)\]\([^\)]+\)', r'\1', text)
|
||||
# Entferne Wikilinks [[Link]] -> Link
|
||||
text = re.sub(r'\[\[([^\]]+)\]\]', r'\1', text)
|
||||
return text
|
||||
|
||||
def _fetch_full_text_stitched(self, note_id):
|
||||
"""Lädt alle Chunks einer Note und baut den Text zusammen."""
|
||||
try:
|
||||
scroll_filter = models.Filter(
|
||||
must=[models.FieldCondition(key="note_id", match=models.MatchValue(value=note_id))]
|
||||
)
|
||||
# Limit hoch genug setzen
|
||||
chunks, _ = self.client.scroll(self.chunks_col, scroll_filter=scroll_filter, limit=100, with_payload=True)
|
||||
# Sortieren nach 'ord' (Reihenfolge im Dokument)
|
||||
chunks.sort(key=lambda x: x.payload.get('ord', 999))
|
||||
|
||||
full_text = []
|
||||
for c in chunks:
|
||||
# 'text' ist der reine Inhalt ohne Overlap
|
||||
txt = c.payload.get('text', '')
|
||||
if txt: full_text.append(txt)
|
||||
|
||||
return "\n\n".join(full_text)
|
||||
except:
|
||||
return "Fehler beim Laden des Volltexts."
|
||||
|
||||
def _fetch_previews_for_nodes(self, node_ids):
|
||||
"""Holt Batch-weise den ersten Chunk für eine Liste von Nodes."""
|
||||
if not node_ids: return {}
|
||||
previews = {}
|
||||
try:
|
||||
scroll_filter = models.Filter(must=[models.FieldCondition(key="note_id", match=models.MatchAny(any=node_ids))])
|
||||
# Limit = Anzahl Nodes * 3 (Puffer)
|
||||
chunks, _ = self.client.scroll(self.chunks_col, scroll_filter=scroll_filter, limit=len(node_ids)*3, with_payload=True)
|
||||
|
||||
for c in chunks:
|
||||
nid = c.payload.get("note_id")
|
||||
# Nur den ersten gefundenen Chunk pro Note nehmen
|
||||
if nid and nid not in previews:
|
||||
previews[nid] = c.payload.get("window") or c.payload.get("text") or ""
|
||||
except: pass
|
||||
return previews
|
||||
|
||||
def _find_connected_edges(self, note_ids, note_title=None):
|
||||
"""Findet eingehende und ausgehende Kanten."""
|
||||
|
||||
results = []
|
||||
|
||||
# 1. OUTGOING EDGES (Der "Owner"-Fix)
|
||||
# Wir suchen Kanten, die im Feld 'note_id' (Owner) eine unserer Notizen haben.
|
||||
# Das findet ALLE ausgehenden Kanten, egal ob sie an einem Chunk oder der Note hängen.
|
||||
if note_ids:
|
||||
out_filter = models.Filter(must=[
|
||||
models.FieldCondition(key="note_id", match=models.MatchAny(any=note_ids)),
|
||||
models.FieldCondition(key="kind", match=models.MatchExcept(**{"except": SYSTEM_EDGES}))
|
||||
])
|
||||
# Limit hoch, um alles zu finden
|
||||
res_out, _ = self.client.scroll(self.edges_col, scroll_filter=out_filter, limit=500, with_payload=True)
|
||||
results.extend(res_out)
|
||||
|
||||
# 2. INCOMING EDGES (Ziel = Chunk ID oder Titel oder Note ID)
|
||||
# Hier müssen wir Chunks auflösen, um Treffer auf Chunks zu finden.
|
||||
|
||||
# Chunk IDs der aktuellen Notes holen
|
||||
chunk_ids = []
|
||||
if note_ids:
|
||||
c_filter = models.Filter(must=[models.FieldCondition(key="note_id", match=models.MatchAny(any=note_ids))])
|
||||
chunks, _ = self.client.scroll(self.chunks_col, scroll_filter=c_filter, limit=300)
|
||||
chunk_ids = [c.id for c in chunks]
|
||||
|
||||
shoulds = []
|
||||
# Case A: Edge zeigt auf einen unserer Chunks
|
||||
if chunk_ids:
|
||||
shoulds.append(models.FieldCondition(key="target_id", match=models.MatchAny(any=chunk_ids)))
|
||||
|
||||
# Case B: Edge zeigt direkt auf unsere Note ID
|
||||
if note_ids:
|
||||
shoulds.append(models.FieldCondition(key="target_id", match=models.MatchAny(any=note_ids)))
|
||||
|
||||
# Case C: Edge zeigt auf unseren Titel (Wikilinks)
|
||||
if note_title:
|
||||
shoulds.append(models.FieldCondition(key="target_id", match=models.MatchValue(value=note_title)))
|
||||
|
||||
if shoulds:
|
||||
in_filter = models.Filter(
|
||||
must=[models.FieldCondition(key="kind", match=models.MatchExcept(**{"except": SYSTEM_EDGES}))],
|
||||
should=shoulds
|
||||
)
|
||||
res_in, _ = self.client.scroll(self.edges_col, scroll_filter=in_filter, limit=500, with_payload=True)
|
||||
results.extend(res_in)
|
||||
|
||||
return results
|
||||
|
||||
def _find_connected_edges_batch(self, note_ids):
|
||||
# Wrapper für Level 2 Suche
|
||||
return self._find_connected_edges(note_ids)
|
||||
|
||||
def _process_edge(self, record, nodes_dict, unique_edges, current_depth):
|
||||
"""Verarbeitet eine rohe Edge, löst IDs auf und fügt sie den Dictionaries hinzu."""
|
||||
payload = record.payload
|
||||
src_ref = payload.get("source_id")
|
||||
tgt_ref = payload.get("target_id")
|
||||
kind = payload.get("kind")
|
||||
provenance = payload.get("provenance", "explicit")
|
||||
|
||||
# IDs zu Notes auflösen
|
||||
src_note = self._resolve_note_from_ref(src_ref)
|
||||
tgt_note = self._resolve_note_from_ref(tgt_ref)
|
||||
|
||||
if src_note and tgt_note:
|
||||
src_id = src_note['note_id']
|
||||
tgt_id = tgt_note['note_id']
|
||||
|
||||
if src_id != tgt_id:
|
||||
# Nodes hinzufügen
|
||||
self._add_node_to_dict(nodes_dict, src_note, level=current_depth)
|
||||
self._add_node_to_dict(nodes_dict, tgt_note, level=current_depth)
|
||||
|
||||
# Kante hinzufügen (mit Deduplizierung)
|
||||
key = (src_id, tgt_id)
|
||||
existing = unique_edges.get(key)
|
||||
|
||||
should_update = True
|
||||
# Bevorzuge explizite Kanten vor Smart Kanten
|
||||
is_current_explicit = (provenance in ["explicit", "rule"])
|
||||
if existing:
|
||||
is_existing_explicit = (existing['provenance'] in ["explicit", "rule"])
|
||||
if is_existing_explicit and not is_current_explicit:
|
||||
should_update = False
|
||||
|
||||
if should_update:
|
||||
unique_edges[key] = {"source": src_id, "target": tgt_id, "kind": kind, "provenance": provenance}
|
||||
return src_id, tgt_id
|
||||
return None, None
|
||||
|
||||
def _fetch_note_cached(self, note_id):
|
||||
if note_id in self._note_cache: return self._note_cache[note_id]
|
||||
res, _ = self.client.scroll(
|
||||
collection_name=self.notes_col,
|
||||
scroll_filter=models.Filter(must=[models.FieldCondition(key="note_id", match=models.MatchValue(value=note_id))]),
|
||||
limit=1, with_payload=True
|
||||
)
|
||||
if res:
|
||||
self._note_cache[note_id] = res[0].payload
|
||||
return res[0].payload
|
||||
return None
|
||||
|
||||
def _resolve_note_from_ref(self, ref_str):
|
||||
"""Löst eine ID (Chunk, Note oder Titel) zu einer Note Payload auf."""
|
||||
if not ref_str: return None
|
||||
|
||||
# Fall A: Chunk ID (enthält #)
|
||||
if "#" in ref_str:
|
||||
try:
|
||||
# Versuch 1: Chunk ID direkt
|
||||
res = self.client.retrieve(self.chunks_col, ids=[ref_str], with_payload=True)
|
||||
if res: return self._fetch_note_cached(res[0].payload.get("note_id"))
|
||||
except: pass
|
||||
|
||||
# Versuch 2: NoteID#Section (Hash abtrennen)
|
||||
possible_note_id = ref_str.split("#")[0]
|
||||
if self._fetch_note_cached(possible_note_id): return self._fetch_note_cached(possible_note_id)
|
||||
|
||||
# Fall B: Note ID direkt
|
||||
if self._fetch_note_cached(ref_str): return self._fetch_note_cached(ref_str)
|
||||
|
||||
# Fall C: Titel
|
||||
res, _ = self.client.scroll(
|
||||
collection_name=self.notes_col,
|
||||
scroll_filter=models.Filter(must=[models.FieldCondition(key="title", match=models.MatchValue(value=ref_str))]),
|
||||
limit=1, with_payload=True
|
||||
)
|
||||
if res:
|
||||
self._note_cache[res[0].payload['note_id']] = res[0].payload
|
||||
return res[0].payload
|
||||
return None
|
||||
|
||||
def _add_node_to_dict(self, node_dict, note_payload, level=1):
|
||||
nid = note_payload.get("note_id")
|
||||
if nid in node_dict: return
|
||||
|
||||
ntype = note_payload.get("type", "default")
|
||||
color = GRAPH_COLORS.get(ntype, GRAPH_COLORS["default"])
|
||||
|
||||
# Basis-Tooltip (wird später erweitert)
|
||||
tooltip = f"Titel: {note_payload.get('title')}\nTyp: {ntype}"
|
||||
|
||||
if level == 0: size = 45
|
||||
elif level == 1: size = 25
|
||||
else: size = 15
|
||||
|
||||
node_dict[nid] = Node(
|
||||
id=nid,
|
||||
label=note_payload.get('title', nid),
|
||||
size=size,
|
||||
color=color,
|
||||
shape="dot" if level > 0 else "diamond",
|
||||
title=tooltip,
|
||||
font={'color': 'black', 'face': 'arial', 'size': 14 if level < 2 else 0}
|
||||
)
|
||||
@@ -0,0 +1,45 @@
|
||||
"""
|
||||
FILE: app/frontend/ui_sidebar.py
|
||||
DESCRIPTION: Rendert die Sidebar. Steuert den Modus-Wechsel (Chat/Editor/Graph) und globale Settings (Top-K).
|
||||
VERSION: 2.6.0
|
||||
STATUS: Active
|
||||
DEPENDENCIES: streamlit, ui_utils, ui_config
|
||||
LAST_ANALYSIS: 2025-12-15
|
||||
"""
|
||||
|
||||
import streamlit as st
|
||||
from ui_utils import load_history_from_logs
|
||||
from ui_config import HISTORY_FILE
|
||||
|
||||
def render_sidebar():
|
||||
with st.sidebar:
|
||||
st.title("🧠 mindnet")
|
||||
st.caption("v2.6 | WP-19 Graph View")
|
||||
|
||||
if "sidebar_mode_selection" not in st.session_state:
|
||||
st.session_state["sidebar_mode_selection"] = "💬 Chat"
|
||||
|
||||
mode = st.radio(
|
||||
"Modus",
|
||||
[
|
||||
"💬 Chat",
|
||||
"📝 Manueller Editor",
|
||||
"🕸️ Graph (Agraph)",
|
||||
"🕸️ Graph (Cytoscape)" # <-- Neuer Punkt
|
||||
],
|
||||
key="sidebar_mode_selection"
|
||||
)
|
||||
|
||||
st.divider()
|
||||
st.subheader("⚙️ Settings")
|
||||
top_k = st.slider("Quellen (Top-K)", 1, 10, 5)
|
||||
explain = st.toggle("Explanation Layer", True)
|
||||
|
||||
st.divider()
|
||||
st.subheader("🕒 Verlauf")
|
||||
for q in load_history_from_logs(HISTORY_FILE, 8):
|
||||
if st.button(f"🔎 {q[:25]}...", key=f"hist_{q}", use_container_width=True):
|
||||
st.session_state.messages.append({"role": "user", "content": q})
|
||||
st.rerun()
|
||||
|
||||
return mode, top_k, explain
|
||||
@@ -0,0 +1,146 @@
|
||||
"""
|
||||
FILE: app/frontend/ui_utils.py
|
||||
DESCRIPTION: String-Utilities. Parser für Markdown/YAML (LLM-Healing) und Helper für History-Loading.
|
||||
VERSION: 2.6.0
|
||||
STATUS: Active
|
||||
DEPENDENCIES: re, yaml, unicodedata, json, datetime
|
||||
LAST_ANALYSIS: 2025-12-15
|
||||
"""
|
||||
|
||||
import re
|
||||
import yaml
|
||||
import unicodedata
|
||||
import json
|
||||
from datetime import datetime
|
||||
|
||||
def slugify(value):
|
||||
if not value: return ""
|
||||
value = str(value).lower()
|
||||
replacements = {'ä': 'ae', 'ö': 'oe', 'ü': 'ue', 'ß': 'ss', '&': 'und', '+': 'und'}
|
||||
for k, v in replacements.items():
|
||||
value = value.replace(k, v)
|
||||
|
||||
value = unicodedata.normalize('NFKD', value).encode('ascii', 'ignore').decode('ascii')
|
||||
value = re.sub(r'[^\w\s-]', '', value).strip()
|
||||
return re.sub(r'[-\s]+', '-', value)
|
||||
|
||||
def normalize_meta_and_body(meta, body):
|
||||
ALLOWED_KEYS = {"title", "type", "status", "tags", "id", "created", "updated", "aliases", "lang"}
|
||||
clean_meta = {}
|
||||
extra_content = []
|
||||
|
||||
if "titel" in meta and "title" not in meta:
|
||||
meta["title"] = meta.pop("titel")
|
||||
|
||||
tag_candidates = ["tags", "emotionale_keywords", "keywords", "schluesselwoerter"]
|
||||
all_tags = []
|
||||
for key in tag_candidates:
|
||||
if key in meta:
|
||||
val = meta[key]
|
||||
if isinstance(val, list): all_tags.extend(val)
|
||||
elif isinstance(val, str): all_tags.extend([t.strip() for t in val.split(",")])
|
||||
|
||||
for key, val in meta.items():
|
||||
if key in ALLOWED_KEYS:
|
||||
clean_meta[key] = val
|
||||
elif key in tag_candidates:
|
||||
pass
|
||||
else:
|
||||
if val and isinstance(val, str):
|
||||
header = key.replace("_", " ").title()
|
||||
extra_content.append(f"## {header}\n{val}\n")
|
||||
|
||||
if all_tags:
|
||||
clean_tags = []
|
||||
for t in all_tags:
|
||||
t_clean = str(t).replace("#", "").strip()
|
||||
if t_clean: clean_tags.append(t_clean)
|
||||
clean_meta["tags"] = list(set(clean_tags))
|
||||
|
||||
if extra_content:
|
||||
new_section = "\n".join(extra_content)
|
||||
final_body = f"{new_section}\n{body}"
|
||||
else:
|
||||
final_body = body
|
||||
|
||||
return clean_meta, final_body
|
||||
|
||||
def parse_markdown_draft(full_text):
|
||||
clean_text = full_text.strip()
|
||||
pattern_block = r"```(?:markdown|md|yaml)?\s*(.*?)\s*```"
|
||||
match_block = re.search(pattern_block, clean_text, re.DOTALL | re.IGNORECASE)
|
||||
if match_block:
|
||||
clean_text = match_block.group(1).strip()
|
||||
|
||||
meta = {}
|
||||
body = clean_text
|
||||
yaml_str = ""
|
||||
|
||||
parts = re.split(r"^---+\s*$", clean_text, maxsplit=2, flags=re.MULTILINE)
|
||||
|
||||
if len(parts) >= 3:
|
||||
yaml_str = parts[1]
|
||||
body = parts[2]
|
||||
elif clean_text.startswith("---"):
|
||||
fallback_match = re.search(r"^---\s*(.*?)(?=\n#)", clean_text, re.DOTALL | re.MULTILINE)
|
||||
if fallback_match:
|
||||
yaml_str = fallback_match.group(1)
|
||||
body = clean_text.replace(f"---{yaml_str}", "", 1).strip()
|
||||
|
||||
if yaml_str:
|
||||
yaml_str_clean = yaml_str.replace("#", "")
|
||||
try:
|
||||
parsed = yaml.safe_load(yaml_str_clean)
|
||||
if isinstance(parsed, dict):
|
||||
meta = parsed
|
||||
except Exception as e:
|
||||
print(f"YAML Parsing Warning: {e}")
|
||||
|
||||
if not meta.get("title"):
|
||||
h1_match = re.search(r"^#\s+(.*)$", body, re.MULTILINE)
|
||||
if h1_match:
|
||||
meta["title"] = h1_match.group(1).strip()
|
||||
|
||||
if meta.get("type") == "draft":
|
||||
meta["status"] = "draft"
|
||||
meta["type"] = "experience"
|
||||
|
||||
return normalize_meta_and_body(meta, body)
|
||||
|
||||
def build_markdown_doc(meta, body):
|
||||
if "id" not in meta or meta["id"] == "generated_on_save":
|
||||
raw_title = meta.get('title', 'note')
|
||||
clean_slug = slugify(raw_title)[:50] or "note"
|
||||
meta["id"] = f"{datetime.now().strftime('%Y%m%d')}-{clean_slug}"
|
||||
|
||||
meta["updated"] = datetime.now().strftime("%Y-%m-%d")
|
||||
|
||||
ordered_meta = {}
|
||||
prio_keys = ["id", "type", "title", "status", "tags"]
|
||||
for k in prio_keys:
|
||||
if k in meta: ordered_meta[k] = meta.pop(k)
|
||||
ordered_meta.update(meta)
|
||||
|
||||
try:
|
||||
yaml_str = yaml.dump(ordered_meta, default_flow_style=None, sort_keys=False, allow_unicode=True).strip()
|
||||
except:
|
||||
yaml_str = "error: generating_yaml"
|
||||
|
||||
return f"---\n{yaml_str}\n---\n\n{body}"
|
||||
|
||||
def load_history_from_logs(filepath, limit=10):
|
||||
queries = []
|
||||
if filepath.exists():
|
||||
try:
|
||||
with open(filepath, "r", encoding="utf-8") as f:
|
||||
lines = f.readlines()
|
||||
for line in reversed(lines):
|
||||
try:
|
||||
entry = json.loads(line)
|
||||
q = entry.get("query_text")
|
||||
if q and q not in queries:
|
||||
queries.append(q)
|
||||
if len(queries) >= limit: break
|
||||
except: continue
|
||||
except: pass
|
||||
return queries
|
||||
@@ -1,172 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
"""
|
||||
Modul: app/graph/service.py
|
||||
Version: 0.1.0
|
||||
Datum: 2025-09-10
|
||||
|
||||
Zweck
|
||||
-----
|
||||
Leichtgewichtiger Graph-Layer über Qdrant:
|
||||
- get_note(note_id)
|
||||
- get_chunks(note_id)
|
||||
- neighbors(source_id, kinds=[...], scope=['note','chunk'], depth=1)
|
||||
- walk_bfs(source_id, kinds, max_depth)
|
||||
- context_for_note(note_id, max_neighbors): heuristische Kontextsammlung
|
||||
|
||||
Hinweise
|
||||
--------
|
||||
- Nutzt die bestehenden Collections <prefix>_notes/_chunks/_edges.
|
||||
- Edges werden über Payload-Felder (`kind`, `source_id`, `target_id`) abgefragt.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
from typing import List, Dict, Any, Optional, Iterable, Set, Tuple
|
||||
from qdrant_client.http import models as rest
|
||||
from app.core.qdrant import QdrantConfig, get_client
|
||||
|
||||
def _cols(prefix: str):
|
||||
return f"{prefix}_notes", f"{prefix}_chunks", f"{prefix}_edges"
|
||||
|
||||
class GraphService:
|
||||
def __init__(self, cfg: Optional[QdrantConfig] = None, prefix: Optional[str] = None):
|
||||
self.cfg = cfg or QdrantConfig.from_env()
|
||||
if prefix:
|
||||
self.cfg.prefix = prefix
|
||||
self.client = get_client(self.cfg)
|
||||
self.notes_col, self.chunks_col, self.edges_col = _cols(self.cfg.prefix)
|
||||
|
||||
# ------------------------ fetch helpers ------------------------
|
||||
def _scroll(self, col: str, flt: Optional[rest.Filter] = None, limit: int = 256):
|
||||
out = []
|
||||
nextp = None
|
||||
while True:
|
||||
pts, nextp = self.client.scroll(
|
||||
collection_name=col,
|
||||
with_payload=True,
|
||||
with_vectors=False,
|
||||
limit=limit,
|
||||
offset=nextp,
|
||||
scroll_filter=flt,
|
||||
)
|
||||
if not pts:
|
||||
break
|
||||
out.extend(pts)
|
||||
if nextp is None:
|
||||
break
|
||||
return out
|
||||
|
||||
# ------------------------ public API ---------------------------
|
||||
def get_note(self, note_id: str) -> Optional[Dict[str, Any]]:
|
||||
f = rest.Filter(must=[rest.FieldCondition(key="note_id", match=rest.MatchValue(value=note_id))])
|
||||
pts, _ = self.client.scroll(self.notes_col, with_payload=True, with_vectors=False, limit=1, scroll_filter=f)
|
||||
return (pts[0].payload or None) if pts else None
|
||||
|
||||
def get_chunks(self, note_id: str) -> List[Dict[str, Any]]:
|
||||
f = rest.Filter(must=[rest.FieldCondition(key="note_id", match=rest.MatchValue(value=note_id))])
|
||||
pts = self._scroll(self.chunks_col, f)
|
||||
# Sortierung analog Export
|
||||
def key(pl):
|
||||
p = pl.payload or {}
|
||||
s = p.get("seq") or 0
|
||||
ci = p.get("chunk_index") or 0
|
||||
n = 0
|
||||
cid = p.get("chunk_id") or ""
|
||||
if isinstance(cid, str) and "#" in cid:
|
||||
try:
|
||||
n = int(cid.rsplit("#", 1)[-1])
|
||||
except Exception:
|
||||
n = 0
|
||||
return (int(s), int(ci), n)
|
||||
pts_sorted = sorted(pts, key=key)
|
||||
return [p.payload or {} for p in pts_sorted]
|
||||
|
||||
def neighbors(self, source_id: str, kinds: Optional[Iterable[str]] = None,
|
||||
scope: Optional[Iterable[str]] = None, depth: int = 1) -> Dict[str, List[Dict[str, Any]]]:
|
||||
"""
|
||||
Liefert eingehende & ausgehende Nachbarn (nur nach kind gefiltert).
|
||||
depth==1: direkte Kanten.
|
||||
"""
|
||||
kinds = list(kinds) if kinds else None
|
||||
must = [rest.FieldCondition(key="source_id", match=rest.MatchValue(value=source_id))]
|
||||
if kinds:
|
||||
must.append(rest.FieldCondition(key="kind", match=rest.MatchAny(any=kinds)))
|
||||
f = rest.Filter(must=must)
|
||||
edges = self._scroll(self.edges_col, f)
|
||||
out = {"out": [], "in": []}
|
||||
for e in edges:
|
||||
out["out"].append(e.payload or {})
|
||||
# Inverse Richtung (eingehend)
|
||||
must_in = [rest.FieldCondition(key="target_id", match=rest.MatchValue(value=source_id))]
|
||||
if kinds:
|
||||
must_in.append(rest.FieldCondition(key="kind", match=rest.MatchAny(any=kinds)))
|
||||
f_in = rest.Filter(must=must_in)
|
||||
edges_in = self._scroll(self.edges_col, f_in)
|
||||
for e in edges_in:
|
||||
out["in"].append(e.payload or {})
|
||||
return out
|
||||
|
||||
def walk_bfs(self, source_id: str, kinds: Iterable[str], max_depth: int = 2) -> Set[str]:
|
||||
visited: Set[str] = {source_id}
|
||||
frontier: Set[str] = {source_id}
|
||||
kinds = list(kinds)
|
||||
for _ in range(max_depth):
|
||||
nxt: Set[str] = set()
|
||||
for s in frontier:
|
||||
neigh = self.neighbors(s, kinds=kinds)
|
||||
for e in neigh["out"]:
|
||||
t = e.get("target_id")
|
||||
if isinstance(t, str) and t not in visited:
|
||||
visited.add(t)
|
||||
nxt.add(t)
|
||||
frontier = nxt
|
||||
if not frontier:
|
||||
break
|
||||
return visited
|
||||
|
||||
def context_for_note(self, note_id: str, kinds: Iterable[str] = ("references","backlink"), max_neighbors: int = 12) -> Dict[str, Any]:
|
||||
"""
|
||||
Heuristischer Kontext: eigene Chunks + Nachbarn nach Kantenarten, dedupliziert.
|
||||
"""
|
||||
note = self.get_note(note_id) or {}
|
||||
chunks = self.get_chunks(note_id)
|
||||
neigh = self.neighbors(note_id, kinds=list(kinds))
|
||||
targets = []
|
||||
for e in neigh["out"]:
|
||||
t = e.get("target_id")
|
||||
if isinstance(t, str):
|
||||
targets.append(t)
|
||||
for e in neigh["in"]:
|
||||
s = e.get("source_id")
|
||||
if isinstance(s, str):
|
||||
targets.append(s)
|
||||
# de-dupe
|
||||
seen = set()
|
||||
uniq = []
|
||||
for t in targets:
|
||||
if t not in seen:
|
||||
seen.add(t)
|
||||
uniq.append(t)
|
||||
uniq = uniq[:max_neighbors]
|
||||
neighbor_notes = [self.get_note(t) for t in uniq]
|
||||
return {
|
||||
"note": note,
|
||||
"chunks": chunks,
|
||||
"neighbors": [n for n in neighbor_notes if n],
|
||||
"edges_out": neigh["out"],
|
||||
"edges_in": neigh["in"],
|
||||
}
|
||||
|
||||
# Optional: Mini-CLI
|
||||
if __name__ == "__main__": # pragma: no cover
|
||||
import argparse, json
|
||||
ap = argparse.ArgumentParser()
|
||||
ap.add_argument("--prefix", help="Collection-Prefix (überschreibt ENV)")
|
||||
ap.add_argument("--note-id", required=True)
|
||||
ap.add_argument("--neighbors", action="store_true", help="Nur Nachbarn anzeigen")
|
||||
args = ap.parse_args()
|
||||
svc = GraphService(prefix=args.prefix)
|
||||
if args.neighbors:
|
||||
out = svc.neighbors(args.note_id, kinds=["references","backlink","prev","next","belongs_to"])
|
||||
else:
|
||||
out = svc.context_for_note(args.note_id)
|
||||
print(json.dumps(out, ensure_ascii=False, indent=2))
|
||||
+11
-5
@@ -1,11 +1,17 @@
|
||||
"""
|
||||
app/main.py — mindnet API bootstrap
|
||||
FILE: app/main.py
|
||||
DESCRIPTION: Bootstrap der FastAPI Anwendung. Inkludiert Router und Middleware.
|
||||
VERSION: 0.6.0
|
||||
STATUS: Active
|
||||
DEPENDENCIES: app.config, app.routers.* (embed, qdrant, query, graph, tools, feedback, chat, ingest, admin)
|
||||
LAST_ANALYSIS: 2025-12-15
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
from fastapi import FastAPI
|
||||
from .config import get_settings
|
||||
from .routers.embed_router import router as embed_router
|
||||
from .routers.qdrant_router import router as qdrant_router
|
||||
#from .routers.embed_router import router as embed_router
|
||||
#from .routers.qdrant_router import router as qdrant_router
|
||||
|
||||
from .routers.query import router as query_router
|
||||
from .routers.graph import router as graph_router
|
||||
@@ -29,8 +35,8 @@ def create_app() -> FastAPI:
|
||||
def healthz():
|
||||
return {"status": "ok", "qdrant": s.QDRANT_URL, "prefix": s.COLLECTION_PREFIX}
|
||||
|
||||
app.include_router(embed_router)
|
||||
app.include_router(qdrant_router)
|
||||
# app.include_router(embed_router)
|
||||
# app.include_router(qdrant_router)
|
||||
|
||||
app.include_router(query_router, prefix="/query", tags=["query"])
|
||||
app.include_router(graph_router, prefix="/graph", tags=["graph"])
|
||||
|
||||
+6
-10
@@ -1,14 +1,10 @@
|
||||
"""
|
||||
app/models/dto.py — Pydantic-Modelle (DTOs) für WP-04/WP-05/WP-06
|
||||
|
||||
Zweck:
|
||||
Laufzeit-Modelle für FastAPI (Requests/Responses).
|
||||
WP-06 Update: Intent & Intent-Source in ChatResponse.
|
||||
|
||||
Version:
|
||||
0.6.2 (WP-06: Decision Engine Transparency, Erweiterung des Feeback Request)
|
||||
Stand:
|
||||
2025-12-09
|
||||
FILE: app/models/dto.py
|
||||
DESCRIPTION: Pydantic-Modelle (DTOs) für Request/Response Bodies. Definiert das API-Schema.
|
||||
VERSION: 0.6.2
|
||||
STATUS: Active
|
||||
DEPENDENCIES: pydantic, typing, uuid
|
||||
LAST_ANALYSIS: 2025-12-15
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
+6
-16
@@ -1,20 +1,10 @@
|
||||
"""
|
||||
app/routers/admin.py — Admin-/Monitoring-Endpunkte (optional)
|
||||
|
||||
Zweck:
|
||||
Liefert einfache Kennzahlen zu Collections (Counts) und Config.
|
||||
Kompatibilität:
|
||||
Python 3.12+, FastAPI 0.110+, qdrant-client 1.x
|
||||
Version:
|
||||
0.1.0 (Erstanlage)
|
||||
Stand:
|
||||
2025-10-07
|
||||
Bezug:
|
||||
- Qdrant Collections: *_notes, *_chunks, *_edges
|
||||
Nutzung:
|
||||
app.include_router(admin.router, prefix="/admin", tags=["admin"])
|
||||
Änderungsverlauf:
|
||||
0.1.0 (2025-10-07) – Erstanlage.
|
||||
FILE: app/routers/admin.py
|
||||
DESCRIPTION: Monitoring-Endpunkt. Zeigt Qdrant-Collection-Counts und geladene Config.
|
||||
VERSION: 0.1.0
|
||||
STATUS: Active (Optional)
|
||||
DEPENDENCIES: qdrant_client, app.config
|
||||
LAST_ANALYSIS: 2025-12-15
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
+7
-2
@@ -1,6 +1,11 @@
|
||||
"""
|
||||
app/routers/chat.py — RAG Endpunkt
|
||||
Version: 2.5.0 (Fix: Question Detection protects against False-Positive Interviews)
|
||||
FILE: app/routers/chat.py
|
||||
DESCRIPTION: Haupt-Chat-Interface (RAG & Interview). Enthält Intent-Router (Keywords/LLM) und Prompt-Construction.
|
||||
VERSION: 2.5.0
|
||||
STATUS: Active
|
||||
DEPENDENCIES: app.config, app.models.dto, app.services.llm_service, app.core.retriever, app.services.feedback_service
|
||||
EXTERNAL_CONFIG: config/decision_engine.yaml, config/types.yaml
|
||||
LAST_ANALYSIS: 2025-12-15
|
||||
"""
|
||||
|
||||
from fastapi import APIRouter, HTTPException, Depends
|
||||
|
||||
@@ -1,5 +1,10 @@
|
||||
"""
|
||||
Version 0.1
|
||||
FILE: app/routers/embed_router.py
|
||||
DESCRIPTION: Exponiert die lokale Embedding-Funktion als API-Endpunkt.
|
||||
VERSION: 0.1.0
|
||||
STATUS: Active
|
||||
DEPENDENCIES: app.embeddings, pydantic
|
||||
LAST_ANALYSIS: 2025-12-15
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
@@ -1,6 +1,10 @@
|
||||
"""
|
||||
app/routers/feedback.py
|
||||
Endpunkt für User-Feedback (WP-04c).
|
||||
FILE: app/routers/feedback.py
|
||||
DESCRIPTION: Endpunkt für explizites User-Feedback (WP-04c).
|
||||
VERSION: 0.1.0
|
||||
STATUS: Active
|
||||
DEPENDENCIES: app.models.dto, app.services.feedback_service
|
||||
LAST_ANALYSIS: 2025-12-15
|
||||
"""
|
||||
from fastapi import APIRouter, HTTPException
|
||||
from app.models.dto import FeedbackRequest
|
||||
|
||||
+6
-17
@@ -1,21 +1,10 @@
|
||||
"""
|
||||
app/routers/graph.py — Graph-Endpunkte (WP-04)
|
||||
|
||||
Zweck:
|
||||
Liefert die Nachbarschaft einer Note/ID als JSON-Graph (Nodes/Edges/Stats).
|
||||
Kompatibilität:
|
||||
Python 3.12+, FastAPI 0.110+, qdrant-client 1.x
|
||||
Version:
|
||||
0.1.0 (Erstanlage)
|
||||
Stand:
|
||||
2025-10-07
|
||||
Bezug:
|
||||
- app/core/graph_adapter.py
|
||||
- app/models/dto.py
|
||||
Nutzung:
|
||||
app.include_router(graph.router, prefix="/graph", tags=["graph"])
|
||||
Änderungsverlauf:
|
||||
0.1.0 (2025-10-07) – Erstanlage.
|
||||
FILE: app/routers/graph.py
|
||||
DESCRIPTION: Liefert Graph-Daten (Knoten/Kanten) für UI-Visualisierungen basierend auf einer Seed-ID. (WP4)
|
||||
VERSION: 0.1.0
|
||||
STATUS: Active
|
||||
DEPENDENCIES: qdrant_client, app.models.dto, app.core.graph_adapter, app.config
|
||||
LAST_ANALYSIS: 2025-12-15
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
+55
-23
@@ -1,12 +1,17 @@
|
||||
"""
|
||||
app/routers/ingest.py
|
||||
API-Endpunkte für WP-11 (Discovery & Persistence).
|
||||
Delegiert an Services.
|
||||
FILE: app/routers/ingest.py
|
||||
DESCRIPTION: Endpunkte für WP-11. Nimmt Markdown entgegen.
|
||||
Refactored für WP-14: Nutzt BackgroundTasks für non-blocking Save.
|
||||
VERSION: 0.7.0 (Fix: Timeout WP-14)
|
||||
STATUS: Active
|
||||
DEPENDENCIES: app.core.ingestion, app.services.discovery, fastapi, pydantic
|
||||
"""
|
||||
|
||||
import os
|
||||
import time
|
||||
import logging
|
||||
from fastapi import APIRouter, HTTPException
|
||||
import asyncio
|
||||
from fastapi import APIRouter, HTTPException, BackgroundTasks
|
||||
from pydantic import BaseModel
|
||||
from typing import Optional, Dict, Any
|
||||
|
||||
@@ -16,7 +21,7 @@ from app.services.discovery import DiscoveryService
|
||||
logger = logging.getLogger(__name__)
|
||||
router = APIRouter()
|
||||
|
||||
# Services Init (Global oder via Dependency Injection)
|
||||
# Services Init
|
||||
discovery_service = DiscoveryService()
|
||||
|
||||
class AnalyzeRequest(BaseModel):
|
||||
@@ -32,7 +37,32 @@ class SaveResponse(BaseModel):
|
||||
status: str
|
||||
file_path: str
|
||||
note_id: str
|
||||
stats: Dict[str, Any]
|
||||
message: str # Neu für UX Feedback
|
||||
stats: Dict[str, Any] # Kann leer sein bei async processing
|
||||
|
||||
# --- Background Task Wrapper ---
|
||||
async def run_ingestion_task(markdown_content: str, filename: str, vault_root: str, folder: str):
|
||||
"""
|
||||
Führt die Ingestion im Hintergrund aus, damit der Request nicht blockiert.
|
||||
"""
|
||||
logger.info(f"🔄 Background Task started: Ingesting {filename}...")
|
||||
try:
|
||||
ingest_service = IngestionService()
|
||||
result = await ingest_service.create_from_text(
|
||||
markdown_content=markdown_content,
|
||||
filename=filename,
|
||||
vault_root=vault_root,
|
||||
folder=folder
|
||||
)
|
||||
# Hier könnte man später Notification-Services (Websockets) triggern
|
||||
if result.get("status") == "error":
|
||||
logger.error(f"❌ Background Ingestion Error for {filename}: {result.get('error')}")
|
||||
else:
|
||||
logger.info(f"✅ Background Task finished: {filename} ({result.get('chunks_count')} Chunks)")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"❌ Critical Background Task Failure: {e}", exc_info=True)
|
||||
|
||||
|
||||
@router.post("/analyze")
|
||||
async def analyze_draft(req: AnalyzeRequest):
|
||||
@@ -40,7 +70,6 @@ async def analyze_draft(req: AnalyzeRequest):
|
||||
WP-11 Intelligence: Liefert Link-Vorschläge via DiscoveryService.
|
||||
"""
|
||||
try:
|
||||
# Hier rufen wir jetzt den verbesserten Service auf
|
||||
result = await discovery_service.analyze_draft(req.text, req.type)
|
||||
return result
|
||||
except Exception as e:
|
||||
@@ -48,9 +77,10 @@ async def analyze_draft(req: AnalyzeRequest):
|
||||
return {"suggestions": [], "error": str(e)}
|
||||
|
||||
@router.post("/save", response_model=SaveResponse)
|
||||
async def save_note(req: SaveRequest):
|
||||
async def save_note(req: SaveRequest, background_tasks: BackgroundTasks):
|
||||
"""
|
||||
WP-11 Persistence: Speichert und indiziert.
|
||||
WP-14 Fix: Startet Ingestion im Hintergrund (Fire & Forget).
|
||||
Verhindert Timeouts bei aktiver Smart-Edge-Allocation (WP-15).
|
||||
"""
|
||||
try:
|
||||
vault_root = os.getenv("MINDNET_VAULT_ROOT", "./vault")
|
||||
@@ -61,29 +91,31 @@ async def save_note(req: SaveRequest):
|
||||
except: pass
|
||||
|
||||
final_filename = req.filename or f"draft_{int(time.time())}.md"
|
||||
ingest_service = IngestionService()
|
||||
|
||||
# Async Call
|
||||
result = await ingest_service.create_from_text(
|
||||
# Wir geben sofort eine ID zurück (optimistisch),
|
||||
# auch wenn die echte ID erst nach dem Parsing feststeht.
|
||||
# Für UI-Feedback nutzen wir den Filename.
|
||||
|
||||
# Task in die Queue schieben
|
||||
background_tasks.add_task(
|
||||
run_ingestion_task,
|
||||
markdown_content=req.markdown_content,
|
||||
filename=final_filename,
|
||||
vault_root=abs_vault_root,
|
||||
folder=req.folder
|
||||
)
|
||||
|
||||
if result.get("status") == "error":
|
||||
raise HTTPException(status_code=500, detail=result.get("error"))
|
||||
|
||||
return SaveResponse(
|
||||
status="success",
|
||||
file_path=result.get("path", "unknown"),
|
||||
note_id=result.get("note_id", "unknown"),
|
||||
status="queued",
|
||||
file_path=os.path.join(req.folder, final_filename),
|
||||
note_id="pending",
|
||||
message="Speicherung & KI-Analyse im Hintergrund gestartet.",
|
||||
stats={
|
||||
"chunks": result.get("chunks_count", 0),
|
||||
"edges": result.get("edges_count", 0)
|
||||
"chunks": -1, # Indikator für Async
|
||||
"edges": -1
|
||||
}
|
||||
)
|
||||
except HTTPException as he: raise he
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Save failed: {e}", exc_info=True)
|
||||
raise HTTPException(status_code=500, detail=f"Save failed: {str(e)}")
|
||||
logger.error(f"Save dispatch failed: {e}", exc_info=True)
|
||||
raise HTTPException(status_code=500, detail=f"Save dispatch failed: {str(e)}")
|
||||
@@ -1,160 +0,0 @@
|
||||
"""
|
||||
Version 0.1
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any, Optional, List
|
||||
import uuid
|
||||
|
||||
from fastapi import APIRouter
|
||||
from pydantic import BaseModel, Field
|
||||
from qdrant_client import QdrantClient
|
||||
from qdrant_client.http.models import (
|
||||
Distance,
|
||||
VectorParams,
|
||||
PointStruct,
|
||||
Filter,
|
||||
FieldCondition,
|
||||
MatchValue,
|
||||
)
|
||||
|
||||
from ..config import get_settings
|
||||
from ..embeddings import embed_texts
|
||||
|
||||
router = APIRouter(prefix="/qdrant", tags=["qdrant"])
|
||||
|
||||
def _client() -> QdrantClient:
|
||||
s = get_settings()
|
||||
return QdrantClient(url=s.QDRANT_URL, api_key=s.QDRANT_API_KEY)
|
||||
|
||||
def _col(name: str) -> str:
|
||||
return f"{get_settings().COLLECTION_PREFIX}_{name}"
|
||||
|
||||
def _uuid5(s: str) -> str:
|
||||
"""Deterministic UUIDv5 from arbitrary string (server-side point id)."""
|
||||
return str(uuid.uuid5(uuid.NAMESPACE_URL, s))
|
||||
|
||||
# --- Models ---
|
||||
class BaseMeta(BaseModel):
|
||||
note_id: str = Field(..., description="Stable ID of the note (e.g., hash of vault-relative path)")
|
||||
title: Optional[str] = Field(None, description="Note or chunk title")
|
||||
path: Optional[str] = Field(None, description="Vault-relative path to the .md file")
|
||||
Typ: Optional[str] = None
|
||||
Status: Optional[str] = None
|
||||
tags: Optional[List[str]] = None
|
||||
Rolle: Optional[List[str]] = None # allow list
|
||||
|
||||
class UpsertChunkRequest(BaseMeta):
|
||||
chunk_id: str = Field(..., description="Stable ID of the chunk within the note")
|
||||
text: str = Field(..., description="Chunk text content")
|
||||
links: Optional[List[str]] = Field(default=None, description="Outbound links detected in the chunk")
|
||||
|
||||
class UpsertNoteRequest(BaseMeta):
|
||||
text: Optional[str] = Field(None, description="Full note text (optional)")
|
||||
|
||||
class UpsertEdgeRequest(BaseModel):
|
||||
src_note_id: str
|
||||
dst_note_id: Optional[str] = None
|
||||
src_chunk_id: Optional[str] = None
|
||||
dst_chunk_id: Optional[str] = None
|
||||
relation: str = Field(default="links_to")
|
||||
link_text: Optional[str] = None
|
||||
|
||||
class QueryRequest(BaseModel):
|
||||
query: str
|
||||
limit: int = 5
|
||||
note_id: Optional[str] = None
|
||||
path: Optional[str] = None
|
||||
tags: Optional[List[str]] = None
|
||||
|
||||
# --- Helpers ---
|
||||
def _ensure_collections():
|
||||
s = get_settings()
|
||||
cli = _client()
|
||||
# chunks
|
||||
try:
|
||||
cli.get_collection(_col("chunks"))
|
||||
except Exception:
|
||||
cli.recreate_collection(_col("chunks"), vectors_config=VectorParams(size=s.VECTOR_SIZE, distance=Distance.COSINE))
|
||||
# notes
|
||||
try:
|
||||
cli.get_collection(_col("notes"))
|
||||
except Exception:
|
||||
cli.recreate_collection(_col("notes"), vectors_config=VectorParams(size=s.VECTOR_SIZE, distance=Distance.COSINE))
|
||||
# edges (dummy vector of size 1)
|
||||
try:
|
||||
cli.get_collection(_col("edges"))
|
||||
except Exception:
|
||||
cli.recreate_collection(_col("edges"), vectors_config=VectorParams(size=1, distance=Distance.COSINE))
|
||||
|
||||
@router.post("/upsert_chunk", summary="Upsert a chunk into mindnet_chunks")
|
||||
def upsert_chunk(req: UpsertChunkRequest) -> dict:
|
||||
_ensure_collections()
|
||||
cli = _client()
|
||||
vec = embed_texts([req.text])[0]
|
||||
payload: dict[str, Any] = req.model_dump()
|
||||
payload.pop("text", None)
|
||||
payload["preview"] = (req.text[:240] + "…") if len(req.text) > 240 else req.text
|
||||
qdrant_id = _uuid5(f"chunk:{req.chunk_id}")
|
||||
pt = PointStruct(id=qdrant_id, vector=vec, payload=payload)
|
||||
cli.upsert(collection_name=_col("chunks"), points=[pt])
|
||||
return {"status": "ok", "id": qdrant_id}
|
||||
|
||||
@router.post("/upsert_note", summary="Upsert a note into mindnet_notes")
|
||||
def upsert_note(req: UpsertNoteRequest) -> dict:
|
||||
_ensure_collections()
|
||||
cli = _client()
|
||||
text_for_embedding = req.text if req.text else (req.title or req.note_id)
|
||||
vec = embed_texts([text_for_embedding])[0]
|
||||
payload: dict[str, Any] = req.model_dump()
|
||||
payload.pop("text", None)
|
||||
qdrant_id = _uuid5(f"note:{req.note_id}")
|
||||
pt = PointStruct(id=qdrant_id, vector=vec, payload=payload)
|
||||
cli.upsert(collection_name=_col("notes"), points=[pt])
|
||||
return {"status": "ok", "id": qdrant_id}
|
||||
|
||||
@router.post("/upsert_edge", summary="Upsert a graph edge into mindnet_edges")
|
||||
def upsert_edge(req: UpsertEdgeRequest) -> dict:
|
||||
_ensure_collections()
|
||||
cli = _client()
|
||||
payload = req.model_dump()
|
||||
vec = [0.0]
|
||||
raw_edge_id = f"{req.src_note_id}|{req.src_chunk_id or ''}->{req.dst_note_id or ''}|{req.dst_chunk_id or ''}|{req.relation}"
|
||||
qdrant_id = _uuid5(f"edge:{raw_edge_id}")
|
||||
pt = PointStruct(id=qdrant_id, vector=vec, payload=payload)
|
||||
cli.upsert(collection_name=_col("edges"), points=[pt])
|
||||
return {"status": "ok", "id": qdrant_id}
|
||||
|
||||
@router.post("/query", summary="Vector query over mindnet_chunks with optional filters")
|
||||
def query(req: QueryRequest) -> dict:
|
||||
_ensure_collections()
|
||||
cli = _client()
|
||||
vec = embed_texts([req.query])[0]
|
||||
|
||||
flt: Optional[Filter] = None
|
||||
conds = []
|
||||
if req.note_id:
|
||||
conds.append(FieldCondition(key="note_id", match=MatchValue(value=req.note_id)))
|
||||
if req.path:
|
||||
conds.append(FieldCondition(key="path", match=MatchValue(value=req.path)))
|
||||
if req.tags:
|
||||
for t in req.tags:
|
||||
conds.append(FieldCondition(key="tags", match=MatchValue(value=t)))
|
||||
if conds:
|
||||
flt = Filter(must=conds)
|
||||
|
||||
res = cli.search(collection_name=_col("chunks"), query_vector=vec, limit=req.limit, with_payload=True, with_vectors=False, query_filter=flt)
|
||||
hits = []
|
||||
for p in res:
|
||||
pl = p.payload or {}
|
||||
hits.append({
|
||||
"chunk_id": p.id,
|
||||
"score": p.score,
|
||||
"note_id": pl.get("note_id"),
|
||||
"title": pl.get("title"),
|
||||
"path": pl.get("path"),
|
||||
"preview": pl.get("preview"),
|
||||
"tags": pl.get("tags"),
|
||||
})
|
||||
return {"results": hits}
|
||||
+7
-18
@@ -1,23 +1,12 @@
|
||||
"""
|
||||
app/routers/query.py — Query-Endpunkte (WP-04)
|
||||
FILE: app/routers/query.py
|
||||
DESCRIPTION: Klassische Such-Endpunkte (Semantic & Hybrid). Initiiert asynchrones Feedback-Logging und ruft den richtigen Retriever Modus auf
|
||||
VERSION: 0.2.0
|
||||
STATUS: Active
|
||||
DEPENDENCIES: app.models.dto, app.core.retriever, app.services.feedback_service
|
||||
LAST_ANALYSIS: 2025-12-15
|
||||
"""
|
||||
|
||||
Zweck:
|
||||
Stellt POST /query bereit und ruft den passenden Retriever-Modus auf.
|
||||
Kompatibilität:
|
||||
Python 3.12+, FastAPI 0.110+
|
||||
Version:
|
||||
0.1.0 (Erstanlage)
|
||||
Stand:
|
||||
2025-10-07
|
||||
Bezug:
|
||||
- app/core/retriever.py
|
||||
- app/models/dto.py
|
||||
Nutzung:
|
||||
app.include_router(query.router, prefix="/query", tags=["query"])
|
||||
Änderungsverlauf:
|
||||
0.2.0 (2025-12-07) - Update für WP04c Feedback
|
||||
0.1.0 (2025-10-07) – Erstanlage.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
from fastapi import APIRouter, HTTPException, BackgroundTasks
|
||||
from app.models.dto import QueryRequest, QueryResponse
|
||||
|
||||
+6
-17
@@ -1,21 +1,10 @@
|
||||
"""
|
||||
app/routers/tools.py — Tool-Definitionen für Ollama/n8n/MCP (read-only)
|
||||
|
||||
Zweck:
|
||||
Liefert Funktions-Schemas (OpenAI-/Ollama-kompatibles Tool-JSON) für:
|
||||
- mindnet_query -> POST /query
|
||||
- mindnet_subgraph -> GET /graph/{note_id}
|
||||
Kompatibilität:
|
||||
Python 3.12+, FastAPI 0.110+
|
||||
Version:
|
||||
0.1.1 (query ODER query_vector möglich)
|
||||
Stand:
|
||||
2025-10-07
|
||||
Nutzung:
|
||||
app.include_router(tools.router, prefix="/tools", tags=["tools"])
|
||||
Änderungsverlauf:
|
||||
0.1.1 (2025-10-07) – mindnet_query: oneOf(query, query_vector).
|
||||
0.1.0 (2025-10-07) – Erstanlage.
|
||||
FILE: app/routers/tools.py
|
||||
DESCRIPTION: Liefert JSON-Schemas für die Integration als 'Tools' in Agents (Ollama/OpenAI). Read-Only.
|
||||
VERSION: 0.1.1
|
||||
STATUS: Active
|
||||
DEPENDENCIES: fastapi
|
||||
LAST_ANALYSIS: 2025-12-15
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
@@ -1,12 +1,11 @@
|
||||
"""
|
||||
app/services/discovery.py
|
||||
Service für Link-Vorschläge und Knowledge-Discovery (WP-11).
|
||||
|
||||
Features:
|
||||
- Sliding Window Analyse für lange Texte.
|
||||
- Footer-Scan für Projekt-Referenzen.
|
||||
- 'Matrix-Logic' für intelligente Kanten-Typen (Experience -> Value = based_on).
|
||||
- Async & Nomic-Embeddings kompatibel.
|
||||
FILE: app/services/discovery.py
|
||||
DESCRIPTION: Service für WP-11. Analysiert Texte, findet Entitäten und schlägt typisierte Verbindungen vor ("Matrix-Logic").
|
||||
VERSION: 0.6.0
|
||||
STATUS: Active
|
||||
DEPENDENCIES: app.core.qdrant, app.models.dto, app.core.retriever
|
||||
EXTERNAL_CONFIG: config/types.yaml
|
||||
LAST_ANALYSIS: 2025-12-15
|
||||
"""
|
||||
import logging
|
||||
import asyncio
|
||||
|
||||
@@ -1,12 +1,10 @@
|
||||
"""
|
||||
app/services/embeddings_client.py — Text→Embedding Service
|
||||
|
||||
Zweck:
|
||||
Einheitlicher Client für Embeddings via Ollama (Nomic).
|
||||
Stellt sicher, dass sowohl Async (Ingestion) als auch Sync (Retriever)
|
||||
denselben Vektorraum (768 Dim) nutzen.
|
||||
|
||||
Version: 2.5.0 (Unified Ollama)
|
||||
FILE: app/services/embeddings_client.py
|
||||
DESCRIPTION: Unified Embedding Client. Nutzt Ollama API (HTTP). Ersetzt lokale sentence-transformers.
|
||||
VERSION: 2.5.0
|
||||
STATUS: Active
|
||||
DEPENDENCIES: httpx, requests, app.config
|
||||
LAST_ANALYSIS: 2025-12-15
|
||||
"""
|
||||
from __future__ import annotations
|
||||
import os
|
||||
|
||||
@@ -1,9 +1,10 @@
|
||||
"""
|
||||
app/services/feedback_service.py
|
||||
Service zum Loggen von Suchanfragen und Feedback (WP-04c).
|
||||
Speichert Daten als JSONL für späteres Self-Tuning (WP-08).
|
||||
|
||||
Version: 1.1 (Chat-Support)
|
||||
FILE: app/services/feedback_service.py
|
||||
DESCRIPTION: Schreibt Search- und Feedback-Logs in JSONL-Dateien.
|
||||
VERSION: 1.1
|
||||
STATUS: Active
|
||||
DEPENDENCIES: app.models.dto
|
||||
LAST_ANALYSIS: 2025-12-15
|
||||
"""
|
||||
import json
|
||||
import os
|
||||
|
||||
@@ -1,88 +0,0 @@
|
||||
"""
|
||||
app/services/llm_ollama.py — Ollama-Integration & Prompt-Bau (WP-04)
|
||||
|
||||
Zweck:
|
||||
Prompt-Template & (optionaler) lokaler Aufruf von Ollama. Der Aufruf ist
|
||||
bewusst gekapselt und kann gefahrlos deaktiviert bleiben, bis ihr ein
|
||||
konkretes Modell konfigurieren wollt.
|
||||
Kompatibilität:
|
||||
Python 3.12+
|
||||
Version:
|
||||
0.1.0 (Erstanlage)
|
||||
Stand:
|
||||
2025-10-07
|
||||
Bezug:
|
||||
WP-04/05 Kontextbereitstellung für LLM
|
||||
Nutzung:
|
||||
from app.services.llm_ollama import build_prompt, call_ollama
|
||||
Änderungsverlauf:
|
||||
0.1.0 (2025-10-07) – Erstanlage.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
from typing import List, Dict, Optional
|
||||
import subprocess
|
||||
import json
|
||||
|
||||
PROMPT_TEMPLATE = """System: You are a helpful expert.
|
||||
User: {question}
|
||||
|
||||
Context (ranked):
|
||||
{contexts}
|
||||
|
||||
Task: Answer precisely. At the end, list sources (note title + section) and important edge paths.
|
||||
"""
|
||||
|
||||
|
||||
def build_context_block(items: List[Dict]) -> str:
|
||||
"""Formatiert Top-K-Kontexte (Chunks) für den Prompt."""
|
||||
lines = []
|
||||
for i, it in enumerate(items, 1):
|
||||
note = it.get("note_title", "") or it.get("note_id", "")
|
||||
sec = it.get("section", "") or it.get("section_title", "")
|
||||
sc = it.get("score", 0)
|
||||
txt = it.get("text", "") or it.get("body", "") or ""
|
||||
lines.append(f"{i}) {note} — {sec} [score={sc:.2f}]\n{txt}\n")
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
def build_prompt(question: str, contexts: List[Dict]) -> str:
|
||||
"""Setzt Frage + Kontexte in ein konsistentes Template."""
|
||||
return PROMPT_TEMPLATE.format(question=question, contexts=build_context_block(contexts))
|
||||
|
||||
|
||||
def call_ollama(prompt: str, model: str = "llama3.1:8b", timeout_s: int = 120) -> Optional[str]:
|
||||
"""
|
||||
Optionaler lokaler Aufruf von `ollama run`.
|
||||
Rückgabe: generierter Text oder None bei Fehler/Abbruch.
|
||||
Hinweis: Nur nutzen, wenn Ollama lokal installiert/konfiguriert ist.
|
||||
"""
|
||||
try:
|
||||
proc = subprocess.run(
|
||||
["ollama", "run", model],
|
||||
input=prompt.encode("utf-8"),
|
||||
stdout=subprocess.PIPE,
|
||||
stderr=subprocess.PIPE,
|
||||
timeout=timeout_s,
|
||||
check=False,
|
||||
)
|
||||
out = proc.stdout.decode("utf-8", errors="replace")
|
||||
# viele ollama Builds streamen JSON-Zeilen; robust extrahieren:
|
||||
try:
|
||||
# Falls JSONL, letztes "response" zusammenfassen
|
||||
texts = []
|
||||
for line in out.splitlines():
|
||||
line = line.strip()
|
||||
if not line:
|
||||
continue
|
||||
try:
|
||||
obj = json.loads(line)
|
||||
if "response" in obj:
|
||||
texts.append(obj["response"])
|
||||
except Exception:
|
||||
texts.append(line)
|
||||
return "".join(texts).strip()
|
||||
except Exception:
|
||||
return out.strip()
|
||||
except Exception:
|
||||
return None
|
||||
@@ -1,6 +1,11 @@
|
||||
"""
|
||||
app/services/llm_service.py — LLM Client
|
||||
Version: 2.8.0 (Configurable Concurrency Limit)
|
||||
FILE: app/services/llm_service.py
|
||||
DESCRIPTION: Asynchroner Client für Ollama. Verwaltet Prompts und Background-Last (Semaphore).
|
||||
VERSION: 2.8.0
|
||||
STATUS: Active
|
||||
DEPENDENCIES: httpx, yaml, asyncio, app.config
|
||||
EXTERNAL_CONFIG: config/prompts.yaml
|
||||
LAST_ANALYSIS: 2025-12-15
|
||||
"""
|
||||
|
||||
import httpx
|
||||
|
||||
@@ -1,6 +1,10 @@
|
||||
"""
|
||||
app/services/semantic_analyzer.py — Edge Validation & Filtering
|
||||
Version: 2.0 (Update: Background Priority for Batch Jobs)
|
||||
FILE: app/services/semantic_analyzer.py
|
||||
DESCRIPTION: KI-gestützte Kanten-Validierung. Nutzt LLM (Background-Priority), um Kanten präzise einem Chunk zuzuordnen.
|
||||
VERSION: 2.1.0 (Fix: Strict Edge String Validation against LLM Hallucinations)
|
||||
STATUS: Active
|
||||
DEPENDENCIES: app.services.llm_service, json, logging
|
||||
LAST_ANALYSIS: 2025-12-16
|
||||
"""
|
||||
|
||||
import json
|
||||
@@ -17,6 +21,34 @@ class SemanticAnalyzer:
|
||||
def __init__(self):
|
||||
self.llm = LLMService()
|
||||
|
||||
def _is_valid_edge_string(self, edge_str: str) -> bool:
|
||||
"""
|
||||
Prüft, ob ein String eine valide Kante im Format 'kind:target' ist.
|
||||
Verhindert, dass LLM-Geschwätz ("Here is the list: ...") als Kante durchrutscht.
|
||||
"""
|
||||
if not isinstance(edge_str, str) or ":" not in edge_str:
|
||||
return False
|
||||
|
||||
parts = edge_str.split(":", 1)
|
||||
kind = parts[0].strip()
|
||||
target = parts[1].strip()
|
||||
|
||||
# Regel 1: Ein 'kind' (Beziehungstyp) darf keine Leerzeichen enthalten.
|
||||
# Erlaubt: "derived_from", "related_to"
|
||||
# Verboten: "derived end of instruction", "Here is the list"
|
||||
if " " in kind:
|
||||
return False
|
||||
|
||||
# Regel 2: Plausible Länge für den Typ
|
||||
if len(kind) > 40 or len(kind) < 2:
|
||||
return False
|
||||
|
||||
# Regel 3: Target darf nicht leer sein
|
||||
if not target:
|
||||
return False
|
||||
|
||||
return True
|
||||
|
||||
async def assign_edges_to_chunk(self, chunk_text: str, all_edges: List[str], note_type: str) -> List[str]:
|
||||
"""
|
||||
Sendet einen Chunk und eine Liste potenzieller Kanten an das LLM.
|
||||
@@ -55,14 +87,13 @@ class SemanticAnalyzer:
|
||||
)
|
||||
|
||||
try:
|
||||
# 4. LLM Call mit Traffic Control (NEU: priority="background")
|
||||
# Wir nutzen die "Slow Lane", damit der User im Chat nicht warten muss.
|
||||
# 4. LLM Call mit Traffic Control
|
||||
response_json = await self.llm.generate_raw_response(
|
||||
prompt=final_prompt,
|
||||
force_json=True,
|
||||
max_retries=5,
|
||||
base_delay=5.0,
|
||||
priority="background" # <--- WICHTIG: Drosselung aktivieren
|
||||
priority="background"
|
||||
)
|
||||
|
||||
# LOG: Raw Response Preview
|
||||
@@ -87,30 +118,38 @@ class SemanticAnalyzer:
|
||||
valid_edges = []
|
||||
|
||||
# 6. Robuste Validierung (List vs Dict)
|
||||
# Wir sammeln erst alle Strings ein
|
||||
raw_candidates = []
|
||||
|
||||
if isinstance(data, list):
|
||||
# Standardfall: ["kind:target", ...]
|
||||
valid_edges = [str(e) for e in data if isinstance(e, str) and ":" in e]
|
||||
raw_candidates = data
|
||||
|
||||
elif isinstance(data, dict):
|
||||
# Abweichende Formate behandeln
|
||||
logger.info(f"ℹ️ [SemanticAnalyzer] LLM lieferte Dict statt Liste. Versuche Reparatur. Keys: {list(data.keys())}")
|
||||
|
||||
for key, val in data.items():
|
||||
# Fall A: {"edges": ["kind:target"]}
|
||||
if key.lower() in ["edges", "results", "kanten", "matches"] and isinstance(val, list):
|
||||
valid_edges.extend([str(e) for e in val if isinstance(e, str) and ":" in e])
|
||||
raw_candidates.extend(val)
|
||||
|
||||
# Fall B: {"kind": "target"}
|
||||
# Fall B: {"kind": "target"} (Beziehung als Key)
|
||||
elif isinstance(val, str):
|
||||
valid_edges.append(f"{key}:{val}")
|
||||
raw_candidates.append(f"{key}:{val}")
|
||||
|
||||
# Fall C: {"kind": ["target1", "target2"]}
|
||||
elif isinstance(val, list):
|
||||
for target in val:
|
||||
if isinstance(target, str):
|
||||
valid_edges.append(f"{key}:{target}")
|
||||
raw_candidates.append(f"{key}:{target}")
|
||||
|
||||
# Safety: Filtere nur Kanten, die halbwegs valide aussehen
|
||||
# 7. Strict Validation Loop
|
||||
for e in raw_candidates:
|
||||
e_str = str(e)
|
||||
if self._is_valid_edge_string(e_str):
|
||||
valid_edges.append(e_str)
|
||||
else:
|
||||
logger.debug(f" [SemanticAnalyzer] Invalid edge format rejected: '{e_str}'")
|
||||
|
||||
# Safety: Filtere nur Kanten, die halbwegs valide aussehen (Doppelcheck)
|
||||
final_result = [e for e in valid_edges if ":" in e]
|
||||
|
||||
# LOG: Ergebnis
|
||||
|
||||
+73
-59
@@ -1,4 +1,4 @@
|
||||
version: 2.4.0 # Optimized for Async Intelligence & Hybrid Router
|
||||
version: 2.6.0 # Final WP-15 Config: Smart Edges & Strict/Soft Chunking
|
||||
|
||||
# ==============================================================================
|
||||
# 1. CHUNKING PROFILES
|
||||
@@ -7,7 +7,6 @@ version: 2.4.0 # Optimized for Async Intelligence & Hybrid Router
|
||||
chunking_profiles:
|
||||
|
||||
# A. SHORT & FAST
|
||||
# Für Glossar, Tasks, Risiken. Kleine Schnipsel.
|
||||
sliding_short:
|
||||
strategy: sliding_window
|
||||
enable_smart_edge_allocation: false
|
||||
@@ -16,7 +15,6 @@ chunking_profiles:
|
||||
overlap: [30, 50]
|
||||
|
||||
# B. STANDARD & FAST
|
||||
# Der "Traktor": Robust für Quellen, Journal, Daily Logs.
|
||||
sliding_standard:
|
||||
strategy: sliding_window
|
||||
enable_smart_edge_allocation: false
|
||||
@@ -24,10 +22,8 @@ chunking_profiles:
|
||||
max: 650
|
||||
overlap: [50, 100]
|
||||
|
||||
# C. SMART FLOW (Performance-Safe Mode)
|
||||
# Für Konzepte, Projekte, Erfahrungen.
|
||||
# HINWEIS: 'enable_smart_edge_allocation' ist vorerst FALSE, um Ollama
|
||||
# bei der Generierung nicht zu überlasten. Später wieder aktivieren.
|
||||
# C. SMART FLOW (Text-Fluss)
|
||||
# Nutzt Sliding Window, aber mit LLM-Kanten-Analyse.
|
||||
sliding_smart_edges:
|
||||
strategy: sliding_window
|
||||
enable_smart_edge_allocation: true
|
||||
@@ -35,12 +31,38 @@ chunking_profiles:
|
||||
max: 600
|
||||
overlap: [50, 80]
|
||||
|
||||
# D. SMART STRUCTURE
|
||||
# Für Profile, Werte, Prinzipien. Trennt hart an Überschriften (H2).
|
||||
# D. SMART STRUCTURE (Soft Split)
|
||||
# Trennt bevorzugt an H2, fasst aber kleine Abschnitte zusammen ("Soft Mode").
|
||||
structured_smart_edges:
|
||||
strategy: by_heading
|
||||
enable_smart_edge_allocation: true
|
||||
split_level: 2
|
||||
strict_heading_split: false
|
||||
max: 600
|
||||
target: 400
|
||||
overlap: [50, 80]
|
||||
|
||||
# E. SMART STRUCTURE STRICT (H2 Hard Split)
|
||||
# Trennt ZWINGEND an jeder H2.
|
||||
# Verhindert, dass "Vater" und "Partner" (Profile) oder Werte verschmelzen.
|
||||
structured_smart_edges_strict:
|
||||
strategy: by_heading
|
||||
enable_smart_edge_allocation: true
|
||||
split_level: 2
|
||||
strict_heading_split: true # Hard Mode
|
||||
max: 600
|
||||
target: 400
|
||||
overlap: [50, 80]
|
||||
|
||||
# F. SMART STRUCTURE DEEP (H3 Hard Split + Merge-Check)
|
||||
# Spezialfall für "Leitbild Prinzipien":
|
||||
# - Trennt H1, H2, H3 hart.
|
||||
# - Aber: Merged "leere" H2 (Tier 2) mit der folgenden H3 (MP1).
|
||||
structured_smart_edges_strict_L3:
|
||||
strategy: by_heading
|
||||
enable_smart_edge_allocation: true
|
||||
split_level: 3
|
||||
strict_heading_split: true
|
||||
max: 600
|
||||
target: 400
|
||||
overlap: [50, 80]
|
||||
@@ -59,24 +81,13 @@ defaults:
|
||||
|
||||
types:
|
||||
|
||||
# --- KERNTYPEN (Hoch priorisiert & Smart) ---
|
||||
# --- KERNTYPEN ---
|
||||
|
||||
experience:
|
||||
chunking_profile: sliding_smart_edges
|
||||
retriever_weight: 0.90
|
||||
edge_defaults: ["derived_from", "references"]
|
||||
# Hybrid Classifier: Wenn diese Worte fallen, ist es eine Experience
|
||||
detection_keywords:
|
||||
- "passiert"
|
||||
- "erlebt"
|
||||
- "gefühl"
|
||||
- "situation"
|
||||
- "stolz"
|
||||
- "geärgert"
|
||||
- "reaktion"
|
||||
- "moment"
|
||||
- "konflikt"
|
||||
# Ghostwriter Schema: Sprechende Anweisungen für besseren Textfluss
|
||||
detection_keywords: ["passiert", "erlebt", "gefühl", "situation", "reaktion"]
|
||||
schema:
|
||||
- "Situation (Was ist passiert?)"
|
||||
- "Meine Reaktion (Was habe ich getan?)"
|
||||
@@ -87,48 +98,37 @@ types:
|
||||
chunking_profile: sliding_smart_edges
|
||||
retriever_weight: 0.97
|
||||
edge_defaults: ["references", "depends_on"]
|
||||
detection_keywords:
|
||||
- "projekt"
|
||||
- "vorhaben"
|
||||
- "ziel ist"
|
||||
- "meilenstein"
|
||||
- "planen"
|
||||
- "starten"
|
||||
- "mission"
|
||||
detection_keywords: ["projekt", "vorhaben", "ziel ist", "planen", "starten"]
|
||||
schema:
|
||||
- "Mission & Zielsetzung"
|
||||
- "Aktueller Status & Blockaden"
|
||||
- "Nächste konkrete Schritte"
|
||||
- "Stakeholder & Ressourcen"
|
||||
|
||||
decision:
|
||||
chunking_profile: structured_smart_edges
|
||||
retriever_weight: 1.00 # MAX: Entscheidungen sind Gesetz
|
||||
# Strict, damit jede Entscheidung atomar bleibt
|
||||
chunking_profile: structured_smart_edges_strict
|
||||
retriever_weight: 1.00
|
||||
edge_defaults: ["caused_by", "references"]
|
||||
detection_keywords:
|
||||
- "entschieden"
|
||||
- "wahl"
|
||||
- "optionen"
|
||||
- "alternativen"
|
||||
- "beschluss"
|
||||
- "adr"
|
||||
detection_keywords: ["entschieden", "wahl", "optionen", "alternativen", "adr"]
|
||||
schema:
|
||||
- "Kontext & Problemstellung"
|
||||
- "Betrachtete Optionen (Alternativen)"
|
||||
- "Betrachtete Optionen"
|
||||
- "Die Entscheidung"
|
||||
- "Begründung (Warum diese Wahl?)"
|
||||
- "Begründung"
|
||||
|
||||
# --- PERSÖNLICHKEIT & IDENTITÄT ---
|
||||
|
||||
value:
|
||||
chunking_profile: structured_smart_edges
|
||||
# Strict, damit Werte nicht verschwimmen
|
||||
chunking_profile: structured_smart_edges_strict
|
||||
retriever_weight: 1.00
|
||||
edge_defaults: ["related_to"]
|
||||
detection_keywords: ["wert", "wichtig ist", "moral", "ethik"]
|
||||
schema: ["Definition", "Warum mir das wichtig ist", "Leitsätze für den Alltag"]
|
||||
schema: ["Definition", "Warum mir das wichtig ist", "Leitsätze"]
|
||||
|
||||
principle:
|
||||
chunking_profile: structured_smart_edges
|
||||
# L3 Strict für P3/P3a und Tier2/MP1 Logik
|
||||
chunking_profile: structured_smart_edges_strict_L3
|
||||
retriever_weight: 0.95
|
||||
edge_defaults: ["derived_from", "references"]
|
||||
detection_keywords: ["prinzip", "regel", "grundsatz", "leitlinie"]
|
||||
@@ -138,11 +138,11 @@ types:
|
||||
chunking_profile: sliding_short
|
||||
retriever_weight: 0.90
|
||||
edge_defaults: ["related_to"]
|
||||
detection_keywords: ["glaube", "überzeugung", "denke dass", "meinung"]
|
||||
schema: ["Der Glaubenssatz", "Ursprung & Reflexion"]
|
||||
|
||||
profile:
|
||||
chunking_profile: structured_smart_edges
|
||||
# Strict: Jede Rolle (H2) muss ein eigener Chunk sein
|
||||
chunking_profile: structured_smart_edges_strict
|
||||
retriever_weight: 0.70
|
||||
edge_defaults: ["references", "related_to"]
|
||||
schema: ["Rolle / Identität", "Fakten & Daten", "Historie"]
|
||||
@@ -159,8 +159,8 @@ types:
|
||||
chunking_profile: sliding_short
|
||||
retriever_weight: 0.85
|
||||
edge_defaults: ["related_to", "blocks"]
|
||||
detection_keywords: ["risiko", "gefahr", "bedrohung", "problem", "angst"]
|
||||
schema: ["Beschreibung des Risikos", "Mögliche Auswirkungen", "Gegenmaßnahmen"]
|
||||
detection_keywords: ["risiko", "gefahr", "bedrohung"]
|
||||
schema: ["Beschreibung des Risikos", "Auswirkungen", "Gegenmaßnahmen"]
|
||||
|
||||
# --- BASIS & WISSEN ---
|
||||
|
||||
@@ -168,10 +168,7 @@ types:
|
||||
chunking_profile: sliding_smart_edges
|
||||
retriever_weight: 0.60
|
||||
edge_defaults: ["references", "related_to"]
|
||||
schema:
|
||||
- "Definition"
|
||||
- "Kontext & Hintergrund"
|
||||
- "Verwandte Konzepte"
|
||||
schema: ["Definition", "Kontext", "Verwandte Konzepte"]
|
||||
|
||||
task:
|
||||
chunking_profile: sliding_short
|
||||
@@ -183,19 +180,36 @@ types:
|
||||
chunking_profile: sliding_standard
|
||||
retriever_weight: 0.80
|
||||
edge_defaults: ["references", "related_to"]
|
||||
schema: ["Log-Eintrag", "Gedanken & Erkenntnisse"]
|
||||
schema: ["Log-Eintrag", "Gedanken"]
|
||||
|
||||
source:
|
||||
chunking_profile: sliding_standard
|
||||
retriever_weight: 0.50
|
||||
edge_defaults: []
|
||||
schema:
|
||||
- "Metadaten (Autor, URL, Datum)"
|
||||
- "Kernaussage / Zusammenfassung"
|
||||
- "Zitate & Notizen"
|
||||
schema: ["Metadaten", "Zusammenfassung", "Zitate"]
|
||||
|
||||
glossary:
|
||||
chunking_profile: sliding_short
|
||||
retriever_weight: 0.40
|
||||
edge_defaults: ["related_to"]
|
||||
schema: ["Begriff", "Definition"]
|
||||
schema: ["Begriff", "Definition"]
|
||||
|
||||
person:
|
||||
chunking_profile: sliding_standard
|
||||
retriever_weight: 0.50
|
||||
edge_defaults: ["related_to"]
|
||||
schema: ["Rolle", "Beziehung", "Kontext"]
|
||||
|
||||
event:
|
||||
chunking_profile: sliding_standard
|
||||
retriever_weight: 0.60
|
||||
edge_defaults: ["related_to"]
|
||||
schema: ["Datum & Ort", "Teilnehmer", "Ergebnisse"]
|
||||
|
||||
# --- FALLBACK ---
|
||||
|
||||
default:
|
||||
chunking_profile: sliding_standard
|
||||
retriever_weight: 1.00
|
||||
edge_defaults: ["references"]
|
||||
schema: ["Inhalt"]
|
||||
@@ -0,0 +1,112 @@
|
||||
# Mindnet v2.6 – Documentation Map & Governance
|
||||
**Status:** Active
|
||||
**Context:** Central Navigation & Maintenance Guide
|
||||
|
||||
## 1. Zweck dieses Dokuments
|
||||
|
||||
Diese Karte dient Entwicklern, dem Mindmaster und KI-Agenten als **zentraler Einstiegspunkt**. Sie beantwortet zwei Fragen:
|
||||
1. **Navigation:** In welcher Datei finde ich Informationen zu Thema X?
|
||||
2. **Wartung:** Ich arbeite an Feature Y – welche Dateien muss ich aktualisieren?
|
||||
|
||||
---
|
||||
|
||||
## 2. Verzeichnisstruktur & Inhalte
|
||||
|
||||
Das Repository ist in **logische Domänen** unterteilt.
|
||||
|
||||
### 📂 00_General (Grundlagen)
|
||||
*Zielgruppe: Alle*
|
||||
| Datei | Inhalt & Zweck |
|
||||
| :--- | :--- |
|
||||
| `00_vision_and_strategy.md` | **Strategie.** Warum bauen wir das? Prinzipien (Privacy, Local-First), High-Level Architektur. |
|
||||
| `00_glossary.md` | **Definitionen.** Was bedeutet "Smart Edge", "Traffic Control", "Chunk"? Verhindert Begriffsverwirrung. |
|
||||
| `00_documentation_map.md` | **Dieser Index.** Navigationshilfe. |
|
||||
|
||||
### 📂 01_User_Manual (Anwendung)
|
||||
*Zielgruppe: Mindmaster, Autoren, Power-User*
|
||||
| Datei | Inhalt & Zweck |
|
||||
| :--- | :--- |
|
||||
| `01_chat_usage_guide.md` | **Bedienung.** Wie steuere ich die Personas (Berater, Spiegel)? Wie nutze ich das Feedback? |
|
||||
| `01_knowledge_design.md` | **Content-Regeln.** Die "Bibel" für den Vault. Erklärt Note-Typen, Matrix-Logik und Markdown-Syntax. |
|
||||
|
||||
### 📂 02_Concepts (Fachliche Logik)
|
||||
*Zielgruppe: Architekten, Product Owner*
|
||||
| Datei | Inhalt & Zweck |
|
||||
| :--- | :--- |
|
||||
| `02_concept_graph_logic.md` | **Graph-Theorie.** Abstrakte Erklärung von Knoten, Kanten, Provenance und Idempotenz. |
|
||||
| `02_concept_ai_personality.md`| **KI-Verhalten.** Konzepte hinter dem Hybrid Router, Empathie-Modell und "Teach-the-AI". |
|
||||
|
||||
### 📂 03_Technical_Reference (Technik & Code)
|
||||
*Zielgruppe: Entwickler, DevOps. (Enthält JSON/YAML Beispiele)*
|
||||
| Datei | Inhalt & Zweck |
|
||||
| :--- | :--- |
|
||||
| `03_tech_data_model.md` | **Datenbank.** Exakte Qdrant-Schemas (Payloads) und Index-Anforderungen. |
|
||||
| `03_tech_ingestion_pipeline.md`| **Import.** Ablauflogik (13 Schritte), Chunker-Profile, Smart Edge Allocation. |
|
||||
| `03_tech_retrieval_scoring.md` | **Suche.** Die mathematischen Formeln für Scoring, Hybrid Search und Explanation Layer. |
|
||||
| `03_tech_chat_backend.md` | **API & LLM.** Implementation des Routers, Traffic Control (Semaphore) und Feedback-Traceability. |
|
||||
| `03_tech_frontend.md` | **UI & Graph.** Architektur des Streamlit-Frontends, State-Management, Cytoscape-Integration und Editor-Logik. |
|
||||
| `03_tech_configuration.md` | **Config.** Referenztabellen für `.env`, `types.yaml` und `retriever.yaml`. |
|
||||
|
||||
### 📂 04_Operations (Betrieb)
|
||||
*Zielgruppe: Administratoren*
|
||||
| Datei | Inhalt & Zweck |
|
||||
| :--- | :--- |
|
||||
| `04_admin_operations.md` | **Runbook.** Installation, Docker-Setup, Backup/Restore, Troubleshooting Guide. |
|
||||
|
||||
### 📂 05_Development (Code)
|
||||
*Zielgruppe: Entwickler*
|
||||
| Datei | Inhalt & Zweck |
|
||||
| :--- | :--- |
|
||||
| `05_developer_guide.md` | **Workflow.** Hardware-Setup (Win/Pi/Beelink), Git-Flow, Test-Befehle, Modul-Interna. |
|
||||
| `05_genai_best_practices.md` | **AI Workflow.** Prompt-Library, Templates und Best Practices für die Entwicklung mit LLMs. |
|
||||
|
||||
### 📂 06_Roadmap & 99_Archive
|
||||
*Zielgruppe: Projektleitung*
|
||||
| Datei | Inhalt & Zweck |
|
||||
| :--- | :--- |
|
||||
| `06_active_roadmap.md` | **Zukunft.** Aktive Workpackages (WP16+), Release-Planung und WP-Historie (Tabelle). |
|
||||
| `99_legacy_workpackages.md` | **Vergangenheit.** Detaillierte Archivdaten zu abgeschlossenen WPs (WP01–WP15). |
|
||||
|
||||
---
|
||||
|
||||
## 3. Maintenance Guide: "Welche Datei muss ich ändern?"
|
||||
|
||||
Nutze diese Matrix, wenn du ein Workpackage bearbeitest, um die Dokumentation konsistent zu halten.
|
||||
|
||||
| Wenn du arbeitest an... | ...aktualisiere diese Dateien: |
|
||||
| :--- | :--- |
|
||||
| **Neuen Note-Typen** | 1. `01_knowledge_design.md` (Für Autoren)<br>2. `03_tech_configuration.md` (Technische Referenz)<br>3. `05_developer_guide.md` (Erweiterungs-How-To) |
|
||||
| **Importer / Parsing** | `03_tech_ingestion_pipeline.md` |
|
||||
| **Datenbank-Schema** | `03_tech_data_model.md` (Payloads anpassen) |
|
||||
| **Retrieval / Scoring** | `03_tech_retrieval_scoring.md` (Formeln anpassen) |
|
||||
| **Frontend / Visualisierung** | 1. `03_tech_frontend.md` (Technische Details)<br>2. `01_chat_usage_guide.md` (Bedienung) |
|
||||
| **Chat-Logik / Prompts**| 1. `02_concept_ai_personality.md` (Konzept)<br>2. `03_tech_chat_backend.md` (Tech)<br>3. `01_chat_usage_guide.md` (User-Sicht) |
|
||||
| **Deployment / Server** | `04_admin_operations.md` |
|
||||
| **Neuen Features (Allg.)**| `06_active_roadmap.md` (Status Update) |
|
||||
|
||||
---
|
||||
|
||||
## 4. Prinzipien für die Dokumentation (Governance)
|
||||
|
||||
Damit dieses System wartbar bleibt (auch für KI-Agenten wie NotebookLM), gelten folgende Regeln:
|
||||
|
||||
1. **Single Source of Truth:**
|
||||
Kopiere keine Informationen. Referenziere sie.
|
||||
* *Ausnahme:* Konkrete JSON-Beispiele in `03_Technical_Reference`. Diese müssen dort stehen, damit Entwickler nicht suchen müssen.
|
||||
|
||||
2. **Konkrete Beispiele:**
|
||||
Technische Dokumente (`03_*`) müssen **immer** Code-Snippets (JSON, YAML, Shell) enthalten. Abstrakte Beschreibungen reichen nicht für die Implementierung.
|
||||
|
||||
3. **Human Readable:**
|
||||
User Manuals (`01_*`) müssen Narrative und Szenarien enthalten ("Stell dir vor..."), keine technischen Auflistungen.
|
||||
|
||||
4. **KI-Optimiert (Context Header):**
|
||||
Jede Datei muss mit einem YAML-Frontmatter beginnen, der `context`, `audience` und `scope` definiert. Dies hilft RAG-Systemen, den Inhalt korrekt einzuordnen.
|
||||
|
||||
```yaml
|
||||
---
|
||||
doc_type: technical_reference
|
||||
audience: developer
|
||||
context: "Beschreibung der Scoring-Formel."
|
||||
---
|
||||
```
|
||||
@@ -0,0 +1,44 @@
|
||||
---
|
||||
doc_type: glossary
|
||||
audience: all
|
||||
status: active
|
||||
version: 2.6.0
|
||||
context: "Definitionen zentraler Begriffe und Entitäten im Mindnet-System."
|
||||
---
|
||||
|
||||
# Mindnet Glossar
|
||||
|
||||
**Quellen:** `appendix.md`, `Overview.md`
|
||||
|
||||
## Kern-Entitäten
|
||||
|
||||
* **Note:** Repräsentiert eine Markdown-Datei. Die fachliche Haupteinheit.
|
||||
* **Chunk:** Ein Textabschnitt einer Note. Die technische Sucheinheit (Vektor). Durch neue Strategien kann dies ein Fließtext-Abschnitt oder ein logisches Kapitel (Heading) sein.
|
||||
* **Edge:** Eine gerichtete Verbindung zwischen zwei Knoten (Chunks oder Notes).
|
||||
* **Vault:** Der lokale Ordner mit den Markdown-Dateien (Source of Truth).
|
||||
* **Frontmatter:** Der YAML-Header am Anfang einer Notiz (enthält `id`, `type`, `title`).
|
||||
|
||||
## Komponenten
|
||||
|
||||
* **Importer:** Das Python-Skript (`import_markdown.py`), das Markdown liest und in Qdrant schreibt.
|
||||
* **Retriever:** Die Komponente, die sucht. Nutzt hybrides Scoring (Semantik + Graph).
|
||||
* **Decision Engine:** Teil des Routers, der entscheidet, wie auf eine Anfrage reagiert wird (z.B. Strategie wählen).
|
||||
* **Hybrid Router v5:** Die Logik, die erkennt, ob der User eine Frage stellt (`RAG`) oder einen Befehl gibt (`INTERVIEW`).
|
||||
* **Draft Editor:** Die Web-UI-Komponente, in der generierte Notizen bearbeitet werden.
|
||||
* **Traffic Control (WP15):** Ein Mechanismus im `LLMService`, der Prioritäten verwaltet (`realtime` für Chat vs. `background` für Import) und Hintergrund-Tasks mittels Semaphoren drosselt.
|
||||
|
||||
## Konzepte & Features
|
||||
|
||||
* **Active Intelligence:** Feature im Web-Editor, das während des Schreibens automatisch Links vorschlägt.
|
||||
* **Smart Edge Allocation (WP15):** Ein KI-Verfahren, das prüft, ob ein Link in einer Notiz für einen spezifischen Textabschnitt relevant ist, statt ihn blind allen Chunks zuzuordnen.
|
||||
* **Strict Heading Split:** Chunking-Strategie, bei der Überschriften (z.B. H2) als harte Grenzen dienen. Verhindert das Vermischen von Themen (z.B. zwei unterschiedliche Rollen in einem Chunk). Besitzt ein "Safety Net" für zu lange Abschnitte.
|
||||
* **Soft Heading Split:** Chunking-Strategie, die Überschriften respektiert, aber kleine Abschnitte zusammenfasst, um Vektor-Kontext zu füllen ("Fuller Chunks").
|
||||
* **Healing Parser:** UI-Funktion, die fehlerhaften Output des LLMs (z.B. defektes YAML) automatisch repariert.
|
||||
* **Explanation Layer:** Die Schicht, die dem Nutzer erklärt, *warum* ein Suchergebnis gefunden wurde (z.B. "Weil Projekt X davon abhängt").
|
||||
* **Provenance:** Die Herkunft einer Kante.
|
||||
* `explicit`: Vom Mensch geschrieben.
|
||||
* `smart`: Vom LLM validiert.
|
||||
* `rule`: Durch Config-Regel erzeugt.
|
||||
* **Matrix Logic:** Regelwerk, das den Typ einer Kante basierend auf Quell- und Ziel-Typ bestimmt (z.B. Erfahrung -> Wert = `based_on`).
|
||||
* **Idempotenz:** Die Eigenschaft des Importers, bei mehrfacher Ausführung dasselbe Ergebnis zu liefern ohne Duplikate.
|
||||
* **Resurrection Pattern:** UI-Technik, um User-Eingaben beim Tab-Wechsel zu erhalten.
|
||||
@@ -0,0 +1,67 @@
|
||||
---
|
||||
doc_type: strategy
|
||||
audience: all
|
||||
status: active
|
||||
version: 2.6
|
||||
context: "Vision, Mission und Architekturprinzipien von Mindnet."
|
||||
---
|
||||
|
||||
# Mindnet Vision & Strategie
|
||||
|
||||
**Quellen:** `Programmplan_V2.2.md`
|
||||
|
||||
## 1. Programmauftrag
|
||||
|
||||
Mindnet v2.6 entwickelt ein persönliches, wachsendes KI-Gedächtnis. Es ist ein **Digitaler Zwilling**, der:
|
||||
- Wissen, Erfahrungen und Werte speichert.
|
||||
- Semantisch verknüpft (Graphen-basiert).
|
||||
- Als Dialogpartner agiert (RAG-Chat).
|
||||
- **Lokal und privat** läuft (Privacy First).
|
||||
|
||||
Es ist **kein statisches Archiv**, sondern ein lebendes System, das durch Interaktion (Feedback, Smart Edges) besser wird.
|
||||
|
||||
## 2. Vision
|
||||
|
||||
> „Ein persönliches semantisches Gedächtnis, das mit mir wächst, meine Persönlichkeit spiegelt und mir als intelligenter, erklärbarer, lernender Begleiter dient.“
|
||||
|
||||
**Kernprinzipien der Vision:**
|
||||
* **Erklärbarkeit:** Jede Antwort muss begründbar sein ("Why-Layer").
|
||||
* **Wachstum:** Das System startet klein und verdichtet sich.
|
||||
* **Autonomie:** Es schlägt fehlende Kanten selbstständig vor (Smart Edges).
|
||||
* **Persönlichkeit:** Es entscheidet basierend auf *deinen* Werten.
|
||||
|
||||
---
|
||||
|
||||
## 3. Architekturprinzipien
|
||||
|
||||
Die folgenden Prinzipien steuern jede technische Entscheidung:
|
||||
|
||||
1. **Late Binding (Späte Semantik):**
|
||||
Struktur und Interpretation werden in Konfigurationen (`types.yaml`, `prompts.yaml`) definiert, nicht direkt in den Vault-Dateien. Die "Persönlichkeit" ist Config, kein Code.
|
||||
|
||||
2. **Virtual Schema Layer:**
|
||||
Markdown-Dateien benötigen nur minimale, robuste Angaben (Frontmatter). Komplexität (Chunk-Größe, Gewichte) wird zur Laufzeit injiziert.
|
||||
|
||||
3. **Self-Healing Graph:**
|
||||
Der Graph wird regelmäßig auf Konsistenz geprüft. "Dangling Edges" werden bereinigt, fehlende Links durch Smart Edges ergänzt.
|
||||
|
||||
4. **Deterministische IDs:**
|
||||
Notes und Chunks erhalten stabile IDs (UUIDv5). Der Graph ist jederzeit aus dem Markdown wiederaufbaubar.
|
||||
|
||||
5. **Full Explainability:**
|
||||
Keine Blackbox. Jede Antwort liefert Metadaten (`[DECISION]`, `[PROJECT]`) und Begründungen.
|
||||
|
||||
6. **Persistence First:**
|
||||
Obsidian (Markdown) bleibt die **einzige Quelle der Wahrheit**. Die Datenbank ist nur ein abgeleiteter Cache.
|
||||
|
||||
7. **Minimalinvasives Schreiben:**
|
||||
Mindnet schreibt nie ungefragt in deine Notizen. Änderungen erfolgen nur über den Draft Editor oder mit expliziter Zustimmung.
|
||||
|
||||
8. **Incremental Growth:**
|
||||
Das System muss bereits mit wenigen Notizen nützlich sein.
|
||||
|
||||
9. **Observability:**
|
||||
Jeder Importlauf und jede Retriever-Anfrage ist logbar.
|
||||
|
||||
10. **Local First & Privacy:**
|
||||
Nutzung lokaler LLMs (Ollama) für Inference. Keine Daten verlassen den Server.
|
||||
@@ -0,0 +1,126 @@
|
||||
---
|
||||
doc_type: user_manual
|
||||
audience: user, mindmaster
|
||||
scope: chat, ui, feedback, graph
|
||||
status: active
|
||||
version: 2.6
|
||||
context: "Anleitung zur Nutzung der Web-Oberfläche, der Chat-Personas und des Graph Explorers."
|
||||
---
|
||||
|
||||
# Chat & Graph Usage Guide
|
||||
|
||||
**Quellen:** `user_guide.md`
|
||||
|
||||
## 1. Was Mindnet für dich tut
|
||||
|
||||
Mindnet ist ein **assoziatives Gedächtnis** mit Persönlichkeit. Es unterscheidet sich von einer reinen Suche dadurch, dass es **kontextsensitiv** agiert.
|
||||
|
||||
**Das Gedächtnis (Der Graph):**
|
||||
Wenn du nach "Projekt Alpha" suchst, findet Mindnet auch:
|
||||
* **Abhängigkeiten:** "Technologie X wird benötigt".
|
||||
* **Entscheidungen:** "Warum nutzen wir X?".
|
||||
* **Ähnliches:** "Projekt Beta war ähnlich".
|
||||
|
||||
**Der Zwilling (Die Personas):**
|
||||
Mindnet passt seinen Charakter an: Mal ist es der neutrale Bibliothekar, mal der strategische Berater, mal der empathische Spiegel.
|
||||
|
||||
---
|
||||
|
||||
## 2. Die Oberfläche (Web UI)
|
||||
|
||||
Seit Version 2.3.1 bedienst du Mindnet über eine grafische Oberfläche im Browser.
|
||||
|
||||
### 2.1 Der Chat-Bereich
|
||||
* **Intent-Badge:** Über jeder Antwort siehst du ein Label (z.B. **⚖️ Intent: DECISION**).
|
||||
* **Quellen-Karten:** Unter der Antwort findest du ausklappbare Karten ("Expanders").
|
||||
* **Grüner Punkt:** Hohe Relevanz (Score > 0.8).
|
||||
* **Klick darauf:** Zeigt den Textauszug und die **Begründung** (Explanation Layer).
|
||||
|
||||
### 2.2 Modus: 🕸️ Graph Explorer (Cytoscape)
|
||||
*Neu in v2.6*: Eine interaktive Karte deines Wissens.
|
||||
|
||||
**Die Farb-Logik:**
|
||||
* 🔴 **Roter Rahmen:** Das aktuelle **Zentrum** (Ego). Alle geladenen Knoten sind Nachbarn dieses Knotens.
|
||||
* 🟡 **Gelber Rahmen:** Der **inspizierte** Knoten. Dessen Details siehst du im "Data Inspector" und in der Action-Bar.
|
||||
|
||||
**Bedienung:**
|
||||
1. **Klick auf einen Knoten:** Wählt ihn aus (Gelb). Der Graph bleibt stabil, aber die Info-Leiste oben aktualisiert sich.
|
||||
2. **Button "🎯 Als Zentrum setzen":** Lädt den Graphen neu und macht den ausgewählten Knoten zum roten Zentrum.
|
||||
3. **Button "📝 Bearbeiten":** Springt mit dem Inhalt dieses Knotens direkt in den Editor.
|
||||
|
||||
**Layout & Persistenz:**
|
||||
Du kannst in der linken Spalte die Physik (Abstoßung, Kantenlänge) einstellen. Diese Einstellungen werden in der **URL gespeichert**. Du kannst den Link als Lesezeichen speichern, um genau diese Ansicht wiederzufinden.
|
||||
|
||||
### 2.3 Modus: 📝 Manueller Editor
|
||||
Ein Editor mit **"File System First"** Garantie.
|
||||
* Wenn du eine Datei bearbeitest, liest Mindnet sie direkt von der Festplatte.
|
||||
* **Resurrection:** Wenn du zwischendurch in den Graph wechselst und zurückkommst, ist dein getippter Text noch da.
|
||||
|
||||
---
|
||||
|
||||
## 3. Den Chat steuern (Intents)
|
||||
|
||||
Du steuerst die Persönlichkeit von Mindnet durch deine Wortwahl. Der **Hybrid Router v5** unterscheidet intelligent:
|
||||
|
||||
### 3.1 Frage-Modus (Wissen abrufen)
|
||||
Ausgelöst durch `?` oder W-Wörter.
|
||||
|
||||
* **Entscheidung ("Soll ich?"):** Der **Berater**.
|
||||
* Mindnet lädt deine Werte (`type: value`) und Ziele (`type: goal`).
|
||||
* *Beispiel:* "Soll ich Tool X nutzen?" -> "Nein, Tool X speichert Daten in den USA. Das verstößt gegen dein Prinzip 'Privacy First'."
|
||||
* **Empathie ("Ich fühle..."):** Der **Spiegel**.
|
||||
* Mindnet lädt deine Erfahrungen (`type: experience`).
|
||||
* *Beispiel:* "Ich bin frustriert." -> "Das erinnert mich an Projekt Y, da ging es uns ähnlich..."
|
||||
* **Fakten ("Was ist?"):** Der **Bibliothekar**.
|
||||
* Liefert präzise Definitionen.
|
||||
|
||||
### 3.2 Befehls-Modus (Interview)
|
||||
Ausgelöst durch Aussagen wie "Neues Projekt", "Ich will festhalten".
|
||||
|
||||
* **Was passiert:** Mindnet sucht nicht, sondern öffnet den **Draft-Editor**.
|
||||
* **Beispiel:** "Neue Erfahrung: Streit am Recyclinghof." -> Das System erstellt sofort eine strukturierte Notiz mit den Feldern "Situation", "Reaktion" und "Learning".
|
||||
|
||||
---
|
||||
|
||||
## 4. Ergebnisse interpretieren (Explanation Layer)
|
||||
|
||||
Mindnet liefert eine **Begründung** ("Reasons"), warum es etwas gefunden hat.
|
||||
Öffne eine Quellen-Karte, um zu sehen:
|
||||
* *"Hohe textuelle Übereinstimmung."* (Semantik)
|
||||
* *"Bevorzugt aufgrund des Typs 'decision'."* (Wichtigkeit)
|
||||
* *"Verweist auf 'Projekt X' via 'depends_on'."* (Graph-Kontext)
|
||||
|
||||
---
|
||||
|
||||
## 5. Feedback & Lernen
|
||||
|
||||
Mindnet wird schlauer, wenn du es pflegst.
|
||||
|
||||
* **Globales Feedback (Sterne):** Bewertet die generierte Antwort (Prompting, Tonfall).
|
||||
* **Granulares Feedback (Smileys):** Bewertet die einzelne Quelle.
|
||||
* 😞 (Sad): Irrelevant. (Senkt das Gewicht dieser Verbindung).
|
||||
* 😀 (Grin): Perfekter Treffer! (Stärkt diesen Typ/Kante).
|
||||
|
||||
---
|
||||
|
||||
## 6. Neues Wissen beisteuern (Authoring & Intelligence)
|
||||
|
||||
Mindnet lebt von deinem Input. Du hast drei Wege, Wissen einzugeben:
|
||||
|
||||
### 6.1 Weg A: Der Interview-Assistent (Auto-Drafting)
|
||||
1. **Start:** Schreibe im Chat: *"Ich möchte ein neues Projekt 'Apollo' starten."*
|
||||
2. **Generierung:** Mindnet erkennt `INTERVIEW`, wählt das Schema und erstellt einen Entwurf.
|
||||
3. **Editor:** Die UI zeigt den Entwurf (`status: draft`).
|
||||
* *Healing UI:* Falls das LLM Syntax-Fehler gemacht hat, hat der Editor sie bereits repariert.
|
||||
4. **Speichern:** Klicke auf "💾 Speichern".
|
||||
|
||||
### 6.2 Weg B: Der Intelligence-Workflow
|
||||
Wenn du im **manuellen Editor** schreibst, unterstützt dich Mindnet aktiv bei der Vernetzung:
|
||||
|
||||
1. **Schreiben:** Tippe deinen Text im Tab **"✏️ Inhalt"**.
|
||||
2. **Analysieren:** Wechsle zum Tab **"🧠 Intelligence"** und klicke auf **"🔍 Analyse starten"**. Das System scannt deinen Text (Vektor-Suche & Exact Match).
|
||||
3. **Vorschläge nutzen:**
|
||||
* **Exakte Treffer:** Das System erkennt Begriffe wie "KI-Gedächtnis" als Alias für "Mindnet".
|
||||
* **Semantische Treffer:** Das System findet inhaltlich verwandte Notizen.
|
||||
* **Klick auf "➕ Einfügen":** Fügt den Link (z.B. `[[rel:related_to Mindnet]]`) an der Cursor-Position ein.
|
||||
4. **Speichern:** Der Text wird sofort in den Vault geschrieben und indiziert.
|
||||
@@ -0,0 +1,192 @@
|
||||
---
|
||||
doc_type: user_manual
|
||||
audience: user, author
|
||||
scope: vault, markdown, schema
|
||||
status: active
|
||||
version: 2.7.0
|
||||
context: "Regelwerk für das Erstellen von Notizen im Vault. Die 'Source of Truth' für Autoren."
|
||||
---
|
||||
|
||||
# Knowledge Design Manual
|
||||
|
||||
**Quellen:** `knowledge_design.md`, `TYPE_REGISTRY_MANUAL.md`
|
||||
|
||||
## ⚡ Die 5 Goldenen Regeln (TL;DR)
|
||||
|
||||
Damit Mindnet als dein Digitaler Zwilling funktioniert, beachte beim Schreiben diese Grundsätze:
|
||||
|
||||
1. **Atomare Gedanken:** Eine Notiz = Ein Thema. Wenn du über zwei Projekte schreibst, mach zwei Notizen draus.
|
||||
2. **Explizite Typen:** Setze immer den `type` im Frontmatter. Mindnet behandelt eine `decision` ("Wir machen X") völlig anders als ein `concept` ("Was ist X").
|
||||
3. **Semantische Links:** Schreibe nicht nur `[[Link]]`, sondern `[[rel:depends_on Link]]`. Sag dem System *wie* Dinge zusammenhängen.
|
||||
4. **Werte & Ziele definieren:** Damit die **Decision Engine** dich beraten kann, musst du deine Kriterien (`type: value`, `type: goal`) explizit als Notizen anlegen.
|
||||
5. **Emotionales Bridging:** Damit die **Empathie** funktioniert, nutze in Erfahrungsberichten (`type: experience`) emotionale Schlüsselwörter ("Krise", "Freude", "Angst").
|
||||
|
||||
---
|
||||
|
||||
## 1. Zweck & Scope
|
||||
|
||||
Mindnet ist mehr als eine Dokumentablage. Es ist ein vernetztes System, das deine Persönlichkeit abbildet. Die Markdown-Dateien in deinem Vault sind die **einzige Quelle der Wahrheit** ("Source of Truth"). Was nicht im Markdown steht, existiert für das System nicht.
|
||||
|
||||
---
|
||||
|
||||
## 2. Note-Struktur & Frontmatter
|
||||
|
||||
Jede Notiz benötigt einen YAML-Header (Frontmatter).
|
||||
|
||||
**Pflichtfelder:**
|
||||
|
||||
```yaml
|
||||
---
|
||||
id: 20251212-projekt-alpha # Eindeutige Kennung (YYYYMMDD-slug empfohlen)
|
||||
title: Projekt Alpha # Sprechender Titel
|
||||
type: project # Steuert Chunking & Wichtigkeit
|
||||
status: active # active, archived, draft
|
||||
created: 2025-12-12 # ISO 8601
|
||||
tags: [ki, entwicklung] # Taxonomie
|
||||
---
|
||||
```
|
||||
|
||||
**Optionale Felder & Overrides (Advanced):**
|
||||
* `aliases`: [Alpha Projekt] – Wichtig für "Active Intelligence" (Exact Match).
|
||||
* `visibility`: internal (default) / public.
|
||||
* **NEU:** Du kannst die KI-Steuerung manuell überschreiben, wenn dir der Standard für den Typ nicht passt:
|
||||
* `chunking_profile`: Zwingt den Chunker in einen Modus (z.B. `structured_smart_edges_strict`).
|
||||
* `retriever_weight`: Setzt die Wichtigkeit manuell hoch/runter (z.B. `1.5` für extrem wichtig).
|
||||
|
||||
---
|
||||
|
||||
## 3. Typ-Referenz & Verhalten
|
||||
|
||||
Wähle den Typ, der die **Rolle** der Notiz am besten beschreibt. Der Typ steuert Chunking, Gewichtung und Kanten-Logik.
|
||||
|
||||
| Typ | Beschreibung & Einsatzzweck | Rolle im Chat (Intent) | Matrix-Logik |
|
||||
| :--- | :--- | :--- | :--- |
|
||||
| **`concept`** | Fachbegriffe, Theorien. Zeitloses Wissen. | **FACT** | Ziel für `uses` |
|
||||
| **`project`** | Ein Vorhaben mit Ziel, Dauer und Aufgaben. | **FACT / DECISION** | Quelle für `depends_on` |
|
||||
| **`experience`** | Persönliche Erfahrung, Lektion oder Erkenntnis. | **EMPATHY** | Quelle für `based_on` |
|
||||
| **`decision`** | Eine bewusst getroffene Entscheidung (ADR). | **DECISION** | Quelle für `caused_by` |
|
||||
| **`value`** | Ein persönlicher Wert oder ein Prinzip. | **DECISION** | Ziel für `based_on` |
|
||||
| **`principle`** | Handlungsleitlinie. | **DECISION** | Quelle für `derived_from` |
|
||||
| **`goal`** | Ein strategisches Ziel. | **DECISION** | Ziel für `related_to` |
|
||||
| **`risk`** | Ein identifiziertes Risiko. | **DECISION** | Quelle für `blocks` |
|
||||
| **`journal`** | Zeitbezogener Log-Eintrag. | **FACT** | - |
|
||||
|
||||
---
|
||||
|
||||
## 4. Edges & Verlinkung
|
||||
|
||||
Mindnet versteht Zusammenhänge durch Kanten.
|
||||
|
||||
### 4.1 Inline-Relationen (Semantische Verknüpfung)
|
||||
Dies ist die **mächtigste** Methode. Du sagst dem System explizit, **wie** Dinge zusammenhängen.
|
||||
|
||||
> "Daher [[rel:depends_on Qdrant]]."
|
||||
> "Dieses Konzept ist [[rel:similar_to Pinecone]]."
|
||||
|
||||
**Gültige Relationen:**
|
||||
* `depends_on`: Hängt ab von / Benötigt.
|
||||
* `blocks`: Blockiert oder gefährdet (z.B. Risiko -> Projekt).
|
||||
* `caused_by`: Wurde verursacht durch (Kausalität).
|
||||
* `similar_to`: Ähnelt / Ist vergleichbar mit.
|
||||
* `solves`: Löst (Problem).
|
||||
* `based_on`: Basiert auf (Fundament).
|
||||
|
||||
### 4.2 Callout-Edges
|
||||
Für Zusammenfassungen am Ende einer Notiz:
|
||||
|
||||
```markdown
|
||||
> [!edge] related_to: [[Vector Embeddings]] [[AI Agents]]
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 5. Schreiben für den KI-Zwilling (Szenarien)
|
||||
|
||||
Damit der **RAG-Chat** dich berät, musst du "Futter" für die Decision Engine liefern.
|
||||
|
||||
### Szenario A: Decision Engine (`DECISION`)
|
||||
* **Ziel:** Das System soll abwägen: "Passt Tool X zu mir?"
|
||||
* **Vorgehen:** Erstelle Notizen mit `type: value` oder `type: goal`.
|
||||
|
||||
**Beispiel Notiz:**
|
||||
```yaml
|
||||
---
|
||||
type: value
|
||||
title: Prinzip: Datensparsamkeit
|
||||
---
|
||||
Wir speichern nur das Minimum an Daten. Cloud-Uploads persönlicher Daten sind verboten, es sei denn, sie sind E2E-verschlüsselt.
|
||||
```
|
||||
|
||||
* **Effekt:** Wenn du fragst "Soll ich Notion nutzen?", lädt die Engine diese Notiz und antwortet: *"Nein, Notion ist SaaS ohne E2E. Das verletzt dein Prinzip der Datensparsamkeit."*
|
||||
|
||||
### Szenario B: Empathie (`EMPATHY`)
|
||||
* **Ziel:** Das System soll dich verstehen.
|
||||
* **Vorgehen:** Erstelle `type: experience` mit **emotionalen Brückenwörtern**.
|
||||
|
||||
**Beispiel Notiz:**
|
||||
```yaml
|
||||
---
|
||||
type: experience
|
||||
title: Erfahrung: Der Durchbruch nach der Krise
|
||||
tags: [krise, hoffnung, grau, angst]
|
||||
---
|
||||
Es gibt Projektphasen, da wirkt alles **sinnlos** und **grau**.
|
||||
Ich habe gelernt: Das ist oft das Zeichen kurz vor dem Durchbruch.
|
||||
```
|
||||
* **Effekt:** Bei "Alles ist grau" findet das System diese Notiz und spiegelt die Lektion zurück.
|
||||
|
||||
---
|
||||
|
||||
## 6. Best Practices & Beispiele
|
||||
|
||||
### 6.1 Beispiel: Projekt-Notiz (Standard)
|
||||
Projekte profitieren von `depends_on`, um Abhängigkeiten zu klären.
|
||||
|
||||
```markdown
|
||||
---
|
||||
id: 20251115-proj-mindnet
|
||||
title: Mindnet Implementierung
|
||||
type: project
|
||||
status: active
|
||||
---
|
||||
|
||||
# Mindnet Implementierung
|
||||
|
||||
Wir bauen ein persönliches Wissensnetz.
|
||||
|
||||
## Tech Stack
|
||||
Wir nutzen [[rel:depends_on Qdrant]] für die Vektorsuche und [[rel:depends_on FastAPI]] für das Backend.
|
||||
|
||||
## Architektur
|
||||
Das Konzept basiert auf [[RAG Architecture]].
|
||||
```
|
||||
|
||||
### 6.2 Beispiel: Advanced Tuning (Manuelles Override)
|
||||
Hier zwingen wir das System, eine Entscheidung extrem kleinteilig (`strict`) zu zerlegen und in der Suche maximal zu priorisieren.
|
||||
|
||||
```markdown
|
||||
---
|
||||
id: 20251120-adr-vektordb
|
||||
title: ADR: Wahl von Qdrant
|
||||
type: decision
|
||||
status: final
|
||||
tags: [architektur, db]
|
||||
# OVERRIDES: Wir wollen diese Notiz extrem wichtig machen und strikt trennen
|
||||
chunking_profile: structured_smart_edges_strict
|
||||
retriever_weight: 1.5
|
||||
---
|
||||
|
||||
# Entscheidung: Qdrant
|
||||
|
||||
Wir haben uns für Qdrant entschieden.
|
||||
|
||||
## Alternativen
|
||||
Wir haben auch [[rel:similar_to Pinecone]] und [[rel:similar_to Weaviate]] betrachtet.
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 7. Virtual Schema Layer
|
||||
|
||||
Grundsätzlich gilt das Prinzip des **Virtual Schema Layers**. Die Logik (wie `chunk_size`) wird zentral in der `types.yaml` verwaltet.
|
||||
**Aber:** Als Power-User hast du über die oben genannten Overrides (`chunking_profile`) jederzeit die Möglichkeit, aus diesem Standard auszubrechen, wenn eine spezifische Notiz eine Sonderbehandlung benötigt.
|
||||
@@ -0,0 +1,92 @@
|
||||
---
|
||||
doc_type: concept
|
||||
audience: architect, product_owner
|
||||
scope: ai, router, personas
|
||||
status: active
|
||||
version: 2.6
|
||||
context: "Fachkonzept der KI-Persönlichkeit, der Decision Engine und Erweiterungsstrategien."
|
||||
---
|
||||
|
||||
# Konzept: KI-Persönlichkeit & Router
|
||||
|
||||
**Quellen:** `mindnet_functional_architecture.md`, `Programmplan_V2.2.md`
|
||||
|
||||
Mindnet soll nicht wie eine Suchmaschine wirken, sondern wie ein **Digitaler Zwilling**. Dazu muss das System erkennen, **was** der Nutzer will, und seine "Persönlichkeit" anpassen.
|
||||
|
||||
## 1. Der Hybrid Router (Das Gehirn)
|
||||
|
||||
Jede Eingabe durchläuft den **Hybrid Router**. Er entscheidet über die Strategie.
|
||||
|
||||
### Modus A: RAG (Retrieval Augmented Generation)
|
||||
* *Intent:* Der Nutzer hat eine Frage oder ein Problem (`FACT`, `DECISION`, `EMPATHY`).
|
||||
* *Aktion:* Das System sucht im Gedächtnis und generiert eine Antwort.
|
||||
|
||||
### Modus B: Interview (Knowledge Capture)
|
||||
* *Intent:* Der Nutzer will Wissen speichern (`INTERVIEW`).
|
||||
* *Aktion:* Das System sucht **nicht**, sondern fragt ab und erstellt einen Draft.
|
||||
|
||||
---
|
||||
|
||||
## 2. Die Personas (Strategien)
|
||||
|
||||
Mindnet wechselt den Hut, je nach Situation.
|
||||
|
||||
### 2.1 Der Berater (Strategy: DECISION)
|
||||
* **Auslöser:** Fragen wie "Soll ich...?", "Was ist besser?".
|
||||
* **Strategic Retrieval:** Lädt aktiv Notizen der Typen `value` (Werte), `goal` (Ziele) und `risk` (Risiken), auch wenn sie im Text nicht direkt vorkommen.
|
||||
* **Reasoning:** *"Wäge die Fakten gegen meine Werte ab. Sei strikt bei Risiken."*
|
||||
|
||||
### 2.2 Der Spiegel (Strategy: EMPATHY)
|
||||
* **Auslöser:** Emotionale Aussagen ("Ich bin frustriert").
|
||||
* **Strategic Retrieval:** Lädt `experience` (Erfahrungen) und `belief` (Glaubenssätze).
|
||||
* **Reasoning:** *"Nutze meine eigenen Erfahrungen, um die Situation einzuordnen."*
|
||||
|
||||
### 2.3 Der Bibliothekar (Strategy: FACT)
|
||||
* **Auslöser:** Sachfragen ("Was ist Qdrant?").
|
||||
* **Behavior:** Präzise, neutral, kurz.
|
||||
|
||||
---
|
||||
|
||||
## 3. Future Concepts: The Empathic Digital Twin
|
||||
|
||||
Um Mindnet von einer Maschine zu einem echten Spiegel der Persönlichkeit zu entwickeln, sind folgende Konzepte in der Architektur angelegt:
|
||||
|
||||
### 3.1 Antizipation durch Erfahrung
|
||||
* **Konzept:** Das System soll Konsequenzen vorhersagen ("Was passiert, wenn...?").
|
||||
* **Logik:** *"In einer ähnlichen Situation (Projekt A) hat Entscheidung X zu Ergebnis Y geführt."* (Analogie-Schluss).
|
||||
|
||||
### 3.2 Empathie & "Ich"-Modus
|
||||
* **Konzept:** Das System antwortet im Tonfall des Nutzers.
|
||||
* **Umsetzung:** Few-Shot Prompting mit eigenen E-Mails/Texten als Stilvorlage.
|
||||
|
||||
### 3.3 Glaubenssätze & Rituale
|
||||
* **Konzept:** Berücksichtigung weicher Faktoren.
|
||||
* **Szenario:** Bei Terminplanungen werden Rituale ("Keine Meetings vor 10 Uhr") automatisch als harte Restriktion gegen Anfragen geprüft.
|
||||
|
||||
---
|
||||
|
||||
## 4. Erweiterbarkeit: Das "Teach-the-AI" Paradigma
|
||||
|
||||
Mindnet lernt nicht durch Training (Fine-Tuning), sondern durch **Konfiguration** und **Vernetzung**. Wenn du dem System ein neues Konzept beibringen willst, musst du an drei Stellen eingreifen.
|
||||
|
||||
**Beispiel: Du willst den Typ `risk` einführen.**
|
||||
|
||||
**1. Daten-Ebene (Physik)**
|
||||
In `types.yaml`: Definiere Gewicht und Verhalten.
|
||||
```yaml
|
||||
risk:
|
||||
retriever_weight: 0.90 # Hohe Priorität
|
||||
edge_defaults: ["blocks"] # Automatische Kante zu Projekten
|
||||
```
|
||||
|
||||
**2. Strategie-Ebene (Router)**
|
||||
In `decision_engine.yaml`: Wann soll das geladen werden?
|
||||
```yaml
|
||||
DECISION:
|
||||
inject_types: ["value", "risk"] # Füge 'risk' hinzu
|
||||
```
|
||||
|
||||
**3. Kognitive Ebene (Verständnis)**
|
||||
In `prompts.yaml`: Erkläre dem LLM, was ein Risiko ist.
|
||||
|
||||
**Fazit:** Nur wenn **Daten** (Vault), **Physik** (Config) und **Semantik** (Prompt) zusammenspielen, entsteht ein intelligenter Zwilling.
|
||||
@@ -0,0 +1,99 @@
|
||||
---
|
||||
doc_type: concept
|
||||
audience: architect, product_owner
|
||||
scope: graph, logic, provenance
|
||||
status: active
|
||||
version: 2.6
|
||||
context: "Fachliche Beschreibung des Wissensgraphen: Knoten, Kanten, Provenance und Matrix-Logik."
|
||||
---
|
||||
|
||||
# Konzept: Die Graph-Logik
|
||||
|
||||
**Quellen:** `mindnet_functional_architecture.md`, `chunking_strategy.md`
|
||||
|
||||
Mindnet ist keine reine Dokumentablage, sondern ein **semantischer Graph**. Dieses Dokument beschreibt, wie aus statischen Textdateien ein vernetztes Wissensobjekt wird.
|
||||
|
||||
## 1. Die Knoten (Nodes)
|
||||
|
||||
Der Graph besteht aus zwei Ebenen von Knoten.
|
||||
|
||||
### 1.1 Die Note (Das Fachobjekt)
|
||||
Eine Note repräsentiert ein atomares Konzept (z.B. "Projekt Alpha").
|
||||
* **Eigenschaften:** Titel, Typ, Tags, Erstellungsdatum.
|
||||
* **Rolle:** Sie ist der Container für Metadaten und steuert via `type`, wie der Inhalt verarbeitet wird (siehe `types.yaml`).
|
||||
* **Identität:** Definiert durch eine deterministische UUIDv5.
|
||||
|
||||
### 1.2 Der Chunk (Das Suchobjekt)
|
||||
Da LLMs (Large Language Models) nicht unendlich viel Text auf einmal lesen können, werden Notes in kleinere Segmente (**Chunks**) zerlegt.
|
||||
* **Eigenschaften:** Vektor (Embedding 768d), Textfenster, Link zum Vorgänger/Nachfolger.
|
||||
* **Rolle:** Dies sind die eigentlichen Treffer bei einer Suche.
|
||||
* **Hierarchie:** Jeder Chunk gehört streng zu einer Note (`belongs_to`).
|
||||
|
||||
---
|
||||
|
||||
## 2. Die Kanten (Edges)
|
||||
|
||||
Kanten machen aus isolierten Informationen Wissen. Mindnet nutzt gerichtete Kanten mit semantischer Bedeutung.
|
||||
|
||||
### 2.1 Semantische Typen
|
||||
|
||||
| Kanten-Typ | Frage, die er beantwortet | Beispiel |
|
||||
| :--- | :--- | :--- |
|
||||
| `references` | Worüber wird gesprochen? | Text erwähnt "Python". |
|
||||
| `depends_on` | Was ist Voraussetzung? | Projekt braucht "Budget". |
|
||||
| `caused_by` | Warum ist das passiert? | Bug durch "Commit X". |
|
||||
| `blocks` | Was steht im Weg? | Risiko blockiert "Release". |
|
||||
| `based_on` | Worauf fußt das? | Erfahrung basiert auf "Wert Y". |
|
||||
| `derived_from` | Woher kommt das? | Prinzip stammt aus "Buch Z". |
|
||||
| `related_to` | Was ist ähnlich? | "Hund" ist verwandt mit "Wolf". |
|
||||
| `solves` | Was ist die Lösung? | "Qdrant" löst "Vektorsuche". |
|
||||
|
||||
### 2.2 Provenance (Herkunft & Vertrauen)
|
||||
|
||||
Nicht alle Kanten sind gleich viel wert. Mindnet unterscheidet in v2.6 drei Qualitätsstufen (**Provenance**), um Konflikte aufzulösen.
|
||||
|
||||
**1. Explicit (Der Mensch hat es gesagt)**
|
||||
* *Quelle:* Inline-Links (`[[rel:...]]`) oder Wikilinks im Text.
|
||||
* *Vertrauen:* **Hoch (1.0)**.
|
||||
* *Bedeutung:* Dies ist hartes Faktenwissen. "Ich habe diesen Link bewusst gesetzt."
|
||||
|
||||
**2. Smart (Die KI hat es bestätigt)**
|
||||
* *Quelle:* Smart Edge Allocation (WP15).
|
||||
* *Vertrauen:* **Mittel (0.9)**.
|
||||
* *Bedeutung:* Ein LLM hat geprüft, ob der Link im Kontext dieses Textabschnitts wirklich relevant ist. Dies filtert "Rauschen" heraus (z.B. Links im Footer, die nichts mit dem Absatz zu tun haben).
|
||||
|
||||
**3. Rule (Die Regel hat es vermutet)**
|
||||
* *Quelle:* `types.yaml` Defaults.
|
||||
* *Vertrauen:* **Niedrig (0.7)**.
|
||||
* *Bedeutung:* Eine Heuristik. "Weil es ein Projekt ist, nehmen wir an, dass es von allen erwähnten Technologien abhängt."
|
||||
|
||||
---
|
||||
|
||||
## 3. Matrix-Logik (Kontext-Sensitivität)
|
||||
|
||||
Mit WP11 wurde eine Intelligenz eingeführt, die Kanten-Typen nicht nur anhand des Quell-Typs, sondern auch anhand des Ziel-Typs bestimmt ("Matrix").
|
||||
|
||||
**Logik-Beispiele:**
|
||||
|
||||
* **Quelle `experience` → Ziel `value`**
|
||||
* *Standard:* `references`
|
||||
* *Matrix:* `based_on` (Erfahrungen basieren auf Werten).
|
||||
|
||||
* **Quelle `principle` → Ziel `source` (Buch)**
|
||||
* *Standard:* `references`
|
||||
* *Matrix:* `derived_from` (Prinzipien stammen aus Quellen).
|
||||
|
||||
* **Quelle `project` → Ziel `tool`**
|
||||
* *Standard:* `references`
|
||||
* *Matrix:* `uses` (Projekte nutzen Tools).
|
||||
|
||||
*Nutzen:* Dies erlaubt im Chat präzise Fragen wie: *"Auf welchen Werten basiert diese Entscheidung?"* (Suche nach eingehenden `based_on` Kanten).
|
||||
|
||||
---
|
||||
|
||||
## 4. Idempotenz & Konsistenz
|
||||
|
||||
Das System garantiert fachliche Konsistenz auch bei mehrfachen Importen.
|
||||
* **Stabile IDs:** Importiert man dieselbe Datei zweimal, ändern sich die IDs der Knoten nicht.
|
||||
* **Keine Duplikate:** Kanten werden dedupliziert. Die "stärkere" Quelle (Explicit > Smart > Rule) gewinnt.
|
||||
* **Lösch-Garantie:** Wenn eine Notiz gelöscht wird, verschwinden auch alle ihre Chunks und ausgehenden Kanten (via `--sync-deletes`).
|
||||
@@ -0,0 +1,78 @@
|
||||
---
|
||||
doc_type: technical_reference
|
||||
audience: developer, architect
|
||||
scope: backend, chat, ollama, traffic_control
|
||||
status: active
|
||||
version: 2.6
|
||||
context: "Technische Implementierung des FastAPI-Routers, der Decision Engine und des Traffic Control Systems."
|
||||
---
|
||||
|
||||
# Chat Backend & Traffic Control
|
||||
|
||||
## 1. Hybrid Router (Decision Engine)
|
||||
|
||||
Der zentrale Einstiegspunkt für jede Chatanfrage ist der **Hybrid Router** (`app/routers/chat.py`). Er entscheidet dynamisch, welche Strategie gewählt wird, basierend auf dem User-Input.
|
||||
|
||||
### 1.1 Intent-Erkennung (Logik)
|
||||
|
||||
Der Router prüft den Input in drei Stufen (Wasserfall-Prinzip):
|
||||
|
||||
1. **Question Detection (Regelbasiert):**
|
||||
* Prüfung auf Vorhandensein von `?` oder W-Wörtern (Wer, Wie, Was, Soll ich).
|
||||
* Wenn positiv: **RAG Modus** (Interview wird blockiert).
|
||||
2. **Keyword Scan (Fast Path):**
|
||||
* Lädt `types.yaml` (Objekte, z.B. "Projekt") und `decision_engine.yaml` (Handlungen, z.B. "neu").
|
||||
* Wenn Match (z.B. "Projekt" + "neu"): **INTERVIEW Modus**.
|
||||
3. **LLM Fallback (Slow Path):**
|
||||
* Wenn unklar: Anfrage an LLM zur Klassifizierung.
|
||||
|
||||
### 1.2 RAG Flow (Technisch)
|
||||
|
||||
Wenn der Intent `FACT` oder `DECISION` ist, wird folgender Flow ausgeführt:
|
||||
|
||||
1. **Pre-Processing:** Query Rewriting (optional).
|
||||
2. **Context Enrichment:**
|
||||
* Abruf via `retriever.py` (Hybrid Search).
|
||||
* Injection von Metadaten (`[TYPE]`, `[SCORE]`) in den Prompt.
|
||||
3. **Prompt Construction:** Assembly aus System-Prompt (Persona) + Context + Query.
|
||||
4. **Streaming:** LLM-Antwort wird via **SSE (Server-Sent Events)** an den Client gestreamt.
|
||||
5. **Post-Processing:** Anhängen des `Explanation` Layers (JSON-Breakdown) an das Ende des Streams.
|
||||
|
||||
---
|
||||
|
||||
## 2. Traffic Control (WP-15)
|
||||
|
||||
Das Traffic Control System (`app/core/llm_service.py`) schützt das System vor Überlastung, wenn rechenintensive Hintergrundprozesse (Smart Edge Import) und Latenz-kritische Chat-Anfragen gleichzeitig laufen.
|
||||
|
||||
### 2.1 Prioritäts-Semaphor
|
||||
|
||||
Jeder LLM-Request muss ein `priority`-Flag setzen.
|
||||
|
||||
**Prioritäten-Levels:**
|
||||
|
||||
| Priority | Verwendung | Limitierung |
|
||||
| :--- | :--- | :--- |
|
||||
| **realtime** | Chat-Anfragen | Keine (Hardware-Limit) |
|
||||
| **background** | Smart Edge Allocation, Drafts | `MINDNET_LLM_BACKGROUND_LIMIT` |
|
||||
|
||||
**Funktionsweise:**
|
||||
* Hintergrund-Tasks nutzen `asyncio.Semaphore`.
|
||||
* Wenn das Limit (Default: 2) erreicht ist, warten weitere Import-Tasks.
|
||||
* Chat-Tasks umgehen die Semaphore und werden sofort bearbeitet.
|
||||
|
||||
### 2.2 Timeout-Konfiguration
|
||||
|
||||
Deadlocks werden durch strikte Timeouts verhindert, die in der `.env` definiert sind.
|
||||
|
||||
* **Chat:** `MINDNET_LLM_TIMEOUT` (Default: 300s).
|
||||
* **Frontend:** `MINDNET_API_TIMEOUT` (Default: 300s).
|
||||
|
||||
---
|
||||
|
||||
## 3. Feedback Traceability
|
||||
|
||||
Unterstützt das geplante Self-Tuning (WP08).
|
||||
|
||||
1. **Query ID:** Generiert bei jedem `/query` Call eine `UUIDv4`.
|
||||
2. **Logging:** Speichert einen Snapshot in `data/logs/query_snapshot.jsonl` (Input + Retrieved Context).
|
||||
3. **Feedback:** Der `/feedback` Endpoint verknüpft das User-Rating (1-5) mit der `query_id`.
|
||||
@@ -0,0 +1,143 @@
|
||||
---
|
||||
doc_type: technical_reference
|
||||
audience: developer, admin
|
||||
scope: configuration, env
|
||||
status: active
|
||||
version: 2.7.0
|
||||
context: "Referenztabellen für Umgebungsvariablen und YAML-Konfigurationen."
|
||||
---
|
||||
|
||||
# Konfigurations-Referenz
|
||||
|
||||
Dieses Dokument beschreibt die Steuerungsdateien von Mindnet.
|
||||
|
||||
## 1. Environment Variablen (`.env`)
|
||||
|
||||
Diese Variablen steuern die Infrastruktur, Timeouts und Feature-Flags.
|
||||
|
||||
| Variable | Default | Beschreibung |
|
||||
| :--- | :--- | :--- |
|
||||
| `QDRANT_URL` | `http://localhost:6333` | URL zur Vektor-DB API. |
|
||||
| `QDRANT_API_KEY` | *(leer)* | Optionaler Key für Absicherung. |
|
||||
| `COLLECTION_PREFIX` | `mindnet` | Namensraum für Collections (erzeugt `{prefix}_notes` etc). |
|
||||
| `VECTOR_DIM` | `768` | **Muss 768 sein** (für Nomic Embeddings). |
|
||||
| `MINDNET_TYPES_FILE` | `config/types.yaml` | Pfad zur Typ-Registry. |
|
||||
| `MINDNET_RETRIEVER_CONFIG`| `config/retriever.yaml`| Pfad zur Scoring-Konfiguration. |
|
||||
| `MINDNET_DECISION_CONFIG` | `config/decision_engine.yaml` | Pfad zur Router & Intent Config. |
|
||||
| `MINDNET_PROMPTS_PATH` | `config/prompts.yaml` | Pfad zu LLM Prompts. |
|
||||
| `MINDNET_LLM_MODEL` | `phi3:mini` | Name des Chat-Modells (Ollama). |
|
||||
| `MINDNET_EMBEDDING_MODEL` | `nomic-embed-text` | Name des Embedding-Modells (Ollama). |
|
||||
| `MINDNET_OLLAMA_URL` | `http://127.0.0.1:11434`| URL zum LLM-Server. |
|
||||
| `MINDNET_LLM_TIMEOUT` | `300.0` | Timeout in Sekunden (Erhöht für CPU Cold-Starts). |
|
||||
| `MINDNET_API_TIMEOUT` | `300.0` | Frontend Timeout (Erhöht für Smart Edge Wartezeiten). |
|
||||
| `MINDNET_LLM_BACKGROUND_LIMIT`| `2` | **Traffic Control (Neu):** Max. parallele Import-Tasks (Semaphore). |
|
||||
| `MINDNET_VAULT_ROOT` | `./vault` | Pfad für Write-Back Operationen (Drafts). |
|
||||
| `MINDNET_CHANGE_DETECTION_MODE` | `full` | **Change Detection (Neu):** `full` (Text + Meta) oder `body` (nur Text). |
|
||||
|
||||
---
|
||||
|
||||
## 2. Typ-Registry (`types.yaml`)
|
||||
|
||||
Steuert das Import-Verhalten, Chunking und die Kanten-Logik pro Typ.
|
||||
|
||||
### 2.1 Konfigurations-Hierarchie (Override-Logik)
|
||||
Seit Version 2.7.0 gilt für `chunking_profile` und `retriever_weight` folgende Priorität:
|
||||
|
||||
1. **Frontmatter (Höchste Prio):** Ein Wert direkt in der Markdown-Datei überschreibt alles.
|
||||
* *Beispiel:* `chunking_profile: structured_smart_edges_strict` im Header einer Notiz erzwingt diesen Splitter, egal welcher Typ eingestellt ist.
|
||||
2. **Type Config:** Der Standardwert für den `type` (z.B. `concept`) aus `types.yaml`.
|
||||
3. **Global Default:** Fallback aus `defaults` in `types.yaml`.
|
||||
|
||||
### 2.2 Typ-Referenztabelle
|
||||
|
||||
| Typ (`type`) | Chunk Profile (Standard) | Retriever Weight | Smart Edges? | Beschreibung |
|
||||
| :--- | :--- | :--- | :--- | :--- |
|
||||
| **concept** | `sliding_smart_edges` | 0.60 | Ja | Abstrakte Begriffe. |
|
||||
| **project** | `sliding_smart_edges` | 0.97 | Ja | Aktive Vorhaben. |
|
||||
| **decision** | `structured_smart_edges_strict` | 1.00 | Ja | Entscheidungen (ADRs). Atomar. |
|
||||
| **experience** | `sliding_smart_edges` | 0.90 | Ja | Persönliche Learnings. |
|
||||
| **journal** | `sliding_standard` | 0.80 | Nein | Logs / Dailies. |
|
||||
| **value** | `structured_smart_edges_strict` | 1.00 | Ja | Werte/Prinzipien. Atomar. |
|
||||
| **risk** | `sliding_short` | 0.90 | Nein | Risiken. |
|
||||
| **person** | `sliding_standard` | 0.50 | Nein | Profile. |
|
||||
| **source** | `sliding_standard` | 0.50 | Nein | Externe Quellen. |
|
||||
| **event** | `sliding_standard` | 0.60 | Nein | Meetings. |
|
||||
| **goal** | `sliding_smart_edges` | 0.95 | Nein | Strategische Ziele. |
|
||||
| **belief** | `sliding_short` | 0.90 | Nein | Glaubenssätze. |
|
||||
| **profile** | `structured_smart_edges_strict` | 0.70 | Nein | Rollenprofile. Strict Split. |
|
||||
| **principle** | `structured_smart_edges_strict_L3`| 0.95 | Nein | Prinzipien. Tiefer Split (H3) für Mikro-Prinzipien. |
|
||||
| **task** | `sliding_short` | 0.80 | Nein | Aufgaben. |
|
||||
| **glossary** | `sliding_short` | 0.40 | Nein | Begriffsdefinitionen. |
|
||||
| **default** | `sliding_standard` | 1.00 | Nein | Fallback. |
|
||||
|
||||
*Hinweis: `Smart Edges?` entspricht dem YAML-Key `enable_smart_edge_allocation: true`.*
|
||||
|
||||
---
|
||||
|
||||
## 3. Retriever Config (`retriever.yaml`)
|
||||
|
||||
Steuert die Gewichtung der Scoring-Formel (WP04a).
|
||||
|
||||
**Beispielkonfiguration:**
|
||||
|
||||
```yaml
|
||||
scoring:
|
||||
semantic_weight: 1.0 # Basis-Relevanz (Cosine Similarity)
|
||||
edge_weight: 0.7 # Einfluss des Graphen (Bonus)
|
||||
centrality_weight: 0.5 # Einfluss von Hubs
|
||||
|
||||
edge_weights:
|
||||
# Multiplikatoren für den Edge-Bonus
|
||||
depends_on: 1.5 # Harte Abhängigkeiten stark gewichten
|
||||
blocks: 1.5 # Risiken stark gewichten
|
||||
caused_by: 1.2 # Kausalitäten stärken
|
||||
related_to: 0.5 # Weiche Themen schwächer gewichten
|
||||
references: 0.8 # Standard-Referenzen
|
||||
based_on: 1.3 # Werte-Bezug
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 4. Edge Typen Referenz
|
||||
|
||||
Definiert die Semantik der `kind`-Felder in der Edge-Collection.
|
||||
|
||||
| Kind | Symmetrisch? | Herkunft (Primär) | Bedeutung |
|
||||
| :--- | :--- | :--- | :--- |
|
||||
| `references` | Nein | Wikilink | Standard-Verweis. "Erwähnt X". |
|
||||
| `belongs_to` | Nein | Struktur | Chunk gehört zu Note. |
|
||||
| `next` / `prev` | Ja | Struktur | Lesereihenfolge. |
|
||||
| `depends_on` | Nein | Inline / Default | Harte Abhängigkeit. |
|
||||
| `related_to` | Ja | Callout / Default | Thematische Nähe. |
|
||||
| `similar_to` | Ja | Inline | Inhaltliche Ähnlichkeit. |
|
||||
| `caused_by` | Nein | Inline | Kausalität. |
|
||||
| `solves` | Nein | Inline | Lösung für ein Problem. |
|
||||
| `blocks` | Nein | Inline | Blockade / Risiko. |
|
||||
| `derived_from` | Nein | Matrix | Herkunft (z.B. Prinzip -> Buch). |
|
||||
| `based_on` | Nein | Matrix | Fundament (z.B. Erfahrung -> Wert). |
|
||||
| `uses` | Nein | Matrix | Nutzung (z.B. Projekt -> Tool). |
|
||||
|
||||
---
|
||||
|
||||
## 5. Decision Engine (`decision_engine.yaml`)
|
||||
|
||||
Steuert den Hybrid Router (WP06). Definiert, welche Keywords welche Strategie auslösen.
|
||||
|
||||
**Beispielauszug:**
|
||||
|
||||
```yaml
|
||||
# Strategie-Definitionen
|
||||
strategies:
|
||||
DECISION:
|
||||
description: "Hilfe bei Entscheidungen"
|
||||
inject_types: ["value", "principle", "goal", "risk"] # Strategic Retrieval
|
||||
llm_fallback_enabled: true
|
||||
|
||||
INTERVIEW:
|
||||
description: "Wissenserfassung"
|
||||
trigger_keywords: ["erstellen", "neu", "anlegen", "festhalten"]
|
||||
|
||||
EMPATHY:
|
||||
description: "Emotionaler Support"
|
||||
inject_types: ["experience", "belief"]
|
||||
```
|
||||
@@ -0,0 +1,123 @@
|
||||
---
|
||||
doc_type: technical_reference
|
||||
audience: developer, architect
|
||||
scope: database, qdrant, schema
|
||||
status: active
|
||||
version: 2.7.0
|
||||
context: "Exakte Definition der Datenmodelle (Payloads) in Qdrant und Index-Anforderungen."
|
||||
---
|
||||
|
||||
# Technisches Datenmodell (Qdrant Schema)
|
||||
|
||||
## 1. Collections & Namenskonvention
|
||||
|
||||
Mindnet speichert Daten in drei getrennten Qdrant-Collections. Der Prefix ist via ENV `COLLECTION_PREFIX` konfigurierbar (Default: `mindnet`).
|
||||
|
||||
Das System nutzt folgende drei Collections:
|
||||
* `{prefix}_notes`: Metadaten der Dateien.
|
||||
* `{prefix}_chunks`: Vektorisierte Textsegmente.
|
||||
* `{prefix}_edges`: Gerichtete Graph-Kanten.
|
||||
|
||||
---
|
||||
|
||||
## 2. Note Payload (`mindnet_notes`)
|
||||
|
||||
Repräsentiert die Metadaten einer Markdown-Datei (1:1 Beziehung).
|
||||
|
||||
**JSON-Schema:**
|
||||
|
||||
```json
|
||||
{
|
||||
"note_id": "string (keyword)", // UUIDv5 (deterministisch) oder Slug
|
||||
"title": "string (text)", // Titel aus Frontmatter
|
||||
"type": "string (keyword)", // Logischer Typ (z.B. 'project', 'concept')
|
||||
"retriever_weight": "float", // Effektive Wichtigkeit (Frontmatter > Type > Default)
|
||||
"chunk_profile": "string", // Effektives Profil (Frontmatter > Type > Default)
|
||||
"edge_defaults": ["string"], // Liste der aktiven Default-Kanten
|
||||
"tags": ["string"], // Liste von Tags aus Frontmatter
|
||||
"aliases": ["string"], // Synonyme für Discovery (WP-11)
|
||||
"created": "string (iso-date)", // Erstellungsdatum
|
||||
"updated": "integer", // Timestamp (File Modification Time)
|
||||
"fulltext": "string (no-index)", // Gesamter Text (nur für Recovery/Export)
|
||||
|
||||
// NEU in v2.7: Multi-Hash für flexible Change Detection
|
||||
"hashes": {
|
||||
"body:parsed:canonical": "string", // Hash nur über den Text-Body
|
||||
"full:parsed:canonical": "string" // Hash über Text + Metadaten (Tags, Title, Config)
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
**Erforderliche Indizes:**
|
||||
Es müssen Payload-Indizes für folgende Felder existieren:
|
||||
* `note_id`
|
||||
* `type`
|
||||
* `tags`
|
||||
|
||||
---
|
||||
|
||||
## 3. Chunk Payload (`mindnet_chunks`)
|
||||
|
||||
Die atomare Sucheinheit. Enthält den Vektor.
|
||||
|
||||
**Vektor-Konfiguration:**
|
||||
* Modell: `nomic-embed-text`
|
||||
* Dimension: **768**
|
||||
* Metrik: Cosine Similarity
|
||||
|
||||
**JSON-Schema:**
|
||||
|
||||
```json
|
||||
{
|
||||
"chunk_id": "string (keyword)", // Format: {note_id}#c{index} (z.B. 'abc-123#c01')
|
||||
"note_id": "string (keyword)", // Foreign Key zur Note
|
||||
"type": "string (keyword)", // Kopie aus Note (Denormalisiert für Filterung)
|
||||
"text": "string (text)", // Reintext für Anzeige (ohne Overlap)
|
||||
"window": "string (text)", // Text + Overlap (Basis für Embedding)
|
||||
"ord": "integer", // Laufende Nummer (1..N) für Sortierung
|
||||
"retriever_weight": "float", // Geerbt von Note (für schnelles Re-Ranking)
|
||||
"chunk_profile": "string", // Geerbt von Note (für Debugging/Filtering)
|
||||
"neighbors_prev": ["string"], // ID des Vorgängers (Linked List)
|
||||
"neighbors_next": ["string"], // ID des Nachfolgers
|
||||
"section": "string", // Pfad/Überschrift, zu der der Chunk gehört
|
||||
"source_path": "string" // Relativer Pfad zur Datei
|
||||
}
|
||||
```
|
||||
|
||||
**Erforderliche Indizes:**
|
||||
Es müssen Payload-Indizes für folgende Felder existieren:
|
||||
* `note_id`
|
||||
* `chunk_id`
|
||||
* `type`
|
||||
|
||||
---
|
||||
|
||||
## 4. Edge Payload (`mindnet_edges`)
|
||||
|
||||
Gerichtete Kanten zwischen Knoten. Stark erweitert in v2.6 für Provenienz-Tracking.
|
||||
|
||||
**JSON-Schema:**
|
||||
|
||||
```json
|
||||
{
|
||||
"edge_id": "string (keyword)", // Deterministischer Hash aus (src, dst, kind)
|
||||
"source_id": "string (keyword)", // Chunk-ID (Start)
|
||||
"target_id": "string (keyword)", // Chunk-ID oder Note-Titel (bei Unresolved)
|
||||
"kind": "string (keyword)", // Beziehungsart (z.B. 'depends_on')
|
||||
"scope": "string (keyword)", // Immer 'chunk' (Legacy-Support: 'note')
|
||||
"note_id": "string (keyword)", // Owner Note ID (Ursprung der Kante)
|
||||
|
||||
// Provenance & Quality (WP03/WP15)
|
||||
"provenance": "keyword", // 'explicit', 'rule', 'smart', 'structure'
|
||||
"rule_id": "string (keyword)", // Traceability: 'inline:rel', 'explicit:wikilink', 'smart:llm'
|
||||
"confidence": "float" // Vertrauenswürdigkeit (0.0 - 1.0)
|
||||
}
|
||||
```
|
||||
|
||||
**Erforderliche Indizes:**
|
||||
Es müssen Payload-Indizes für folgende Felder existieren:
|
||||
* `source_id`
|
||||
* `target_id`
|
||||
* `kind`
|
||||
* `scope`
|
||||
* `note_id`
|
||||
@@ -0,0 +1,172 @@
|
||||
---
|
||||
doc_type: technical_reference
|
||||
audience: developer, frontend_architect
|
||||
scope: architecture, graph_viz, state_management
|
||||
status: active
|
||||
version: 2.7.0
|
||||
context: "Technische Dokumentation des modularen Streamlit-Frontends, der Graph-Engines und des Editors."
|
||||
---
|
||||
|
||||
# Technical Reference: Frontend & Visualization
|
||||
|
||||
**Kontext:** Mindnet nutzt Streamlit nicht nur als einfaches UI, sondern als komplexe Applikation mit eigenem State-Management, Routing und Persistenz.
|
||||
|
||||
---
|
||||
|
||||
## 1. Architektur & Modularisierung (WP19)
|
||||
|
||||
Seit Version 2.6 ist das Frontend (`app/frontend/`) kein Monolith mehr, sondern in funktionale Module unterteilt.
|
||||
|
||||
### 1.1 Dateistruktur & Aufgaben
|
||||
|
||||
| Modul | Funktion |
|
||||
| :--- | :--- |
|
||||
| `ui.py` | **Router.** Der Entrypoint. Initialisiert Session-State und entscheidet anhand der Sidebar-Auswahl, welche View gerendert wird. |
|
||||
| `ui_config.py` | **Konstanten.** Zentraler Ort für Farben (`GRAPH_COLORS`), API-Endpunkte und Timeouts. |
|
||||
| `ui_api.py` | **Backend-Bridge.** Kapselt alle `requests`-Aufrufe an die FastAPI. |
|
||||
| `ui_callbacks.py` | **State Transitions.** Logik für View-Wechsel (z.B. Sprung vom Graph in den Editor). |
|
||||
| `ui_utils.py` | **Helper.** Markdown-Parsing (`parse_markdown_draft`) und String-Normalisierung. |
|
||||
| `ui_graph_service.py`| **Data Logic.** Holt Daten aus Qdrant und bereitet Nodes/Edges auf (unabhängig von der Vis-Library). |
|
||||
| `ui_graph_cytoscape.py`| **View: Graph.** Implementierung mit `st-cytoscape` (COSE Layout). |
|
||||
| `ui_editor.py` | **View: Editor.** Logik für Drafts, manuelles Editieren und **Async Feedback**. |
|
||||
|
||||
### 1.2 Konfiguration (`ui_config.py`)
|
||||
|
||||
Zentrale Steuerung der visuellen Semantik.
|
||||
|
||||
# Mapping von Node-Typen zu Farben (Hex)
|
||||
GRAPH_COLORS = {
|
||||
"project": "#ff9f43", # Orange
|
||||
"decision": "#5f27cd", # Lila
|
||||
"experience": "#feca57", # Gelb (Empathie)
|
||||
"concept": "#54a0ff", # Blau
|
||||
"risk": "#ff6b6b" # Rot
|
||||
}
|
||||
|
||||
---
|
||||
|
||||
## 2. Graph Visualisierung
|
||||
|
||||
Mindnet nutzt primär **Cytoscape** für Stabilität bei großen Graphen.
|
||||
|
||||
### 2.1 Engine: Cytoscape (`st-cytoscape`)
|
||||
* **Algorithmus:** `COSE` (Compound Spring Embedder).
|
||||
* **Vorteil:** Verhindert Überlappungen aktiv (`nodeRepulsion`).
|
||||
|
||||
### 2.2 Architektur-Pattern: "Active Inspector, Passive Graph"
|
||||
Ein häufiges Problem bei Streamlit-Graphen ist das "Flackern" (Re-Render) bei Klicks. Wir lösen das durch Entkopplung:
|
||||
|
||||
1. **Stable Key:** Der React-Key der Komponente hängt *nicht* von der Selektion ab, sondern nur vom Zentrum (`center_id`) und Layout-Settings.
|
||||
2. **CSS-Selektion:** Wir nutzen **nicht** den nativen `:selected` State (buggy bei Single-Select), sondern injizieren eine CSS-Klasse `.inspected`.
|
||||
|
||||
**Stylesheet Implementierung (`ui_graph_cytoscape.py`):**
|
||||
|
||||
stylesheet = [
|
||||
{
|
||||
"selector": "node",
|
||||
"style": { "background-color": "data(bg_color)" }
|
||||
},
|
||||
# Wir steuern das Highlight manuell über eine Klasse
|
||||
{
|
||||
"selector": ".inspected",
|
||||
"style": {
|
||||
"border-width": 6,
|
||||
"border-color": "#FFC300", # Gelb/Gold
|
||||
"z-index": 999
|
||||
}
|
||||
},
|
||||
# Native Selektion wird unterdrückt/unsichtbar gemacht
|
||||
{
|
||||
"selector": "node:selected",
|
||||
"style": { "overlay-opacity": 0, "border-width": 0 }
|
||||
}
|
||||
]
|
||||
|
||||
---
|
||||
|
||||
## 3. Editor & Single Source of Truth
|
||||
|
||||
Ein kritisches Design-Pattern ist der Umgang mit Datenkonsistenz beim Editieren ("File System First").
|
||||
|
||||
### 3.1 Das Problem
|
||||
Qdrant speichert Metadaten und Chunks, aber das Feld `fulltext` im Payload kann veraltet sein oder Formatierungen verlieren.
|
||||
|
||||
### 3.2 Die Lösung (Logic Flow)
|
||||
Der `switch_to_editor_callback` in `ui_callbacks.py` implementiert folgende Kaskade:
|
||||
|
||||
def switch_to_editor_callback(note_payload):
|
||||
# 1. Pfad aus Qdrant Payload lesen
|
||||
origin_fname = note_payload.get('path')
|
||||
|
||||
content = ""
|
||||
# 2. Versuch: Hard Read von der Festplatte (Source of Truth)
|
||||
if origin_fname and os.path.exists(origin_fname):
|
||||
with open(origin_fname, "r", encoding="utf-8") as f:
|
||||
content = f.read()
|
||||
else:
|
||||
# 3. Fallback: Rekonstruktion aus der DB ("Stitching")
|
||||
# Nur Notfall, falls Docker-Volume fehlt
|
||||
content = note_payload.get('fulltext', '')
|
||||
|
||||
# State setzen (Transport via Message-Bus)
|
||||
st.session_state.messages.append({
|
||||
"role": "assistant",
|
||||
"intent": "INTERVIEW",
|
||||
"content": content,
|
||||
"origin_filename": origin_fname
|
||||
})
|
||||
st.session_state["sidebar_mode_selection"] = "📝 Manueller Editor"
|
||||
|
||||
### 3.3 Async Save Pattern (Neu in v2.7 / WP-14)
|
||||
Um Timeouts bei der Smart-Edge-Berechnung zu vermeiden, nutzt der Editor ein **"Fire & Forget"** Muster.
|
||||
|
||||
1. **Request:** UI sendet Markdown an `/ingest/save`.
|
||||
2. **Backend:**
|
||||
* Validiert Request.
|
||||
* Speichert Datei auf Disk (Persistenz garantiert).
|
||||
* Startet `BackgroundTasks` für LLM-Analyse und Embedding.
|
||||
* Returniert sofort `status: queued`.
|
||||
3. **UI Feedback:**
|
||||
* Editor zeigt "Erfolgreich eingereiht".
|
||||
* User muss nicht warten.
|
||||
* (ToDo: WebSocket Notification bei Abschluss).
|
||||
|
||||
---
|
||||
|
||||
## 4. State Management Patterns
|
||||
|
||||
### 4.1 URL Persistenz (Deep Linking)
|
||||
Layout-Einstellungen werden in der URL gespeichert, damit sie einen Page-Refresh (F5) überleben.
|
||||
|
||||
# ui_graph_cytoscape.py
|
||||
def update_url_params():
|
||||
st.query_params["depth"] = st.session_state.cy_depth
|
||||
st.query_params["rep"] = st.session_state.cy_node_repulsion
|
||||
|
||||
# Init
|
||||
if "cy_depth" not in st.session_state:
|
||||
st.session_state.cy_depth = int(st.query_params.get("depth", 2))
|
||||
|
||||
### 4.2 Resurrection Pattern
|
||||
Verhindert Datenverlust, wenn der Nutzer während des Tippens den Tab wechselt. Der Editor-Inhalt wird bei jedem Keystroke (`on_change`) in `st.session_state` gespiegelt und beim Neuladen der Komponente von dort wiederhergestellt.
|
||||
|
||||
### 4.3 Healing Parser (`ui_utils.py`)
|
||||
Das LLM liefert oft invalides YAML oder Markdown. Der Parser (`parse_markdown_draft`):
|
||||
* Repariert fehlende Frontmatter-Trenner (`---`).
|
||||
* Extrahiert JSON/YAML aus Code-Blöcken.
|
||||
* Normalisiert Tags (entfernt `#`).
|
||||
|
||||
---
|
||||
|
||||
## 5. Constraints & Security (Known Limitations)
|
||||
|
||||
### 5.1 File System Security
|
||||
Der Editor ("File System First") vertraut dem Pfad im Qdrant-Feld `path`.
|
||||
* **Risiko:** Path Traversal (z.B. `../../etc/passwd`).
|
||||
* **Mitigation:** Aktuell findet keine strikte Prüfung statt, ob der Pfad innerhalb des `./vault` Ordners liegt. Das System setzt voraus, dass die Vektor-Datenbank eine **Trusted Source** ist und nur vom internen Importer befüllt wird.
|
||||
* **ToDo:** Bei Öffnung der API für Dritte muss hier eine `Path.resolve().is_relative_to(VAULT_ROOT)` Prüfung implementiert werden.
|
||||
|
||||
### 5.2 Browser Performance
|
||||
Die Graph-Visualisierung (`st-cytoscape`) rendert Client-seitig im Browser.
|
||||
* **Limit:** Ab ca. **500 Knoten/Kanten** kann das Rendering träge werden.
|
||||
* **Design-Entscheidung:** Das UI ist auf **Ego-Graphen** (Nachbarn eines Knotens) und gefilterte Ansichten ausgelegt, nicht auf die Darstellung des gesamten Knowledge-Graphs ("Whole Brain Visualization").
|
||||
@@ -0,0 +1,154 @@
|
||||
---
|
||||
doc_type: technical_reference
|
||||
audience: developer, devops
|
||||
scope: backend, ingestion, smart_edges
|
||||
status: active
|
||||
version: 2.7.0
|
||||
context: "Detaillierte technische Beschreibung der Import-Pipeline, Chunking-Strategien und CLI-Befehle."
|
||||
---
|
||||
|
||||
# Ingestion Pipeline & Smart Processing
|
||||
|
||||
**Quellen:** `pipeline_playbook.md`, `Handbuch.md`
|
||||
|
||||
Die Ingestion transformiert Markdown in den Graphen. Entrypoint: `scripts/import_markdown.py` (CLI) oder `routers/ingest.py` (API).
|
||||
|
||||
## 1. Der Import-Prozess (14-Schritte-Workflow)
|
||||
|
||||
Der Prozess ist **asynchron** und **idempotent**.
|
||||
|
||||
1. **Trigger & Async Dispatch:**
|
||||
* **API (`/save`):** Nimmt Request entgegen, validiert und startet Background-Task ("Fire & Forget"). Antwortet sofort mit `202/Queued`.
|
||||
* **CLI:** Iteriert über Dateien und nutzt `asyncio.Semaphore` zur Drosselung.
|
||||
2. **Markdown lesen:** Rekursives Scannen des Vaults.
|
||||
3. **Frontmatter extrahieren:** Validierung von Pflichtfeldern (`id`, `type`, `title`).
|
||||
4. **Config Resolution:**
|
||||
* Bestimmung von `chunking_profile` und `retriever_weight`.
|
||||
* **Priorität:** 1. Frontmatter (Override) -> 2. `types.yaml` (Type) -> 3. Default.
|
||||
5. **Note-Payload generieren:**
|
||||
* Erstellen des JSON-Objekts für `mindnet_notes`.
|
||||
* **Multi-Hash Calculation:** Berechnet Hashtabellen für `body` (nur Text) und `full` (Text + Metadaten).
|
||||
6. **Change Detection:**
|
||||
* Vergleich des Hashes mit Qdrant.
|
||||
* Strategie wählbar via ENV `MINDNET_CHANGE_DETECTION_MODE` (`full` oder `body`).
|
||||
7. **Chunking anwenden:** Zerlegung des Textes basierend auf dem ermittelten Profil (siehe Kap. 3).
|
||||
8. **Smart Edge Allocation (WP15):**
|
||||
* Wenn `enable_smart_edge_allocation: true`: Der `SemanticAnalyzer` sendet Chunks an das LLM.
|
||||
* **Traffic Control:** Request nutzt `priority="background"`. Semaphore (Limit via `.env`) drosselt die Last.
|
||||
* **Resilienz:** Bei Timeout (Ollama) greift ein Fallback (Broadcasting an alle Chunks).
|
||||
9. **Inline-Kanten finden:** Parsing von `[[rel:...]]`.
|
||||
10. **Callout-Kanten finden:** Parsing von `> [!edge]`.
|
||||
11. **Default-Edges erzeugen:** Anwendung der `edge_defaults` aus Registry.
|
||||
12. **Strukturkanten erzeugen:** `belongs_to`, `next`, `prev`.
|
||||
13. **Embedding (Async):** Generierung via `nomic-embed-text` (768 Dim).
|
||||
14. **Diagnose:** Integritäts-Check nach dem Lauf.
|
||||
|
||||
---
|
||||
|
||||
## 2. Betrieb & CLI Befehle
|
||||
|
||||
### 2.1 Standard-Betrieb (Inkrementell)
|
||||
Für regelmäßige Updates (Cronjob). Erkennt Änderungen via Hash.
|
||||
|
||||
```bash
|
||||
export QDRANT_URL="http://localhost:6333"
|
||||
export COLLECTION_PREFIX="mindnet"
|
||||
# Steuert, wann eine Datei als "geändert" gilt
|
||||
export MINDNET_CHANGE_DETECTION_MODE="full"
|
||||
|
||||
# Nutzt das Venv der Produktionsumgebung
|
||||
/home/llmadmin/mindnet/.venv/bin/python3 -m scripts.import_markdown \
|
||||
--vault ./vault \
|
||||
--prefix "$COLLECTION_PREFIX" \
|
||||
--apply \
|
||||
--purge-before-upsert \
|
||||
--sync-deletes
|
||||
```
|
||||
|
||||
> **[!WARNING] Purge-Before-Upsert**
|
||||
> Das Flag `--purge-before-upsert` ist kritisch. Es löscht vor dem Schreiben einer Note ihre alten Chunks/Edges. Ohne dieses Flag entstehen **"Geister-Chunks"** (alte Textabschnitte, die im Markdown gelöscht wurden, aber im Index verbleiben).
|
||||
|
||||
### 2.2 Full Rebuild (Clean Slate)
|
||||
Notwendig bei Änderungen an `types.yaml` (z.B. neue Chunking-Profile) oder Modell-Wechsel.
|
||||
|
||||
```bash
|
||||
# 0. Modell sicherstellen
|
||||
ollama pull nomic-embed-text
|
||||
|
||||
# 1. Qdrant Collections löschen (Wipe)
|
||||
python3 -m scripts.reset_qdrant --mode wipe --prefix "mindnet" --yes
|
||||
|
||||
# 2. Vollständiger Import (Force)
|
||||
# --force ignoriert alle Hashes und schreibt alles neu
|
||||
python3 -m scripts.import_markdown --vault ./vault --prefix "mindnet" --apply --force
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 3. Chunking & Payload
|
||||
|
||||
Das Chunking ist profilbasiert und in `types.yaml` konfiguriert.
|
||||
|
||||
### 3.1 Profile und Strategien
|
||||
|
||||
| Profil | Strategie | Parameter | Einsatzgebiet |
|
||||
| :--- | :--- | :--- | :--- |
|
||||
| `sliding_short` | `sliding_window` | Max: 350, Target: 200 | Kurze Logs, Chats, Risiken. |
|
||||
| `sliding_standard` | `sliding_window` | Max: 650, Target: 450 | Massendaten (Journal, Quellen). |
|
||||
| `sliding_smart_edges`| `sliding_window` | Max: 600, Target: 400 | Fließtexte mit hohem Wert (Projekte, Erfahrungen). |
|
||||
| `structured_smart_edges` | `by_heading` | `strict: false` (Soft) | Strukturierte Texte, wo kleine Abschnitte gemergt werden dürfen. |
|
||||
| `structured_smart_edges_strict` | `by_heading` | `strict: true` (Hard) | **Atomare Einheiten**: Entscheidungen, Werte, Profile. |
|
||||
| `structured_smart_edges_strict_L3`| `by_heading` | `strict: true`, `level: 3` | Tief geschachtelte Prinzipien (Tier 2/MP1 Logik). |
|
||||
|
||||
### 3.2 Die `by_heading` Logik (v2.9 Hybrid)
|
||||
|
||||
Die Strategie `by_heading` zerlegt Texte anhand ihrer Struktur (Überschriften). Sie unterstützt seit v2.9 ein "Safety Net" gegen zu große Chunks.
|
||||
|
||||
* **Split Level:** Definiert die Tiefe (z.B. `2` = H1 & H2 triggern Split).
|
||||
* **Modus "Strict" (`strict_heading_split: true`):**
|
||||
* Jede Überschrift (`<= split_level`) erzwingt einen neuen Chunk.
|
||||
* *Merge-Check:* Wenn der vorherige Chunk leer war (nur Überschriften), wird gemergt (verhindert verwaiste Überschriften).
|
||||
* *Safety Net:* Wird ein Abschnitt zu lang (> `max` Token), wird auch ohne Überschrift getrennt.
|
||||
* **Modus "Soft" (`strict_heading_split: false`):**
|
||||
* **Hierarchie-Check:** Überschriften *oberhalb* des Split-Levels (z.B. H1 bei Level 2) erzwingen **immer** einen Split.
|
||||
* **Füll-Logik:** Überschriften *auf* dem Split-Level (z.B. H2) lösen nur dann einen neuen Chunk aus, wenn der aktuelle Chunk die `target`-Größe erreicht hat.
|
||||
* *Safety Net:* Auch hier greift das `max` Token Limit.
|
||||
|
||||
### 3.3 Payload-Felder (Qdrant)
|
||||
|
||||
* `text`: Der reine Inhalt (Anzeige im UI). Überschriften bleiben erhalten.
|
||||
* `window`: Inhalt plus Overlap (für Embedding). Bei `by_heading` wird der Kontext (Eltern-Überschrift) oft vorangestellt.
|
||||
* `chunk_profile`: Das effektiv genutzte Profil (zur Nachverfolgung).
|
||||
|
||||
---
|
||||
|
||||
## 4. Edge-Erzeugung & Prioritäten
|
||||
|
||||
Kanten werden nach Vertrauenswürdigkeit (`provenance`) priorisiert. Die höhere Prio gewinnt.
|
||||
|
||||
| Prio | Quelle | Rule ID | Confidence |
|
||||
| :--- | :--- | :--- | :--- |
|
||||
| **1** | Inline | `inline:rel` | 0.95 |
|
||||
| **2** | Callout | `callout:edge` | 0.90 |
|
||||
| **3** | Wikilink | `explicit:wikilink` | 1.00 |
|
||||
| **4** | Smart Edge | `smart:llm_filter` | 0.90 |
|
||||
| **5** | Type Default | `edge_defaults` | 0.70 |
|
||||
| **6** | Struktur | `structure` | 1.00 |
|
||||
|
||||
---
|
||||
|
||||
## 5. Quality Gates & Tests
|
||||
|
||||
Diese Tests garantieren die Stabilität der Pipeline.
|
||||
|
||||
**1. Payload Dryrun (Schema-Check):**
|
||||
Simuliert Import, prüft JSON-Schema Konformität.
|
||||
```bash
|
||||
python3 -m scripts.payload_dryrun --vault ./test_vault
|
||||
```
|
||||
|
||||
**2. Full Edge Check (Graph-Integrität):**
|
||||
Prüft Invarianten (z.B. `next` muss reziprok zu `prev` sein).
|
||||
```bash
|
||||
python3 -m scripts.edges_full_check
|
||||
```
|
||||
@@ -0,0 +1,113 @@
|
||||
---
|
||||
doc_type: technical_reference
|
||||
audience: developer, data_scientist
|
||||
scope: backend, retrieval, scoring
|
||||
status: active
|
||||
version: 2.6
|
||||
context: "Formeln und Algorithmen des Hybrid Retrievers und Explanation Layer."
|
||||
---
|
||||
|
||||
# Retrieval & Scoring Algorithmen
|
||||
|
||||
Der Retriever (`app/core/retriever.py`) unterstützt **Semantic Search** und **Hybrid Search**. Seit v2.4 (WP04a) nutzt Mindnet ein gewichtetes Scoring-Modell, das Semantik, Graphentheorie und Metadaten kombiniert.
|
||||
|
||||
## 1. Scoring Formel (WP04a)
|
||||
|
||||
Der Gesamtscore eines Treffers berechnet sich als gewichtete Summe. Alle Gewichte ($W$) sind in `retriever.yaml` konfigurierbar.
|
||||
|
||||
$$
|
||||
TotalScore = (W_{sem} \cdot S_{sem} \cdot \max(W_{type}, 0)) + (W_{edge} \cdot B_{edge}) + (W_{cent} \cdot B_{cent})
|
||||
$$
|
||||
|
||||
### Die Komponenten
|
||||
|
||||
**1. Semantic Score ($S_{sem}$):**
|
||||
* **Basis:** Cosine Similarity des Vektors.
|
||||
* **Modell:** `nomic-embed-text` (768d).
|
||||
* **Wertebereich:** 0.0 bis 1.0.
|
||||
|
||||
**2. Type Weight ($W_{type}$):**
|
||||
* **Herkunft:** Feld `retriever_weight` aus der Note/Chunk Payload.
|
||||
* **Zweck:** Priorisierung bestimmter Dokumententypen unabhängig vom Inhalt.
|
||||
* **Beispiel:** Eine `decision` (Gewicht 1.0) schlägt ein `concept` (Gewicht 0.6) bei gleicher textueller Ähnlichkeit.
|
||||
|
||||
**3. Edge Bonus ($B_{edge}$):**
|
||||
* **Kontext:** Berechnet im lokalen Subgraphen (Expansion Tiefe 1).
|
||||
* **Logik:** Summe der `confidence` aller eingehenden Kanten, die von Knoten stammen, die *ebenfalls* im aktuellen Result-Set (oder dem übergebenen Kontext) enthalten sind.
|
||||
* **Zweck:** Belohnt Chunks, die "im Thema" vernetzt sind.
|
||||
|
||||
**4. Centrality Bonus ($B_{cent}$):**
|
||||
* **Kontext:** Berechnet im lokalen Subgraphen.
|
||||
* **Logik:** Eine vereinfachte PageRank-Metrik (Degree Centrality) im temporären Graphen.
|
||||
* **Zweck:** Belohnt "Hubs", die viele Verbindungen zu anderen Treffern haben.
|
||||
|
||||
---
|
||||
|
||||
## 2. Hybrid Retrieval Flow
|
||||
|
||||
Der Hybrid-Modus ist der Standard für den Chat (`/chat`). Er läuft in drei Phasen ab:
|
||||
|
||||
**Phase 1: Vector Search (Seed Generation)**
|
||||
* Suche die Top-K (z.B. 20) Kandidaten via Embeddings in Qdrant.
|
||||
* Dies sind die "Seeds" für den Graphen.
|
||||
|
||||
**Phase 2: Graph Expansion**
|
||||
* Nutze `graph_adapter.expand(seeds, depth=1)`.
|
||||
* Lade alle direkten Nachbarn (Incoming & Outgoing) der Seeds aus der `_edges` Collection.
|
||||
* Konstruiere einen temporären `NetworkX`-Graphen im Speicher (`Subgraph`).
|
||||
|
||||
**Phase 3: Re-Ranking**
|
||||
* Berechne für jeden Knoten im Subgraphen die Boni ($B_{edge}$, $B_{cent}$).
|
||||
* Wende die Scoring-Formel an.
|
||||
* Sortiere die Liste neu absteigend nach `TotalScore`.
|
||||
* Schneide die Liste beim finalen Limit (z.B. 5) ab.
|
||||
|
||||
---
|
||||
|
||||
## 3. Explanation Layer (WP04b)
|
||||
|
||||
Wenn der Parameter `explain=True` an die API übergeben wird, generiert der Retriever ein `Explanation` Objekt für jeden Treffer.
|
||||
|
||||
**JSON-Struktur der Erklärung:**
|
||||
|
||||
```json
|
||||
{
|
||||
"score_breakdown": {
|
||||
"semantic": 0.85,
|
||||
"type_boost": 1.0,
|
||||
"edge_bonus": 0.4,
|
||||
"centrality": 0.1
|
||||
},
|
||||
"reasons": [
|
||||
"Hohe textuelle Übereinstimmung (>0.85).",
|
||||
"Bevorzugt, da Typ 'decision' (Gewicht 1.0).",
|
||||
"Wird referenziert von 'Projekt Alpha' via 'depends_on'."
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
**Logik der Text-Generierung:**
|
||||
* **Semantik:** Wenn $S_{sem} > 0.8$: "Hohe Übereinstimmung".
|
||||
* **Typ:** Wenn $W_{type} > 0.8$: "Bevorzugt, da Typ X".
|
||||
* **Graph:** Listet bis zu 3 eingehende Kanten mit hoher Konfidenz auf ("Wird referenziert von...").
|
||||
|
||||
---
|
||||
|
||||
## 4. Konfiguration (`retriever.yaml`)
|
||||
|
||||
Diese Datei steuert die Balance der Formel.
|
||||
|
||||
```yaml
|
||||
scoring:
|
||||
semantic_weight: 1.0 # Basis-Relevanz (sollte immer ca. 1.0 sein)
|
||||
edge_weight: 0.7 # Einfluss des Graphen (0.5 - 1.0 empfohlen)
|
||||
centrality_weight: 0.5 # Einfluss der Zentralität (Hub-Bonus)
|
||||
|
||||
# Kanten-spezifische Gewichtung für den Edge-Bonus
|
||||
edge_weights:
|
||||
depends_on: 1.5 # Harte Abhängigkeiten sehr stark gewichten
|
||||
blocks: 1.5 # Risiken/Blocker stark gewichten
|
||||
caused_by: 1.2 # Kausalitäten moderat stärken
|
||||
related_to: 0.5 # Weiche Themen schwächer gewichten
|
||||
references: 0.8 # Standard-Referenzen
|
||||
```
|
||||
@@ -0,0 +1,156 @@
|
||||
---
|
||||
doc_type: operations_manual
|
||||
audience: admin, devops
|
||||
scope: deployment, maintenance, backup
|
||||
status: active
|
||||
version: 2.6
|
||||
context: "Installationsanleitung, Systemd-Units und Wartungsprozesse."
|
||||
---
|
||||
|
||||
# Admin Operations Guide
|
||||
|
||||
## 1. Installation & Setup
|
||||
|
||||
### 1.1 Voraussetzungen
|
||||
* **OS:** Ubuntu 22.04+ (empfohlen).
|
||||
* **Tools:** Python 3.10+, Docker, Ollama.
|
||||
* **Hardware:** Min. 8GB RAM, 4 CPU Cores (für Async Import).
|
||||
|
||||
### 1.2 Qdrant (Docker)
|
||||
Startet die Vektor-DB mit persistentem Storage auf Port 6333.
|
||||
|
||||
```bash
|
||||
docker run -d \
|
||||
--name mindnet_qdrant \
|
||||
--restart always \
|
||||
-p 6333:6333 \
|
||||
-v $(pwd)/qdrant_storage:/qdrant/storage \
|
||||
qdrant/qdrant
|
||||
```
|
||||
|
||||
### 1.3 Ollama (Modelle)
|
||||
**Wichtig:** Seit v2.4 ist `nomic-embed-text` Pflicht für Embeddings.
|
||||
|
||||
```bash
|
||||
# Modelle laden
|
||||
ollama pull phi3:mini
|
||||
ollama pull nomic-embed-text
|
||||
|
||||
# Testen
|
||||
curl http://localhost:11434/api/generate -d '{"model": "phi3:mini", "prompt":"Hi"}'
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 2. Deployment (Systemd Services)
|
||||
|
||||
Wir unterscheiden strikt zwischen **Prod** (Port 8001/8501) und **Dev** (Port 8002/8502).
|
||||
|
||||
### 2.1 Backend Service (`/etc/systemd/system/mindnet-prod.service`)
|
||||
|
||||
```ini
|
||||
[Unit]
|
||||
Description=Mindnet API Prod (8001)
|
||||
After=network.target
|
||||
|
||||
[Service]
|
||||
User=llmadmin
|
||||
Group=llmadmin
|
||||
WorkingDirectory=/home/llmadmin/mindnet
|
||||
# Startet Uvicorn (Async Server)
|
||||
ExecStart=/home/llmadmin/mindnet/.venv/bin/uvicorn app.main:app --host 0.0.0.0 --port 8001 --env-file .env
|
||||
Restart=always
|
||||
RestartSec=5
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
```
|
||||
|
||||
### 2.2 UI Service (`/etc/systemd/system/mindnet-ui-prod.service`)
|
||||
|
||||
```ini
|
||||
[Unit]
|
||||
Description=Mindnet UI Prod (8501)
|
||||
After=mindnet-prod.service
|
||||
|
||||
[Service]
|
||||
User=llmadmin
|
||||
Group=llmadmin
|
||||
WorkingDirectory=/home/llmadmin/mindnet
|
||||
|
||||
# Environment für Streamlit Port & API-Ziel
|
||||
Environment="MINDNET_API_URL=http://localhost:8001"
|
||||
Environment="MINDNET_API_TIMEOUT=300"
|
||||
Environment="STREAMLIT_SERVER_PORT=8501"
|
||||
Environment="STREAMLIT_SERVER_ADDRESS=0.0.0.0"
|
||||
Environment="STREAMLIT_SERVER_HEADLESS=true"
|
||||
|
||||
# WICHTIG: Pfad zur neuen Router-Datei (ui.py)
|
||||
ExecStart=/home/llmadmin/mindnet/.venv/bin/streamlit run app/frontend/ui.py
|
||||
Restart=always
|
||||
RestartSec=5
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 3. Wartung & Cronjobs
|
||||
|
||||
### 3.1 Regelmäßiger Import (Cron)
|
||||
Führt den Sync stündlich durch. Nutzt `--purge-before-upsert` für Sauberkeit.
|
||||
|
||||
```bash
|
||||
# Crontab Eintrag (user: llmadmin)
|
||||
0 * * * * cd /home/llmadmin/mindnet && .venv/bin/python3 -m scripts.import_markdown --vault ./vault --prefix "mindnet" --apply --purge-before-upsert --sync-deletes >> ./logs/import.log 2>&1
|
||||
```
|
||||
|
||||
### 3.2 Troubleshooting Guide
|
||||
|
||||
**Fehler: "ModuleNotFoundError: No module named 'st_cytoscape'"**
|
||||
* Ursache: Alte Dependencies oder falsches Paket installiert.
|
||||
* Lösung: Environment aktualisieren.
|
||||
```bash
|
||||
source .venv/bin/activate
|
||||
pip uninstall streamlit-cytoscapejs
|
||||
pip install st-cytoscape
|
||||
# Oder sicherheitshalber:
|
||||
pip install -r requirements.txt
|
||||
```
|
||||
|
||||
**Fehler: "Vector dimension error: expected 768, got 384"**
|
||||
* Ursache: Alte DB (v2.2), neues Modell (v2.4).
|
||||
* Lösung: **Full Reset** (siehe Kap. 4.2).
|
||||
|
||||
**Fehler: Import sehr langsam**
|
||||
* Ursache: Smart Edges sind aktiv und analysieren jeden Chunk.
|
||||
* Lösung: `MINDNET_LLM_BACKGROUND_LIMIT` prüfen oder Feature in `types.yaml` deaktivieren.
|
||||
|
||||
**Fehler: UI "Read timed out"**
|
||||
* Ursache: Backend braucht für Smart Edges länger als 60s.
|
||||
* Lösung: `MINDNET_API_TIMEOUT=300.0` in `.env` setzen (oder im Systemd Service).
|
||||
|
||||
---
|
||||
|
||||
## 4. Backup & Restore
|
||||
|
||||
### 4.1 Qdrant Snapshot
|
||||
Sichert den Vektor-Index.
|
||||
|
||||
```bash
|
||||
docker stop mindnet_qdrant
|
||||
tar -czf qdrant_backup_$(date +%F).tar.gz ./qdrant_storage
|
||||
docker start mindnet_qdrant
|
||||
```
|
||||
|
||||
### 4.2 Notfall-Rebuild (Clean Slate)
|
||||
Wenn alles inkonsistent ist oder Dimensionen sich ändern:
|
||||
|
||||
```bash
|
||||
# 1. DB löschen
|
||||
python3 -m scripts.reset_qdrant --mode wipe --prefix "mindnet" --yes
|
||||
|
||||
# 2. Neu importieren (Force Hash recalculation)
|
||||
python3 -m scripts.import_markdown --vault ./vault --prefix "mindnet" --apply --force
|
||||
```
|
||||
@@ -0,0 +1,281 @@
|
||||
---
|
||||
doc_type: operations_manual
|
||||
audience: system_admin, devops
|
||||
scope: server_lifecycle, disaster_recovery, maintenance, backup, monitoring
|
||||
status: active
|
||||
version: 1.9
|
||||
hostname: llm-node
|
||||
ip_address: 192.168.2.144
|
||||
context: "Zentrale Dokumentation für Host-Konfiguration, Mindnet-Applikation, Gitea und Backup-Strategie. Aktualisiert um die Two-Stage Disaster Recovery und Backup-Monitoring."
|
||||
created_date: 2025-12-14
|
||||
last_updated: 2025-12-15
|
||||
---
|
||||
|
||||
# Server Operations Manual: llm-node (192.168.2.144)
|
||||
|
||||
Dieses Dokument beschreibt den Betrieb, die Wartung und die Wiederherstellung (Disaster Recovery) des Servers "llm-node".
|
||||
|
||||
## 1. Systemübersicht & Netzwerk
|
||||
|
||||
### 1.1 Host Details
|
||||
* **Hostname:** `llm-node`
|
||||
* **IP-Adresse:** `192.168.2.144`
|
||||
* **OS:** Ubuntu Server
|
||||
* **Qdrant Host-Volume Pfad:** `/home/llmadmin/docker/qdrant/qdrant_data` (Bind-Mount)
|
||||
|
||||
### 1.2 Storage & NAS Mount
|
||||
Das System sichert auf ein Synology NAS via NFSv3.
|
||||
|
||||
* **Mount Point:** `/mnt/nas_backup`
|
||||
* **Quelle:** `192.168.2.63:/volume1/Backup_LLM`
|
||||
* **Fstab-Eintrag (Referenz für Restore):**
|
||||
```text
|
||||
192.168.2.63:/volume1/Backup_LLM /mnt/nas_backup nfs vers=3,_netdev,x-systemd.automount,nofail 0 0
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 2. Dienste & Port-Matrix
|
||||
|
||||
### 2.1 Native Dienste (Systemd)
|
||||
|
||||
| Service | Port | User | Beschreibung |
|
||||
| :--- | :--- | :--- | :--- |
|
||||
| **SSH** | 22 | root | Remote Zugriff |
|
||||
| **Gitea** | 3000 | `git` | Git Version Control (User: git) |
|
||||
| **Ollama** | 11434 | `ollama` | AI Model Server |
|
||||
| **Mindnet Prod API** | 8001 | `llmadmin` | Backend Applikation |
|
||||
| **Mindnet Dev API** | 8002 | `llmadmin` | Backend Applikation (Entwicklung) |
|
||||
| **Mindnet Prod UI** | 8501 | `llmadmin` | Frontend Applikation |
|
||||
| **Mindnet Dev UI** | 8502 | `llmadmin` | Frontend Applikation (Entwicklung) |
|
||||
| **Act Runner** | 38703 | `root` | Gitea CI/CD Runner |
|
||||
|
||||
### 2.2 Docker Container
|
||||
Übersicht der Container (`docker ps`).
|
||||
|
||||
| Container Name | Port | Beschreibung | Backup Strategie |
|
||||
| :--- | :--- | :--- | :--- |
|
||||
| **qdrant** | 6333 | Vektor Datenbank (Container Name: `qdrant`) | **Stop -> Tar -> Start** (Konsistenter Snapshot) |
|
||||
| **mindnet-embed** | 8990 | Embeddings Service | Volume Backup |
|
||||
| **code-server** | 8443 | VS Code (Web) | Volume Backup |
|
||||
| **silverbullet** | 13000 | Knowledge Base | Volume Backup |
|
||||
|
||||
---
|
||||
|
||||
## 3. Applikations-Management
|
||||
|
||||
### 3.1 Gitea (Git Server)
|
||||
* **User:** `git`
|
||||
* **Datenpfad:** `/var/lib/gitea`
|
||||
* **Backup:** Konsistenter Dump (`gitea-dump.zip`) im `before_backup` Hook integriert.
|
||||
|
||||
### 3.2 Ollama (AI Models)
|
||||
* **User:** `ollama`
|
||||
* **Modell-Speicher:** `/usr/share/ollama/.ollama/models`
|
||||
* **Backup:** Nur Metadaten. Blobs werden exkludiert.
|
||||
|
||||
### 3.3 Mindnet (AI App)
|
||||
* **User:** `llmadmin`
|
||||
* **Qdrant Storage:** `/home/llmadmin/docker/qdrant/qdrant_data`
|
||||
* **Cronjob:** Regelmäßiger Import (stündlich) unter User `llmadmin`.
|
||||
|
||||
---
|
||||
|
||||
## 4. Backup Strategie (Borgmatic)
|
||||
|
||||
**Status:** Automatisiert via `systemctl start borgmatic.timer`.
|
||||
**Ziel:** `/mnt/nas_backup/borg_repo`
|
||||
|
||||
### 4.1 Konsistenz-Strategie
|
||||
Alle schreibenden Dienste werden durch Hooks für das Backup vorbereitet:
|
||||
|
||||
### 4.2 Konfiguration (`/etc/borgmatic/config.yaml`)
|
||||
|
||||
```yaml
|
||||
source_directories:
|
||||
- /etc
|
||||
- /home
|
||||
- /var
|
||||
- /opt
|
||||
- /root
|
||||
|
||||
repositories:
|
||||
- path: /mnt/nas_backup/borg_repo
|
||||
label: nas
|
||||
|
||||
exclude_patterns:
|
||||
- /mnt/*
|
||||
- /var/lib/gitea/data/tmp/*
|
||||
# Ollama Blobs (Speicher sparen)
|
||||
- /usr/share/ollama/.ollama/models/blobs/*
|
||||
- /home/*/.ollama/models/blobs/*
|
||||
# Qdrant Live-Daten exkludieren
|
||||
- /home/llmadmin/docker/qdrant/qdrant_data/*
|
||||
|
||||
keep_daily: 7
|
||||
keep_weekly: 4
|
||||
keep_monthly: 6
|
||||
|
||||
before_backup:
|
||||
- echo "--- Start Pre-Backup Hooks ---"
|
||||
|
||||
# 1. Ollama Liste sichern
|
||||
- ollama list > /root/ollama_models_backup.txt
|
||||
|
||||
# 2. Gitea Dump
|
||||
- echo "Erstelle Gitea Dump..."
|
||||
- rm -f /var/lib/gitea/gitea-dump.zip
|
||||
- runuser -u git -- gitea dump -c /etc/gitea/app.ini -f /var/lib/gitea/gitea-dump.zip
|
||||
|
||||
# 3. Qdrant Snapshot
|
||||
- echo "Erstelle Qdrant Snapshot..."
|
||||
- docker stop qdrant
|
||||
- rm -f /home/llmadmin/qdrant_backup_latest.tar.gz
|
||||
# Tar Archiv im Home-Verzeichnis erstellen (wird von Borg gesichert)
|
||||
- tar -czf /home/llmadmin/qdrant_backup_latest.tar.gz -C /home/llmadmin/docker/qdrant qdrant_data
|
||||
- docker start qdrant
|
||||
|
||||
after_backup:
|
||||
- echo "Backup erfolgreich beendet."
|
||||
# Nach erfolgreichem Backup wird das temporäre Tar-Archiv gelöscht
|
||||
- rm -f /home/llmadmin/qdrant_backup_latest.tar.gz
|
||||
|
||||
on_error:
|
||||
- echo "FEHLER aufgetreten! Versuche Container zu retten..."
|
||||
- docker start qdrant
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 5. Disaster Recovery (Wiederherstellung) - Two-Stage DR
|
||||
|
||||
Das Wiederherstellungsverfahren basiert auf einer **"Two-Stage DR"**-Strategie, die die Geschwindigkeit eines Basis-Images mit der Datenkonsistenz des Borgmatic-Archives kombiniert.
|
||||
|
||||
### 5.0 Vorbereitung: Erstellung des Basis-Images (Monatlich/Quartalsweise)
|
||||
|
||||
Dieses Image sichert das bootfähige System (OS, Pakete, Konfiguration) und dient als schneller Startpunkt bei einem Festplattenausfall.
|
||||
|
||||
1. **System Bereinigen:** Führen Sie eine Systembereinigung durch, um die Image-Größe zu minimieren.
|
||||
```bash
|
||||
sudo apt clean
|
||||
sudo journalctl --vacuum-time=7d
|
||||
```
|
||||
2. **Booten vom Live-Medium:** Starten Sie den Server von einem **Ubuntu Live USB-Stick** (Größe min. 8 GB).
|
||||
3. **Mount NAS:** Stellen Sie die Verbindung zum NAS her, um das Image direkt dorthin zu schreiben.
|
||||
```bash
|
||||
sudo mkdir /mnt/nas_backup
|
||||
sudo mount -t nfs 192.168.2.63:/volume1/Backup_LLM /mnt/nas_backup
|
||||
```
|
||||
4. **Image erstellen und streamen:** Ermitteln Sie die Root-Partition des Servers (z.B. `/dev/sda1`) und erstellen Sie das komprimierte Image direkt auf dem NAS.
|
||||
```bash
|
||||
# Das Image wird direkt zum NAS gestreamt (USB-Stick benötigt nur 8GB für Live OS)
|
||||
sudo dd if=/dev/sda1 bs=1M status=progress | gzip > /mnt/nas_backup/base_image_$(date +%Y%m%d).img.gz
|
||||
```
|
||||
|
||||
### 5.1 Stage 1: Basis-Image Restore (Bare Metal Recovery)
|
||||
|
||||
Dieses Verfahren setzt das System auf den Stand des letzten Basis-Images zurück.
|
||||
|
||||
**Prozedur (Von Live-Medium booten):**
|
||||
|
||||
1. **Voraussetzungen:** Booten Sie den neuen/reparierten PC von einem **Live-Medium** (z.B. Ubuntu Live USB).
|
||||
2. **Mount NAS (auf Live-System):** Stellen Sie die Verbindung zum Backup-Speicher her, um auf das Image zuzugreifen.
|
||||
```bash
|
||||
sudo mkdir /mnt/nas_backup
|
||||
sudo mount -t nfs 192.168.2.63:/volume1/Backup_LLM /mnt/nas_backup
|
||||
```
|
||||
3. **Zielpartition identifizieren:** Ermitteln Sie den Gerätenamen der Root-Partition der **neuen** Festplatte (z.B. `/dev/sda1`). **ACHTUNG: Falsches Gerät löscht alle Daten!**
|
||||
```bash
|
||||
sudo fdisk -l
|
||||
```
|
||||
4. **Image Restore:** Schreiben Sie das komprimierte Basis-Image auf die neue Partition zurück. Ersetzen Sie `YYYYMMDD` durch das tatsächliche Datum und `/dev/sda1` durch Ihre Zielpartition.
|
||||
```bash
|
||||
sudo gunzip -c /mnt/nas_backup/base_image_YYYYMMDD.img.gz | sudo dd of=/dev/sda1 status=progress bs=1M
|
||||
```
|
||||
5. **Neustart:** Entfernen Sie den Live-USB und starten Sie das System neu. Es sollte nun in das wiederhergestellte Basis-OS booten.
|
||||
|
||||
### 5.2 Stage 2: Daten-Update (Borgmatic)
|
||||
|
||||
Nach dem Booten des Basis-Systems (Stage 1) werden die aktuellen Daten und die kritischen Applikations-Snapshots wiederhergestellt.
|
||||
|
||||
#### Schritt 1: Aktueller Daten Restore (Borg)
|
||||
Das Borg-Repository ist dank des Basis-Images bereits in `/etc/borgmatic/config.yaml` und `/etc/fstab` bekannt.
|
||||
|
||||
```bash
|
||||
# Alle Daten aus dem letzten Archiv (latest) auf das laufende System wiederherstellen
|
||||
sudo borgmatic extract --archive latest --path / --destination /
|
||||
```
|
||||
|
||||
#### Schritt 2: Dienste spezifisch wiederherstellen (Gitea/Qdrant/Ollama)
|
||||
|
||||
**A. Gitea (Aus Dump):**
|
||||
1. Dump entpacken: `unzip /var/lib/gitea/gitea-dump.zip -d /tmp/gitea_restore`
|
||||
2. Service starten: `systemctl enable --now gitea`
|
||||
|
||||
**B. Qdrant (Aus Snapshot):**
|
||||
Das Tar-Archiv liegt im Home-Verzeichnis (`/home/llmadmin/`) und muss in das Volume-Verzeichnis entpackt werden.
|
||||
|
||||
1. Wechsle in das Host-Verzeichnis des Volumes:
|
||||
```bash
|
||||
cd /home/llmadmin/docker/qdrant
|
||||
```
|
||||
2. Entpacke das gesicherte Tar (stellt den Ordner `qdrant_data` wieder her):
|
||||
```bash
|
||||
sudo tar -xzf /home/llmadmin/qdrant_backup_latest.tar.gz
|
||||
```
|
||||
3. Container starten (Volume-Mount ist korrekt):
|
||||
```bash
|
||||
docker start qdrant
|
||||
```
|
||||
|
||||
**C. Ollama (Smart Restore):**
|
||||
1. Ollama installieren (falls im Basis-Image nicht enthalten).
|
||||
2. Modelle mit dem Script aus `/root/ollama_models_backup.txt` neu ziehen:
|
||||
```bash
|
||||
sudo tail -n +2 /root/ollama_models_backup.txt | awk '{print $1}' | while read model; do ollama pull "$model"; done
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 6. Log- und Fehleranalyse & Wartung
|
||||
|
||||
### 6.1 Backup-Überwachung (Monitoring)
|
||||
|
||||
Die Überprüfung der Backup-Korrektheit erfolgt über das Systemd Journal und die Borgmatic-Befehle.
|
||||
|
||||
| Aktion | Befehl | Zweck |
|
||||
| :--- | :--- | :--- |
|
||||
| **Prüfung letzter Lauf** | `sudo journalctl -u borgmatic --since "yesterday"` | Zeigt das Journal der letzten 24 Stunden, inklusive der Hooks und Fehler. |
|
||||
| **Liste Archive** | `sudo borgmatic list` | Zeigt alle existierenden Archive, sortiert nach Datum/Uhrzeit. Dient zur Bestätigung, dass das Backup erstellt wurde. |
|
||||
| **Repo-Integrität** | `sudo borgmatic check` | Führt eine Konsistenzprüfung des gesamten Repositorys durch (kann lange dauern). |
|
||||
|
||||
### 6.2 Granulare Wiederherstellung (Einzelne Dateien)
|
||||
|
||||
Um auf einzelne Dateien oder Verzeichnisse in einem Archiv zuzugreifen, wird das Archiv als virtuelles Dateisystem gemountet.
|
||||
|
||||
1. **Mount-Punkt erstellen:**
|
||||
```bash
|
||||
mkdir /tmp/borg_mount
|
||||
```
|
||||
2. **Archiv einhängen:** Hängen Sie das gewünschte Archiv (hier: `latest`) in den Mount-Punkt ein. Geben Sie bei Bedarf den vollständigen ARCHIVNAMEN an.
|
||||
```bash
|
||||
sudo borgmatic mount --destination /tmp/borg_mount --archive latest
|
||||
```
|
||||
3. **Dateizugriff:** Das gesamte Backup-Dateisystem ist nun unter `/tmp/borg_mount` verfügbar. Dateien können mit `cp` kopiert werden.
|
||||
```bash
|
||||
# Beispiel: Eine Datei aus dem Home-Verzeichnis wiederherstellen
|
||||
sudo cp /tmp/borg_mount/home/llmadmin/wichtige_datei.txt /home/llmadmin/
|
||||
```
|
||||
4. **Archiv aushängen:** Nach dem Kopieren muss das virtuelle Dateisystem immer ausgehängt werden.
|
||||
```bash
|
||||
sudo umount /tmp/borg_mount
|
||||
# Oder:
|
||||
# sudo borgmatic umount /tmp/borg_mount
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 7. Anhang
|
||||
|
||||
* **Qdrant Container Logs:** `docker logs qdrant`
|
||||
* **Applikations-Logs:** `journalctl -u mindnet-prod`
|
||||
@@ -0,0 +1,457 @@
|
||||
---
|
||||
doc_type: developer_guide
|
||||
audience: developer
|
||||
scope: workflow, testing, architecture, modules
|
||||
status: active
|
||||
version: 2.6.1
|
||||
context: "Umfassender Guide für Entwickler: Architektur, Modul-Interna (Deep Dive), Setup, Git-Workflow und Erweiterungs-Anleitungen."
|
||||
---
|
||||
|
||||
# Mindnet Developer Guide & Workflow
|
||||
|
||||
**Quellen:** `developer_guide.md`, `dev_workflow.md`, `Architecture_Audit_v2.6`
|
||||
|
||||
Dieser Guide ist die zentrale technische Referenz für Mindnet v2.6. Er vereint das technische Verständnis der Module mit dem operativen Workflow zwischen Windows (Dev) und Linux (Runtime).
|
||||
|
||||
---
|
||||
|
||||
# Inhaltsverzeichnis
|
||||
- [Mindnet Developer Guide \& Workflow](#mindnet-developer-guide--workflow)
|
||||
- [Inhaltsverzeichnis](#inhaltsverzeichnis)
|
||||
- [1. Einführung \& Systemüberblick](#1-einführung--systemüberblick)
|
||||
- [Was ist Mindnet?](#was-ist-mindnet)
|
||||
- [Kern-Philosophie](#kern-philosophie)
|
||||
- [2. Architektur](#2-architektur)
|
||||
- [2.1 High-Level Übersicht](#21-high-level-übersicht)
|
||||
- [2.2 Datenfluss-Muster](#22-datenfluss-muster)
|
||||
- [A. Ingestion (Write)](#a-ingestion-write)
|
||||
- [B. Retrieval (Read)](#b-retrieval-read)
|
||||
- [C. Visualisierung (Graph)](#c-visualisierung-graph)
|
||||
- [3. Physische Architektur](#3-physische-architektur)
|
||||
- [4. Projektstruktur \& Modul-Referenz (Deep Dive)](#4-projektstruktur--modul-referenz-deep-dive)
|
||||
- [4.1 Verzeichnisbaum](#41-verzeichnisbaum)
|
||||
- [4.2 Frontend Architecture (`app/frontend/`)](#42-frontend-architecture-appfrontend)
|
||||
- [Frontend Design Patterns (Wichtig!)](#frontend-design-patterns-wichtig)
|
||||
- [4.3 Backend Architecture (`app/`)](#43-backend-architecture-app)
|
||||
- [4.4 Scripts \& Tooling (Die Admin-Toolbox)](#44-scripts--tooling-die-admin-toolbox)
|
||||
- [1. Script-Übersicht](#1-script-übersicht)
|
||||
- [2. Einsatzszenarien \& Bewertung](#2-einsatzszenarien--bewertung)
|
||||
- [5. Maintenance \& "Kill List"](#5-maintenance--kill-list)
|
||||
- [6. Lokales Setup (Development)](#6-lokales-setup-development)
|
||||
- [7. Der Entwicklungs-Zyklus (Workflow)](#7-der-entwicklungs-zyklus-workflow)
|
||||
- [Phase 1: Windows (Code)](#phase-1-windows-code)
|
||||
- [Phase 2: Beelink (Test / Dev)](#phase-2-beelink-test--dev)
|
||||
- [Phase 3: Release \& Deployment (Prod)](#phase-3-release--deployment-prod)
|
||||
- [8. Erweiterungs-Guide: "Teach-the-AI"](#8-erweiterungs-guide-teach-the-ai)
|
||||
- [Workflow A: Neuen Typ implementieren (z. B. `type: risk`)](#workflow-a-neuen-typ-implementieren-z-b-type-risk)
|
||||
- [Workflow B: Graph-Farben ändern](#workflow-b-graph-farben-ändern)
|
||||
- [9. Tests \& Debugging](#9-tests--debugging)
|
||||
- [10. Troubleshooting \& One-Liners](#10-troubleshooting--one-liners)
|
||||
|
||||
---
|
||||
|
||||
## 1. Einführung & Systemüberblick
|
||||
|
||||
### Was ist Mindnet?
|
||||
Mindnet ist ein **Hybrides Knowledge Management System**, das klassische Notizen (Markdown) mit KI-gestützter Analyse verbindet. Es kombiniert **RAG** (Retrieval Augmented Generation) mit einer **Graphen-Datenbank** (Qdrant), um Wissen nicht nur semantisch zu finden, sondern auch strukturell zu vernetzen.
|
||||
|
||||
### Kern-Philosophie
|
||||
1. **Filesystem First:** Die Wahrheit liegt immer auf der Festplatte (Markdown-Dateien). Die Datenbank ist ein abgeleiteter Index.
|
||||
2. **Hybrid Retrieval:** Relevanz entsteht aus Textähnlichkeit (Semantik) + Graphen-Verbindungen (Edges) + Wichtigkeit (Centrality).
|
||||
3. **Active Intelligence:** Das System wartet nicht nur auf Anfragen, sondern schlägt beim Schreiben proaktiv Verbindungen vor ("Matrix Logic").
|
||||
4. **Local Privacy:** Alle KI-Berechnungen (Ollama) laufen lokal. Keine Cloud-Abhängigkeit für Inference.
|
||||
|
||||
---
|
||||
|
||||
## 2. Architektur
|
||||
|
||||
### 2.1 High-Level Übersicht
|
||||
Das System folgt einer strikten Trennung zwischen Frontend (Streamlit) und Backend (FastAPI), wobei bestimmte Performance-Pfade (Graph-Visualisierung) optimiert wurden.
|
||||
|
||||
```mermaid
|
||||
graph TD
|
||||
User((User))
|
||||
|
||||
subgraph "Frontend Layer (Streamlit)"
|
||||
UI["ui.py Router"]
|
||||
ViewChat["Chat View"]
|
||||
ViewGraph["Graph View"]
|
||||
ViewEditor["Editor View"]
|
||||
Logic["Callbacks & State"]
|
||||
end
|
||||
|
||||
subgraph "Backend Layer (FastAPI)"
|
||||
API["main.py"]
|
||||
RouterChat["Chat / RAG"]
|
||||
RouterIngest["Ingest / Write"]
|
||||
CoreRet["Retriever Engine"]
|
||||
CoreIngest["Ingestion Pipeline"]
|
||||
end
|
||||
|
||||
subgraph "Infrastructure & Services"
|
||||
LLM["Ollama (Phi3/Nomic)"]
|
||||
DB[("Qdrant Vector DB")]
|
||||
FS["File System (.md)"]
|
||||
end
|
||||
|
||||
User <--> UI
|
||||
UI -- "REST (Chat, Save, Feedback)" --> API
|
||||
UI -. "Direct Read (Graph Viz Performance)" .-> DB
|
||||
API -- "Embeddings & Completion" --> LLM
|
||||
API -- "Read/Write" --> DB
|
||||
API -- "Read/Write (Source of Truth)" --> FS
|
||||
```
|
||||
|
||||
### 2.2 Datenfluss-Muster
|
||||
|
||||
#### A. Ingestion (Write)
|
||||
Vom Markdown zur Vektor-Datenbank.
|
||||
```mermaid
|
||||
graph LR
|
||||
MD["Markdown File"] --> Parser("Parser")
|
||||
Parser --> Chunker("Chunker")
|
||||
Chunker -- "Text Chunks" --> SemAn{"SemanticAnalyzer<br/>(LLM)"}
|
||||
SemAn -- "Smart Edges" --> Embedder("Embedder")
|
||||
Embedder --> DB[("Qdrant<br/>Points")]
|
||||
|
||||
style DB fill:#f9f,stroke:#333,stroke-width:2px
|
||||
style SemAn fill:#ff9,stroke:#333,stroke-width:2px
|
||||
```
|
||||
|
||||
#### B. Retrieval (Read)
|
||||
Die hybride Suche für Chat & RAG.
|
||||
```mermaid
|
||||
graph LR
|
||||
Query(["Query"]) --> Embed("Embedding")
|
||||
Embed --> Hybrid{"Hybrid Search"}
|
||||
|
||||
subgraph Search Components
|
||||
Vec["Vector Score"]
|
||||
Graph["Graph/Edge Bonus"]
|
||||
end
|
||||
|
||||
Vec --> Hybrid
|
||||
Graph --> Hybrid
|
||||
|
||||
Hybrid --> Rank("Re-Ranking")
|
||||
Rank --> Ctx["LLM Context"]
|
||||
```
|
||||
|
||||
#### C. Visualisierung (Graph)
|
||||
Der optimierte Pfad für das Frontend.
|
||||
```mermaid
|
||||
graph LR
|
||||
UI["Frontend UI"] --> Service("GraphService")
|
||||
Service -- "Direct Read" --> DB[("Qdrant<br/>Edges Collection")]
|
||||
DB --> Cyto["Cytoscape<br/>Rendering"]
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 3. Physische Architektur
|
||||
|
||||
Mindnet läuft in einer verteilten Umgebung (Post-WP15 Setup).
|
||||
|
||||
* **Windows 11 (VS Code):** Entwicklungsumgebung. **Nie** direkt auf `main` arbeiten!
|
||||
* **Beelink (Runtime):** Der Server hostet zwei Instanzen via Systemd:
|
||||
* **PROD:** API (Port 8001) + UI (Port 8501). Home: `~/mindnet`.
|
||||
* **DEV:** API (Port 8002) + UI (Port 8502). Home: `~/mindnet_dev`.
|
||||
* **Gitea (Raspberry Pi):** Versionskontrolle ("Safe"). Speichert den Code.
|
||||
|
||||
---
|
||||
|
||||
## 4. Projektstruktur & Modul-Referenz (Deep Dive)
|
||||
|
||||
Das System ist modular aufgebaut. Hier ist die detaillierte Analyse aller Komponenten.
|
||||
|
||||
### 4.1 Verzeichnisbaum
|
||||
|
||||
```text
|
||||
mindnet/
|
||||
├── app/
|
||||
│ ├── core/ # Business Logic & Algorithms
|
||||
│ ├── routers/ # API Interface (FastAPI)
|
||||
│ ├── services/ # External Integrations (LLM, DB)
|
||||
│ ├── models/ # Pydantic DTOs
|
||||
│ └── frontend/ # UI Logic (Streamlit)
|
||||
├── config/ # Configuration Files (YAML)
|
||||
├── scripts/ # CLI Tools (Ops & Maintenance)
|
||||
└── vault/ # Local Content Storage
|
||||
```
|
||||
|
||||
### 4.2 Frontend Architecture (`app/frontend/`)
|
||||
|
||||
Das Frontend ist eine Streamlit-App, die sich wie eine Single-Page-Application (SPA) verhält.
|
||||
|
||||
| Modul | Status | Verantwortung |
|
||||
| :--- | :--- | :--- |
|
||||
| **`ui.py`** | 🟢 **Core** | **Main Router.** Initialisiert Session-State und entscheidet anhand der Sidebar-Auswahl, welche View gerendert wird. |
|
||||
| **`ui_config.py`** | 🟢 **Config** | **Constants.** Zentraler Ort für Farben (`GRAPH_COLORS`), API-URLs und Timeouts. Änderungen am Look & Feel passieren hier. |
|
||||
| **`ui_chat.py`** | 🟢 **View** | **Chat UI.** Rendert Nachrichtenverlauf, Intent-Badges, Quellen-Expanders und Feedback-Buttons. |
|
||||
| **`ui_editor.py`** | 🟢 **View** | **Editor UI.** Markdown-Editor mit Live-Vorschau. Integriert "Intelligence" (KI-Link-Vorschläge). |
|
||||
| **`ui_graph_cytoscape.py`**| 🟢 **View** | **Modern Graph.** Interaktiver Graph basierend auf Cytoscape.js (COSE Layout). |
|
||||
| **`ui_graph.py`** | 🟡 **Legacy** | **Graph UI (Fallback).** Alte Implementierung mittels `streamlit-agraph`. |
|
||||
| **`ui_callbacks.py`** | 🟢 **Logic** | **State Controller.** Handhabt komplexe State-Übergänge (z.B. Graph -> Editor). |
|
||||
| **`ui_utils.py`** | 🟢 **Logic** | **Helper.** Enthält den **Healing Parser** (`parse_markdown_draft`), der defektes JSON/YAML von LLMs repariert. |
|
||||
| **`ui_api.py`** | 🟢 **Data** | **API Client.** Wrapper für Backend REST-Calls. |
|
||||
| **`ui_graph_service.py`** | 🟢 **Data** | **Performance Hack.** Greift direkt auf Qdrant zu (bypass API), um Graphen schnell zu laden. |
|
||||
|
||||
#### Frontend Design Patterns (Wichtig!)
|
||||
|
||||
1. **Active Inspector Pattern (`ui_graph_cytoscape.py`)**
|
||||
Um Re-Renders im Graphen zu vermeiden, nutzen wir CSS-Klassen. Wird ein Knoten angeklickt, ändert sich nur die CSS-Klasse (`.inspected`), aber die Physik-Simulation startet nicht neu. Das sorgt für ein stabiles UI-Gefühl.
|
||||
|
||||
2. **Resurrection Pattern (`ui_editor.py`)**
|
||||
Streamlit neigt dazu, Eingaben bei Re-Runs zu "vergessen". Der Editor synchronisiert seinen Inhalt aggressiv in den `session_state`.
|
||||
* Logik: `if widget_key not in session_state: restore_from_data_key()`.
|
||||
* Ergebnis: Texteingaben überleben Tab-Wechsel.
|
||||
|
||||
3. **Filesystem First (`ui_callbacks.py`)**
|
||||
Wenn man im Graphen auf "Bearbeiten" klickt:
|
||||
1. Versucht das System, die **echte Datei** von der Festplatte zu lesen.
|
||||
2. Nur wenn das fehlschlägt, wird der Text aus den Datenbank-Chunks rekonstruiert ("Stitching").
|
||||
Dies verhindert, dass veraltete Datenbank-Stände die echten Dateien überschreiben.
|
||||
|
||||
### 4.3 Backend Architecture (`app/`)
|
||||
|
||||
Das Backend ist das Herzstück. Es stellt die Logik via REST-API bereit.
|
||||
|
||||
| Layer | Datei | Status | Verantwortung |
|
||||
| :--- | :--- | :--- | :--- |
|
||||
| **Entry** | `app/main.py` | 🟢 **Core** | **Entrypoint.** Initialisiert FastAPI, CORS, und bindet alle Router ein. |
|
||||
| **Config** | `app/config.py` | 🟢 **Core** | **Settings.** Zentrale Konfiguration (Pydantic). Lädt Env-Vars für Qdrant, LLM und Pfade. |
|
||||
| **Router** | `app/routers/chat.py` | 🟢 **API** | **Conversation API.** Haupt-Endpunkt für Chat. Entscheidet zwischen Interview- und RAG-Modus. |
|
||||
| | `app/routers/ingest.py` | 🟢 **API** | **Write API.** Nimmt Markdown entgegen, steuert Ingestion und Discovery-Analyse. |
|
||||
| | `app/routers/query.py` | 🟢 **API** | **Search API.** Klassischer Hybrid-Retriever Endpunkt. |
|
||||
| | `app/routers/graph.py` | 🟢 **API** | **Viz API.** Liefert Knoten/Kanten für Frontend-Graphen (Cytoscape). |
|
||||
| | `app/routers/tools.py` | 🟢 **API** | **Agent Specs.** Liefert JSON-Schemas für die Integration in externe Agenten (Ollama/MCP). |
|
||||
| **Engine** | `app/core/ingestion.py` | ⚙️ **Core** | **Pipeline Controller.** Koordiniert Parsing, Hashing (Change-Detection) und DB-Upserts. |
|
||||
| | `app/core/retriever.py` | ⚙️ **Core** | **Search Engine.** Berechnet Scores (Vektor + Graph + Centrality) und baut Erklärungen. |
|
||||
| | `app/core/chunker.py` | ⚙️ **Core** | **Segmentation.** Zerlegt Text intelligent. Orchestriert `SemanticAnalyzer` für Smart Edges. |
|
||||
| | `app/core/parser.py` | ⚙️ **Core** | **I/O.** Liest Markdown robust (Encoding-Fallback), trennt Frontmatter/Body. |
|
||||
| | `app/core/derive_edges.py`| ⚙️ **Core** | **Link Extractor.** Findet Wikilinks, Callouts und Typed Relations im Text. |
|
||||
| | `app/core/note_payload.py`| ⚙️ **Core** | **Builder.** Erzeugt JSON für `mindnet_notes`. Vererbt Configs (Frontmatter > Type > Default). |
|
||||
| | `app/core/qdrant_points.py`| ⚙️ **Core** | **Object Mapper.** Wandelt Payloads in Qdrant `PointStruct`s um. Handhabt UUIDs. |
|
||||
| **Services** | `app/services/llm_service.py`| 🧠 **AI** | **AI Client.** Async Client für Ollama. Verwaltet Concurrency (Semaphore). |
|
||||
| | `app/services/embeddings_client.py`| 🧠 **AI** | **Vector Client.** Unified Client für Embeddings (Ollama/Nomic). Ersetzt lokale Modelle. |
|
||||
| | `app/services/discovery.py`| 🧠 **AI** | **Intelligence.** "Matrix Logic" für Link-Vorschläge (WP-11). |
|
||||
| | `app/services/semantic_analyzer.py`| 🧠 **AI** | **Filter.** KI-Validierung von Kanten im Hintergrund (Background Priority). |
|
||||
|
||||
### 4.4 Scripts & Tooling (Die Admin-Toolbox)
|
||||
|
||||
Der Ordner `scripts/` enthält verifizierte Werkzeuge für den Betrieb.
|
||||
|
||||
#### 1. Script-Übersicht
|
||||
|
||||
| Skript | Status | Zweck | Argumente & Parameter | Beispielaufruf |
|
||||
| :--- | :--- | :--- | :--- | :--- |
|
||||
| **`import_markdown.py`** | 🟢 **Core** | **Ingestion.** Scannt den Vault und importiert Dateien asynchron in Qdrant. Beachtet Hashes. | `--vault PATH` (Quellordner)<br>`--prefix TEXT` (Collection Prefix)<br>`--force` (Erzwingt Re-Index)<br>`--apply` (Schreibt in DB; sonst Dry-Run) | `python3 scripts/import_markdown.py --vault ./vault --apply` |
|
||||
| **`reset_qdrant.py`** | 🟢 **Core** | **DB-Reset.** Löscht Collections (`wipe`) oder leert sie (`truncate`). Legt Indizes neu an. | `--mode {wipe,truncate}`<br>`--prefix TEXT`<br>`--yes` (Keine Rückfrage)<br>`--no-indexes` (Skip Index-Erstellung) | `python3 -m scripts.reset_qdrant --mode wipe --yes` |
|
||||
| **`health_check_mindnet.py`** | 🟢 **Ops** | **Monitoring.** Prüft API-Verfügbarkeit (`/query`) und Antwortqualität. Standalone (keine Imports). | `--url URL`<br>`--query TEXT`<br>`--top-k INT`<br>`--strict` (Exit-Code 1 bei Warnings) | `python3 scripts/health_check_mindnet.py --strict` |
|
||||
| **`payload_dryrun.py`** | 🟡 **Dev** | **Debugger.** Simuliert die JSON-Erstellung (Payloads) ohne DB-Schreibzugriff. Prüft `types.yaml`. | `--vault PATH`<br>`--note-id ID` (Filter)<br>`--with-edges` (Zeigt Kanten) | `python3 -m scripts.payload_dryrun --vault ./vault --note-id "projekt-alpha"` |
|
||||
| **`edges_full_check.py`** | 🟡 **Audit** | **Integritäts-Check.** Zählt Kanten in der DB und prüft logische Konsistenz (z.B. Chunk-Reihenfolge). | Keine (Liest Konfiguration nur aus Umgebungsvariablen `.env`) | `python3 -m scripts.edges_full_check` |
|
||||
| **`resolve_unresolved_references.py`** | 🔵 **Maint** | **Link-Healer.** Repariert "tote" Links in der DB nachträglich und erzeugt Backlinks. | `--prefix TEXT`<br>`--limit INT`<br>`--apply` (Schreibt Änderungen) | `python3 -m scripts.resolve_unresolved_references --apply` |
|
||||
| **`export_markdown.py`** | ⚪ **Utility** | **Reverse ETL.** Exportiert den Datenbank-Inhalt zurück in Markdown-Dateien (Backup/Recovery). | `--out PATH` (Ziel)<br>`--note-id ID`<br>`--include-edges {yaml,footer}`<br>`--flatten-paths` | `python3 -m scripts.export_markdown --out ./backup` |
|
||||
|
||||
#### 2. Einsatzszenarien & Bewertung
|
||||
|
||||
* **🟢 Essentiell für den Betrieb (Must-Have):**
|
||||
* **`import_markdown.py`**: Das Arbeitspferd. Ohne dieses Skript kommen keine Daten ins System.
|
||||
* **`reset_qdrant.py`**: Zwingend notwendig für CI/CD-Pipelines.
|
||||
* **`health_check_mindnet.py`**: Ideal für Docker-Healthchecks.
|
||||
|
||||
* **🟡 Hilfreich für Entwicklung & Debugging (Should-Have):**
|
||||
* **`payload_dryrun.py`**: Wertvoll, wenn man an der `config/types.yaml` arbeitet.
|
||||
* **`edges_full_check.py`**: Wichtiges Diagnose-Tool für den Graphen.
|
||||
|
||||
* **🔵 Wartung & Spezialfälle (Nice-to-Have):**
|
||||
* **`resolve_unresolved_references.py`**: Sinnvoll in einem "Knowledge Garden", wo oft Links auf noch nicht existierende Notizen gesetzt werden ("Red Links"). Dieses Skript "heilt" den Graphen nachträglich.
|
||||
* **`export_markdown.py`**: Ein Notfall-Tool. Da Mindnet nach dem Prinzip "Filesystem First" arbeitet, ist ein Export aus der DB selten nötig, kann aber bei versehentlichem Löschen von Dateien lebensrettend sein.
|
||||
|
||||
---
|
||||
|
||||
## 5. Maintenance & "Kill List"
|
||||
|
||||
Folgende Dateien wurden im Audit v2.6 als veraltet, redundant oder "Zombie-Code" identifiziert und sollten entfernt werden.
|
||||
|
||||
| Datei | Diagnose | Empfohlene Aktion |
|
||||
| :--- | :--- | :--- |
|
||||
| `app/embed_server.py` | **Zombie.** Alter Standalone-Server. | 🗑️ Löschen |
|
||||
| `app/embeddings.py` | **Zombie.** Veraltete lokale Lib. **(Achtung: Erst Importe in `main.py` entfernen!)** | 🗑️ Löschen |
|
||||
| `app/routers/embed_router.py` | **Zombie.** Nutzt `embeddings.py`. | 🗑️ Löschen |
|
||||
| `app/routers/qdrant_router.py`| **Deprecated.** Keine Logik, nur CRUD. | 🗑️ Löschen |
|
||||
| `app/core/edges.py` | **Redundant.** Ersetzt durch `derive_edges.py`. | 🗑️ Löschen |
|
||||
| `app/core/ranking.py` | **Redundant.** Logik in `retriever.py` integriert. | 🗑️ Löschen |
|
||||
| `app/core/type_registry.py` | **Redundant.** Logik in `ingestion.py` integriert. | 🗑️ Löschen |
|
||||
| `app/core/env_vars.py` | **Veraltet.** Ersetzt durch `config.py`. | 🗑️ Löschen |
|
||||
| `app/services/llm_ollama.py` | **Veraltet.** Ersetzt durch `llm_service.py`. | 🗑️ Löschen |
|
||||
|
||||
---
|
||||
|
||||
## 6. Lokales Setup (Development)
|
||||
|
||||
**Voraussetzungen:** Python 3.10+, Docker, Ollama.
|
||||
|
||||
**Installation:**
|
||||
```bash
|
||||
# 1. Repo & Venv
|
||||
git clone <repo> mindnet
|
||||
cd mindnet
|
||||
python3 -m venv .venv
|
||||
source .venv/bin/activate
|
||||
|
||||
# 2. Dependencies
|
||||
pip install -r requirements.txt
|
||||
|
||||
# 3. Ollama (Nomic ist Pflicht!)
|
||||
ollama pull phi3:mini
|
||||
ollama pull nomic-embed-text
|
||||
```
|
||||
|
||||
**Konfiguration (`.env`):**
|
||||
```ini
|
||||
QDRANT_URL="http://localhost:6333"
|
||||
MINDNET_OLLAMA_URL="http://localhost:11434"
|
||||
MINDNET_LLM_MODEL="phi3:mini"
|
||||
MINDNET_EMBEDDING_MODEL="nomic-embed-text"
|
||||
COLLECTION_PREFIX="mindnet_dev"
|
||||
VECTOR_DIM=768
|
||||
MINDNET_LLM_BACKGROUND_LIMIT=2
|
||||
MINDNET_API_URL="http://localhost:8002"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 7. Der Entwicklungs-Zyklus (Workflow)
|
||||
|
||||
### Phase 1: Windows (Code)
|
||||
1. **Basis aktualisieren:** `git checkout main && git pull`.
|
||||
2. **Branch erstellen:** `git checkout -b feature/mein-feature`.
|
||||
3. **Coden & Committen.**
|
||||
4. **Push:** `git push origin feature/mein-feature`.
|
||||
|
||||
### Phase 2: Beelink (Test / Dev)
|
||||
Hier prüfst du, ob dein Code auf Linux läuft.
|
||||
1. **Einloggen:** `ssh user@beelink`.
|
||||
2. **Ordner:** `cd ~/mindnet_dev`.
|
||||
3. **Code holen:** `git fetch && git checkout feature/mein-feature && git pull`.
|
||||
4. **Dependencies:** `pip install -r requirements.txt`.
|
||||
5. **Restart:** `sudo systemctl restart mindnet-dev`.
|
||||
6. **Validierung (Smoke Tests):**
|
||||
* **Last-Test:** Starte `python3 -m scripts.import_markdown ...` im Terminal und chatte gleichzeitig im UI (Port 8502).
|
||||
* **API Check:** `curl -X POST "http://localhost:8002/ingest/analyze" ...`
|
||||
|
||||
### Phase 3: Release & Deployment (Prod)
|
||||
Wenn alles getestet ist:
|
||||
1. **Gitea:** Pull Request erstellen und mergen.
|
||||
2. **Deploy auf Prod (Beelink):**
|
||||
```bash
|
||||
cd ~/mindnet
|
||||
git pull origin main
|
||||
|
||||
# Sicherstellen, dass Prod-Dependencies aktuell sind
|
||||
source .venv/bin/activate
|
||||
pip install -r requirements.txt
|
||||
ollama pull nomic-embed-text # Falls neue Modelle nötig sind
|
||||
|
||||
# Restart
|
||||
sudo systemctl restart mindnet-prod
|
||||
sudo systemctl restart mindnet-ui-prod
|
||||
```
|
||||
3. **Cleanup:** Branch löschen (lokal und remote).
|
||||
|
||||
---
|
||||
|
||||
## 8. Erweiterungs-Guide: "Teach-the-AI"
|
||||
|
||||
Mindnet lernt nicht durch Training (Fine-Tuning), sondern durch **Konfiguration** und **Vernetzung**.
|
||||
|
||||
### Workflow A: Neuen Typ implementieren (z. B. `type: risk`)
|
||||
1. **Physik (`config/types.yaml`):**
|
||||
```yaml
|
||||
risk:
|
||||
chunk_profile: sliding_short
|
||||
retriever_weight: 0.90 # Sehr wichtig
|
||||
edge_defaults: ["blocks"] # Automatische Kante
|
||||
detection_keywords: ["gefahr", "risiko"]
|
||||
```
|
||||
2. **Strategie (`config/decision_engine.yaml`):**
|
||||
```yaml
|
||||
DECISION:
|
||||
inject_types: ["value", "risk"] # <--- "risk" hinzufügen
|
||||
```
|
||||
*Ergebnis:* Wenn der Intent `DECISION` erkannt wird, sucht das System nun auch aktiv nach Risiken.
|
||||
|
||||
### Workflow B: Graph-Farben ändern
|
||||
1. Öffne `app/frontend/ui_config.py`.
|
||||
2. Bearbeite das Dictionary `GRAPH_COLORS`.
|
||||
|
||||
```python
|
||||
GRAPH_COLORS = {
|
||||
"project": "#FF4B4B",
|
||||
"risk": "#8B0000" # Neu
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 9. Tests & Debugging
|
||||
|
||||
**Unit Tests (Pytest):**
|
||||
```bash
|
||||
pytest tests/test_retriever_basic.py
|
||||
pytest tests/test_chunking.py
|
||||
```
|
||||
|
||||
**Pipeline Tests (Integration):**
|
||||
```bash
|
||||
# JSON-Schema prüfen
|
||||
python3 -m scripts.payload_dryrun --vault ./test_vault
|
||||
|
||||
# Graph-Integrität prüfen
|
||||
python3 -m scripts.edges_full_check
|
||||
```
|
||||
|
||||
**E2E Smoke Tests:**
|
||||
```bash
|
||||
# Decision Engine
|
||||
python tests/test_wp06_decision.py -p 8002 -e DECISION -q "Soll ich X tun?"
|
||||
|
||||
# Feedback
|
||||
python tests/test_feedback_smoke.py --url http://localhost:8002/query
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 10. Troubleshooting & One-Liners
|
||||
|
||||
**DB komplett zurücksetzen (Vorsicht!):**
|
||||
```bash
|
||||
# --yes überspringt die Bestätigung
|
||||
python3 -m scripts.reset_qdrant --mode wipe --prefix "mindnet_dev" --yes
|
||||
```
|
||||
|
||||
**Graphen reparieren (Red Links auflösen):**
|
||||
Nutze dies, wenn Kanten im Graphen ins Leere zeigen (weil die Notiz beim Import noch nicht da war).
|
||||
```bash
|
||||
python3 -m scripts.resolve_unresolved_references --apply
|
||||
```
|
||||
|
||||
**Einen einzelnen File inspizieren (Parser-Sicht):**
|
||||
```bash
|
||||
python3 tests/inspect_one_note.py --file ./vault/MeinFile.md
|
||||
```
|
||||
|
||||
**Live-Logs sehen:**
|
||||
```bash
|
||||
journalctl -u mindnet-dev -f
|
||||
journalctl -u mindnet-ui-dev -f
|
||||
```
|
||||
|
||||
**"UnicodeDecodeError in .env":**
|
||||
* **Ursache:** Umlaute oder Sonderzeichen in der `.env`.
|
||||
* **Lösung:** Datei bereinigen (nur ASCII) und sicherstellen, dass UTF-8 ohne BOM genutzt wird.
|
||||
|
||||
**"Read timed out" im Frontend:**
|
||||
* **Ursache:** Smart Edges brauchen länger als 60s.
|
||||
* **Lösung:** `MINDNET_API_TIMEOUT=300.0` in `.env`.
|
||||
@@ -0,0 +1,152 @@
|
||||
---
|
||||
doc_type: developer_guide
|
||||
audience: developer, architect
|
||||
scope: genai, prompting, workflow
|
||||
status: active
|
||||
version: 1.0
|
||||
context: "Leitfaden für die effiziente Softwareentwicklung mit LLMs im Mindnet-Projekt."
|
||||
---
|
||||
|
||||
# GenAI Development Best Practices & Prompt Library
|
||||
|
||||
Dieser Leitfaden definiert Standards für die Zusammenarbeit mit KI-Modellen (ChatGPT, Claude, Gemini) im Rahmen der Mindnet-Entwicklung. Ziel ist es, Halluzinationen zu minimieren, den Kontext effizient zu nutzen und die Dokumentation synchron zum Code zu halten.
|
||||
|
||||
---
|
||||
|
||||
## 1. Grundprinzipien
|
||||
|
||||
### 1.1 Context is King (aber teuer)
|
||||
LLMs haben ein begrenztes Kontext-Fenster.
|
||||
* **Don't:** "Hier ist mein ganzer Code, fix den Bug." (Führt zu Vergessen von Details).
|
||||
* **Do:** Nutze die **"Map & Fetch" Strategie**:
|
||||
1. Gib der KI eine Inhaltsübersicht (z.B. `project_scan_report.json` oder `tree`).
|
||||
2. Lass die KI entscheiden, welche Dateien sie für die Aufgabe benötigt.
|
||||
3. Lade nur diese Dateien hoch.
|
||||
|
||||
### 1.2 Trust but Verify (Validierung)
|
||||
* **Code:** Führe generierten Code **immer** lokal aus (Unit Tests oder Smoke Tests), bevor du ihn committest.
|
||||
* **Pfade:** KIs erfinden gerne Pfade (z.B. `app/utils.py`, obwohl es `app/core/utils.py` ist). Prüfe Importe immer gegen die Projektstruktur.
|
||||
* **Security:** Achte darauf, dass keine Secrets (API-Keys) in den Prompts landen und keine Secrets vom LLM halluziniert und hardcodiert werden.
|
||||
|
||||
### 1.3 Atomic Chats
|
||||
Nutze für verschiedene Aufgaben frische Chat-Kontexte.
|
||||
* Ein Chat für "Frontend Refactoring".
|
||||
* Ein neuer Chat für "Documentation Update".
|
||||
* *Grund:* Alte Chats akkumulieren "Rauschen" und führen zu Fehlern.
|
||||
|
||||
---
|
||||
|
||||
## 2. Prompt Library (Standard-Vorlagen)
|
||||
|
||||
Nutze diese Prompts, um konsistente Ergebnisse zu erzielen.
|
||||
|
||||
### 2.1 Der "Render-Safe" Prompt (System Instruction)
|
||||
**Wann nutzen?** Immer am Anfang eines Chats, wenn die KI Markdown-Dateien oder Code generieren soll.
|
||||
**Zweck:** Verhindert, dass die Antwort im Chat-Fenster abbricht, weil die KI Code-Blöcke falsch verschachtelt.
|
||||
|
||||
```text
|
||||
# SYSTEM-ANWEISUNG: SICHERES MARKDOWN-RENDERING
|
||||
|
||||
Du agierst als technischer Assistent. Deine Aufgabe ist das Erstellen von Markdown-Dateien, die oft selbst Code-Blöcke enthalten.
|
||||
|
||||
**DAS PROBLEM:**
|
||||
Wenn du eine Markdown-Datei generierst, die Code-Blöcke (```) enthält, und diese Ausgabe selbst in einen Code-Block packst, interpretiert das Chat-Interface das erste innere ``` oft fälschlicherweise als das Ende der Ausgabe.
|
||||
|
||||
**DIE REGEL (STRIKT BEFOLGEN):**
|
||||
Um eine ununterbrochene Darstellung zu garantieren, musst du zwingend eine der folgenden Kapselungs-Methoden anwenden:
|
||||
|
||||
### Methode A: Die 4-Backtick-Methode (Bevorzugt)
|
||||
Umschließe den **gesamten** Datei-Inhalt mit **4 Backticks** (````).
|
||||
Dies erlaubt dir, innerhalb der Datei normale 3 Backticks zu verwenden.
|
||||
|
||||
### Methode B: Die 4-Space-Einrückung (Alternative)
|
||||
Wenn du außen 3 Backticks verwendest, darfst du im Inneren **KEINE** Backticks verwenden.
|
||||
Stattdessen müssen alle inneren Code-Beispiele mit **4 Leerzeichen (Spaces)** eingerückt werden.
|
||||
|
||||
**ZUSAMMENFASSUNG:**
|
||||
Generiere niemals verschachtelte 3-Backtick-Blöcke innerhalb von 3-Backtick-Blöcken.
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
### 2.2 Der "Doku-Update" Prompt (Nach WP-Abschluss)
|
||||
**Wann nutzen?** Wenn ein Feature fertig codiert ist und die Doku (`docs/`) nachgezogen werden muss.
|
||||
**Zweck:** Automatische Identifikation der betroffenen Doku-Dateien ohne manuelles Suchen.
|
||||
|
||||
**Vorbedingung:** Lade `docs/00_General/00_documentation_map.md` und `docs/06_Roadmap/06_active_roadmap.md` hoch.
|
||||
|
||||
```text
|
||||
Du agierst als **Technical Documentation Lead**.
|
||||
|
||||
**Kontext:**
|
||||
Wir haben soeben ein Workpackage (WP) abgeschlossen. Der Code ist implementiert.
|
||||
Jetzt müssen wir die Systemdokumentation (Mindnet v2.6 Modular Docs) aktualisieren.
|
||||
|
||||
**Deine Aufgabe - Phase 1: Identifikation**
|
||||
Analysiere die durchgeführten Änderungen dieses Workpackages (aus dem Chat-Verlauf).
|
||||
Nutze die beiliegende `00_documentation_map.md`, um zu identifizieren, welche Dokumentations-Module betroffen sind.
|
||||
|
||||
**Mapping-Logik:**
|
||||
* Neue Features? -> `00_glossary.md`, `02_Concepts/*`
|
||||
* DB/Payloads geändert? -> `03_tech_data_model.md`
|
||||
* Import/Algorithmus geändert? -> `03_tech_ingestion_pipeline.md`, `03_tech_retrieval_scoring.md`
|
||||
* Neue Configs? -> `03_tech_configuration.md`, `04_admin_operations.md`
|
||||
* UI/UX geändert? -> `01_User_Manual/*`, `03_tech_frontend.md`
|
||||
|
||||
**Output für Phase 1:**
|
||||
Erstelle eine **Liste der betroffenen Dateien** mit Begründung.
|
||||
Fordere mich explizit auf, dir diese Dateien hochzuladen.
|
||||
|
||||
---
|
||||
|
||||
**Deine Aufgabe - Phase 2: Sequenzielle Bearbeitung**
|
||||
Sobald ich die Dateien hochgeladen habe:
|
||||
1. Nimm dir **eine** Datei aus der Liste vor.
|
||||
2. Schreibe den kompletten, aktualisierten Inhalt (Markdown).
|
||||
* *Wichtig:* Halte dich an den bestehenden Stil und die "Render-Safe"-Regel (4 Backticks).
|
||||
3. **Warte** nach der Ausgabe auf mein "OK", bevor du die nächste Datei bearbeitest.
|
||||
|
||||
**Bist du bereit für die Analyse?**
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
### 2.3 Der "Code Architect" Prompt (Refactoring & Analyse)
|
||||
**Wann nutzen?** Wenn du dich in den Code einarbeiten willst oder Aufräumen musst.
|
||||
**Vorbedingung:** Führe lokal `deep_scan.py` aus und lade `project_scan_report.json` hoch.
|
||||
|
||||
```text
|
||||
Du agierst als **Senior Software Architect**.
|
||||
|
||||
**INPUT:**
|
||||
Ich habe dir die Datei `project_scan_report.json` hochgeladen. Sie enthält eine Liste aller Dateien und ihrer Import-Beziehungen.
|
||||
|
||||
**DIE SOLL-STRUKTUR (4 SÄULEN):**
|
||||
Jede Datei muss einem dieser Zweige zugeordnet werden können:
|
||||
1. **Backend:** via `app/main.py`
|
||||
2. **Frontend:** via `app/frontend/ui.py`
|
||||
3. **Batch/Ops:** via `scripts/` (Produktions-Tools)
|
||||
4. **Tests:** via `tests/`
|
||||
|
||||
**DEINE AUFGABE:**
|
||||
Analysiere das JSON. Identifiziere "Zombies" (Dateien, die nirgends importiert werden und keinen klaren Entrypoint haben).
|
||||
Erstelle eine:
|
||||
1. **Modul-Tabelle** (Wer ruft wen auf?).
|
||||
2. **Lösch-Vorschlagsliste** (Dead Code).
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 3. Workflow für ein Workpackage (WP)
|
||||
|
||||
Ein typisches Mindnet-Feature wird so entwickelt:
|
||||
|
||||
1. **Start:** Neuer Chat. Prompt **2.1 (Render-Safe)** eingeben.
|
||||
2. **Kontext:** `project_scan_report.json` oder relevante Core-Dateien hochladen.
|
||||
3. **Code:** Feature implementieren (Iterativ).
|
||||
4. **Test:** Code lokal validieren.
|
||||
5. **Doku:**
|
||||
* Neuer Chat (optional, für sauberen Kontext).
|
||||
* Prompt **2.1** + Prompt **2.2 (Doku-Update)** eingeben.
|
||||
* Doku aktualisieren lassen.
|
||||
6. **Commit:** Code + Doku zusammen pushen.
|
||||
@@ -0,0 +1,116 @@
|
||||
---
|
||||
doc_type: roadmap
|
||||
audience: product_owner, developer
|
||||
status: active
|
||||
version: 2.7
|
||||
context: "Aktuelle Planung für kommende Features (ab WP16), Release-Strategie und Historie der abgeschlossenen WPs."
|
||||
---
|
||||
|
||||
# Mindnet Active Roadmap
|
||||
|
||||
**Aktueller Stand:** v2.6.0 (Post-WP15/WP19)
|
||||
**Fokus:** Visualisierung, Exploration & Intelligent Ingestion.
|
||||
|
||||
## 1. Programmstatus
|
||||
|
||||
Wir haben mit der Implementierung des Graph Explorers (WP19) und der Smart Edge Allocation (WP15) die Basis für ein intelligentes, robustes System gelegt. Der nächste Schritt (WP19a) vertieft die Analyse, während WP16 die "Eingangs-Intelligenz" erhöht.
|
||||
|
||||
| Phase | Fokus | Status |
|
||||
| :--- | :--- | :--- |
|
||||
| **Phase A** | Fundament & Import | ✅ Fertig |
|
||||
| **Phase B** | Semantik & Graph | ✅ Fertig |
|
||||
| **Phase C** | Persönlichkeit | ✅ Fertig |
|
||||
| **Phase D** | Interaktion & Tools | ✅ Fertig |
|
||||
| **Phase E** | Maintenance & Visualisierung | 🚀 Aktiv |
|
||||
|
||||
---
|
||||
|
||||
## 2. Historie: Abgeschlossene Workpackages
|
||||
|
||||
Eine Übersicht der implementierten Features zum schnellen Auffinden von Funktionen. Details siehe `99_legacy_workpackages.md`.
|
||||
|
||||
| WP | Titel | Ergebnis / Kern-Feature |
|
||||
| :--- | :--- | :--- |
|
||||
| **WP-01** | Knowledge Design | Definition von `types.yaml` und Note-Typen (Project, Concept, etc.). |
|
||||
| **WP-02** | Chunking Strategy | Implementierung von Sliding-Window und Hash-basierter Änderungserkennung. |
|
||||
| **WP-03** | Import-Pipeline | Asynchroner Importer, der Markdown in Qdrant (Notes/Edges) schreibt. |
|
||||
| **WP-04a**| Retriever Scoring | Hybride Suche: `Score = Semantik + GraphBonus + TypGewicht`. |
|
||||
| **WP-04b**| Explanation Layer | Transparenz: API liefert "Reasons" (Warum wurde das gefunden?). |
|
||||
| **WP-04c**| Feedback Loop | Logging von User-Feedback (JSONL) als Basis für Learning. |
|
||||
| **WP-05** | RAG-Chat | Integration von Ollama (`phi3`) und Context-Enrichment im Prompt. |
|
||||
| **WP-06** | Decision Engine | Hybrid Router unterscheidet Frage (`RAG`) vs. Handlung (`Interview`). |
|
||||
| **WP-07** | Interview-Assistent | One-Shot Extraction: Erzeugt Markdown-Drafts aus User-Input. |
|
||||
| **WP-10** | Web UI | Streamlit-Frontend als Ersatz für das Terminal. |
|
||||
| **WP-10a**| Draft Editor | GUI-Komponente zum Bearbeiten und Speichern generierter Notizen. |
|
||||
| **WP-11** | Backend Intelligence | `nomic-embed-text` (768d) und Matrix-Logik für Kanten-Typisierung. |
|
||||
| **WP-15** | Smart Edge Allocation | LLM-Filter für Kanten in Chunks + Traffic Control (Semaphore) + Strict Chunking. |
|
||||
| **WP-19** | Graph Visualisierung | **Frontend Modularisierung:** Umbau auf `ui_*.py`.<br>**Graph Engines:** Parallelbetrieb von Cytoscape (COSE) und Agraph.<br>**Tools:** "Single Source of Truth" Editor, Persistenz via URL. |
|
||||
|
||||
---
|
||||
|
||||
## 3. Offene Workpackages (Planung)
|
||||
|
||||
Diese Features stehen als nächstes an oder befinden sich in der Umsetzung.
|
||||
|
||||
### WP-19a – Graph Intelligence & Discovery (Sprint-Fokus)
|
||||
**Status:** 🚀 Startklar
|
||||
**Ziel:** Vom "Anschauen" zum "Verstehen". Deep-Dive Werkzeuge für den Graphen.
|
||||
* **Discovery Screen:** Neuer Tab für semantische Suche ("Finde Notizen über Vaterschaft") und Wildcard-Filter.
|
||||
* **Filter-Logik:** "Zeige nur Wege, die zu `type:decision` führen".
|
||||
* **Chunk Inspection:** Umschaltbare Granularität (Notiz vs. Chunk) zur Validierung des Smart Chunkers.
|
||||
|
||||
### WP-14 – Review / Refactoring / Dokumentation
|
||||
**Status:** 🟡 Laufend (Phase E)
|
||||
**Ziel:** Technische Schulden abbauen, die durch schnelle Feature-Entwicklung (WP15/WP19) entstanden sind.
|
||||
* **Refactoring `chunker.py`:** Die Datei ist monolithisch geworden (Parsing, Strategien, LLM-Orchestrierung).
|
||||
* *Lösung:* Aufteilung in ein Package `app/core/chunking/` mit Modulen (`strategies.py`, `orchestration.py`, `utils.py`).
|
||||
* **Dokumentation:** Kontinuierliche Synchronisation von Code und Docs (v2.6 Stand).
|
||||
|
||||
### WP-16 – Auto-Discovery & Intelligent Ingestion
|
||||
**Status:** 🟡 Geplant
|
||||
**Ziel:** Das System soll "dumme" Textdateien beim Import automatisch analysieren, strukturieren und anreichern, bevor sie gespeichert werden.
|
||||
**Kern-Features:**
|
||||
1. **Smart Link Enricher:** Automatisches Erkennen von fehlenden Kanten in Texten ohne explizite Wikilinks. Ein "Enricher" scannt Text vor dem Import, findet Keywords (z.B. "Mindnet") und schlägt Links vor (`[[Mindnet]]`).
|
||||
2. **Structure Analyzer (Auto-Strategy):**
|
||||
* *Problem:* Manuelle Zuweisung von `chunking_profile` in `types.yaml` ist starr.
|
||||
* *Lösung:* Vorschalten einer Analysestufe im Importer (`chunker.py`), die die Text-Topologie prüft und die Strategie wählt.
|
||||
* *Metrik 1 (Heading Density):* Verhältnis `Anzahl Überschriften / Wortanzahl`. Hohe Dichte (> 1/200) -> Indikator für `structured_smart_edges`. Niedrige Dichte -> `sliding_smart_edges`.
|
||||
* *Metrik 2 (Variance):* Regelmäßigkeit der Abstände zwischen Headings.
|
||||
3. **Context-Aware Hierarchy Merging:**
|
||||
* *Problem:* Leere Zwischenüberschriften (z.B. "Tier 2") gingen früher als bedeutungslose Chunks verloren oder wurden isoliert.
|
||||
* *Lösung:* Generalisierung der Logik aus WP-15, die leere Eltern-Elemente automatisch mit dem ersten Kind-Element verschmilzt ("Tier 2 + MP1"), um den Kontext für das Embedding zu wahren.
|
||||
|
||||
### WP-17 – Conversational Memory (Gedächtnis)
|
||||
**Status:** 🟡 Geplant
|
||||
**Ziel:** Echte Dialoge statt Request-Response.
|
||||
* **Tech:** Erweiterung des `ChatRequest` DTO um `history`.
|
||||
* **Logik:** Token-Management (Context Window Balancing zwischen RAG-Doks und Chat-Verlauf).
|
||||
|
||||
### WP-18 – Graph Health & Maintenance
|
||||
**Status:** 🟡 Geplant (Prio 2)
|
||||
**Ziel:** Konsistenzprüfung ("Garbage Collection").
|
||||
* **Feature:** Cronjob `check_graph_integrity.py`.
|
||||
* **Funktion:** Findet "Dangling Edges" (Links auf gelöschte Notizen) und repariert/löscht sie.
|
||||
|
||||
### WP-13 – MCP-Integration & Agenten-Layer
|
||||
**Status:** 🟡 Geplant
|
||||
**Ziel:** mindnet als MCP-Server bereitstellen, damit Agenten (Claude Desktop, OpenAI) standardisierte Tools nutzen können.
|
||||
* **Umfang:** MCP-Server mit Tools (`mindnet_query`, `mindnet_explain`, etc.).
|
||||
|
||||
### WP-20 – Cloud Hybrid Mode (Optional)
|
||||
**Status:** ⚪ Optional
|
||||
**Ziel:** "Turbo-Modus" für Massen-Imports.
|
||||
* **Konzept:** Switch in `.env`, um statt Ollama (Lokal) auf Google Gemini (Cloud) umzuschalten.
|
||||
|
||||
---
|
||||
|
||||
## 4. Abhängigkeiten & Release-Plan
|
||||
|
||||
```mermaid
|
||||
graph TD
|
||||
WP19(Graph Viz) --> WP19a(Discovery)
|
||||
WP19a --> WP17(Memory)
|
||||
WP15(Smart Edges) --> WP16(Auto-Discovery)
|
||||
WP15 --> WP14(Refactoring)
|
||||
WP03(Import) --> WP18(Health Check)
|
||||
WP03/WP04 --> WP13(MCP)
|
||||
@@ -0,0 +1,202 @@
|
||||
---
|
||||
doc_type: operations
|
||||
audience: developer, admin
|
||||
status: active
|
||||
version: 1.0
|
||||
context: "Sammlung von Initialisierungs-Prompts für neue Chat-Sessions. Jeder Prompt entspricht dem Projektauftrag für ein spezifisches Workpackage."
|
||||
---
|
||||
|
||||
# Mindnet WP-Handover Prompts
|
||||
|
||||
**Verwendung:**
|
||||
Kopiere den entsprechenden Block in ein **neues** Chat-Fenster, um die KI-Instanz exakt auf den Kontext und die Ziele des Workpackages einzustellen.
|
||||
|
||||
---
|
||||
|
||||
## WP-19a: Graph Intelligence & Discovery
|
||||
|
||||
**Status:** 🚀 Startklar
|
||||
**Fokus:** Frontend-Erweiterung, Semantische Suche, Filterung.
|
||||
|
||||
```text
|
||||
Du bist der Lead Developer für "Mindnet", ein lokales RAG-System (Python/FastAPI/Streamlit/Qdrant).
|
||||
Wir starten jetzt **WP-19a: Graph Intelligence & Discovery**.
|
||||
|
||||
**Status Quo (v2.6.0):**
|
||||
- Backend: Async API mit `/query` (Hybrid Search) und `/chat`.
|
||||
- Frontend: Modularisiertes Streamlit (`ui.py`, `ui_graph.py`).
|
||||
- Daten: Qdrant Indizes (`notes`, `chunks`, `edges`) sind gefüllt.
|
||||
|
||||
**Dein Auftrag (WP-19a):**
|
||||
Implementiere "Deep Dive" Werkzeuge im Frontend, um den Graphen nicht nur zu sehen, sondern zu verstehen.
|
||||
1. **Neues UI-Modul:** Erstelle `app/frontend/ui_discovery.py`.
|
||||
2. **Discovery Tab:** Implementiere eine Oberfläche für:
|
||||
- Semantische Suche (ohne Chat-Modus).
|
||||
- Wildcard-Filter ("Zeige alle Notes vom Typ 'decision'").
|
||||
- Pfad-Analyse ("Wie sind Note A und Note B verbunden?").
|
||||
3. **Chunk Inspection:** Baue einen Toggle, der im Graph-Explorer zwischen "Note-View" (grob) und "Chunk-View" (fein) umschaltet.
|
||||
|
||||
**Regeln:**
|
||||
- Nutze `st.session_state` für Persistenz zwischen Re-Renders.
|
||||
- Halte die Business-Logik im Backend (ggf. neue Endpoints in `app/routers/query.py`).
|
||||
- Gib vollständigen, lauffähigen Code aus.
|
||||
|
||||
Bitte bestätige die Übernahme und skizziere die Architektur für `ui_discovery.py`.
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## WP-13: MCP Integration & Agenten-Layer
|
||||
|
||||
**Status:** 🟡 Geplant
|
||||
**Fokus:** Schnittstelle für externe Agenten (Claude Desktop).
|
||||
|
||||
```text
|
||||
Du bist der Lead Developer für "Mindnet" (Python/FastAPI/Qdrant).
|
||||
Wir starten jetzt **WP-13: MCP Integration**.
|
||||
|
||||
**Status Quo (v2.6.0):**
|
||||
- Das System läuft stabil asynchron.
|
||||
- `types.yaml` steuert die Logik.
|
||||
- Es existieren Services für Retrieval und Graph-Access.
|
||||
|
||||
**Dein Auftrag (WP-13):**
|
||||
Implementiere einen MCP-Server (Model Context Protocol), der Mindnet als "Tool" für Claude Desktop verfügbar macht.
|
||||
1. **Server:** Erstelle `app/mcp_server.py` basierend auf dem `mcp`-SDK.
|
||||
2. **Tools:** Implementiere folgende Tools:
|
||||
- `search_notes(query)`: Nutzt unseren Hybriden Retriever.
|
||||
- `read_note(id)`: Liest Fulltext einer Notiz.
|
||||
- `list_connections(id)`: Zeigt Edges an.
|
||||
- `Notes(content)`: (Optional) Nutzt die Ingestion-Pipeline.
|
||||
3. **Integration:** Nutze die bestehenden Services (`Retriever`, `QdrantClient`) wieder – kein redundanter Code!
|
||||
4. **Async:** Achte auf Kompatibilität zwischen MCP und unserem `asyncio` Core.
|
||||
|
||||
**Regeln:**
|
||||
- Halte dich strikt an die Architektur in `mindnet_technical_architecture.md`.
|
||||
- Aktualisiere den `admin_guide.md` mit Anweisungen zur Einbindung in Claude Desktop config.
|
||||
|
||||
Bitte bestätige die Übernahme und zeige einen ersten Entwurf für `app/mcp_server.py`.
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## WP-14: Review & Refactoring
|
||||
|
||||
**Status:** 🟡 Laufend
|
||||
**Fokus:** Code-Qualität, Modularisierung, Technische Schulden.
|
||||
|
||||
```text
|
||||
Du bist der Software-Architekt für "Mindnet".
|
||||
Wir starten **WP-14: Review & Refactoring**.
|
||||
|
||||
**Status Quo (v2.6.0):**
|
||||
- Das System ist funktional mächtig, aber einige Dateien (z.B. `chunker.py`) sind monolithisch geworden.
|
||||
- Dokumentation und Code müssen synchronisiert werden.
|
||||
|
||||
**Dein Auftrag (WP-14):**
|
||||
1. **Refactoring `chunker.py`:** Zerlege den Monolithen in ein sauberes Package `app/core/chunking/`.
|
||||
- `strategies.py`: Enthält `sliding_window` und `by_heading` Logik.
|
||||
- `orchestration.py`: Enthält `assemble_chunks` und Smart-Edge-Flow.
|
||||
- `utils.py`: Helper.
|
||||
2. **Cleanup:** Entferne veraltete / auskommentierte Code-Blöcke im gesamten Projekt.
|
||||
3. **Doc-Sync:** Prüfe, ob alle Parameter in `types.yaml` auch im Code verwendet werden (Dead Config Detection).
|
||||
|
||||
**Regeln:**
|
||||
- Funktionalität darf sich nicht ändern (Regression Tests!).
|
||||
- Imports in `scripts/import_markdown.py` müssen angepasst werden.
|
||||
|
||||
Bitte bestätige und beginne mit der Strukturierung des neuen `chunking` Packages.
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## WP-16: Auto-Discovery & Intelligent Ingestion
|
||||
|
||||
**Status:** 🟡 Geplant
|
||||
**Fokus:** Automatisierung beim Import, "Smarter Text".
|
||||
|
||||
```text
|
||||
Du bist der Lead Developer für "Mindnet".
|
||||
Wir starten **WP-16: Auto-Discovery & Intelligent Ingestion**.
|
||||
|
||||
**Status Quo (v2.6.0):**
|
||||
- Import verlässt sich auf explizite Wikilinks und manuelle Profil-Wahl in `types.yaml`.
|
||||
- Smart Edges filtern nur vorhandene Links.
|
||||
|
||||
**Dein Auftrag (WP-16):**
|
||||
Mache den Import intelligenter, bevor Daten gespeichert werden.
|
||||
1. **Structure Analyzer:** Erweitere den Chunker um eine Vor-Analyse.
|
||||
- Berechne "Heading Density" (Überschriften pro Wort).
|
||||
- Wähle automatisch `structured` (hohe Dichte) oder `sliding` (niedrige Dichte), wenn `profile: auto` gesetzt ist.
|
||||
2. **Smart Link Enricher:** Implementiere einen Service, der im Text nach Keywords sucht, die als Titel anderer Notizen existieren (Exact Match & Fuzzy Match).
|
||||
- Schlage diese als `suggested_edges` vor.
|
||||
3. **Hierarchy Merging:** Generalisiere die Logik, dass leere Überschriften ("Tier 2") automatisch mit dem folgenden Inhalt verschmelzen.
|
||||
|
||||
**Regeln:**
|
||||
- Performance beachten! Der Import darf nicht ewig dauern.
|
||||
- Änderungen am Content nur im RAM, Original-Datei bleibt unangetastet (außer User will Writeback).
|
||||
|
||||
Bitte bestätige und skizziere den Algorithmus für den Structure Analyzer.
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## WP-17: Conversational Memory
|
||||
|
||||
**Status:** 🟡 Geplant
|
||||
**Fokus:** Dialog-Qualität, Kontext.
|
||||
|
||||
```text
|
||||
Du bist der AI-Engineer für "Mindnet".
|
||||
Wir starten **WP-17: Conversational Memory**.
|
||||
|
||||
**Status Quo (v2.6.0):**
|
||||
- Chat ist "stateless". Jede Anfrage wird isoliert betrachtet.
|
||||
- RAG funktioniert, aber Rückfragen ("Was meinst du damit?") scheitern.
|
||||
|
||||
**Dein Auftrag (WP-17):**
|
||||
Implementiere ein Kurzzeitgedächtnis für den Chat.
|
||||
1. **API Update:** Erweitere `ChatRequest` (DTO) um ein Feld `history: List[Message]`.
|
||||
2. **Frontend:** Passe `ui.py` an, um die letzten N Nachrichten mitzusenden.
|
||||
3. **Token Management:** Implementiere eine Logik im `LLMService`, die das Kontext-Fenster (z.B. 4k Token) balanciert:
|
||||
- System Prompt (fest)
|
||||
- RAG Chunks (hoch gewichtet)
|
||||
- Chat History (auffüllen bis Limit)
|
||||
4. **Prompting:** Integriere `{chat_history}` in das Template in `prompts.yaml`.
|
||||
|
||||
**Regeln:**
|
||||
- Nutze effizientes Truncation (älteste Nachrichten zuerst weg).
|
||||
- History darf RAG-Wissen nicht verdrängen (Reserviere min. 60% für RAG).
|
||||
|
||||
Bitte bestätige und zeige das aktualisierte Pydantic-Modell für `ChatRequest`.
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## WP-18: Graph Health & Maintenance
|
||||
|
||||
**Status:** 🟡 Geplant
|
||||
**Fokus:** Datenintegrität, Garbage Collection.
|
||||
|
||||
```text
|
||||
Du bist der DevOps Engineer für "Mindnet".
|
||||
Wir starten **WP-18: Graph Health & Maintenance**.
|
||||
|
||||
**Status Quo (v2.6.0):**
|
||||
- Import ist asynchron. Bei Timeouts kann der DB-Stand vom File-System abweichen (Hash-Mismatch).
|
||||
- Gelöschte Notizen hinterlassen "Dangling Edges".
|
||||
|
||||
**Dein Auftrag (WP-18):**
|
||||
1. **Transactional Ingestion:** Implementiere einen "Two-Phase Commit" für den Import.
|
||||
- Der File-Hash für die Änderungserkennung darf erst aktualisiert werden, wenn der Qdrant-Upsert *bestätigt* erfolgreich war.
|
||||
2. **Integrity Script:** Erstelle `scripts/check_graph_integrity.py`.
|
||||
- Prüfe: Gibt es Edges, deren `target_id` nicht in `notes` existiert?
|
||||
- Aktion: Report oder Auto-Delete.
|
||||
3. **Resolve References:** Erweitere das Skript um Logik, die "Unresolved Targets" (Text-Links) nachträglich in echte UUID-Links wandelt, wenn die Ziel-Notiz später importiert wurde.
|
||||
|
||||
**Regeln:**
|
||||
- Sicherheit geht vor Geschwindigkeit.
|
||||
- Keine Datenlöschung ohne Log-Eintrag.
|
||||
|
||||
Bitte bestätige und skizziere die Logik für den Transactional Hash Update.
|
||||
```
|
||||
@@ -0,0 +1,94 @@
|
||||
---
|
||||
doc_type: archive
|
||||
audience: historian, architect
|
||||
status: archived
|
||||
context: "Archivierte Details zu abgeschlossenen Workpackages (WP01-WP19). Referenz für historische Design-Entscheidungen."
|
||||
---
|
||||
|
||||
# Legacy Workpackages (Archiv)
|
||||
|
||||
**Quellen:** `Programmplan_V2.2.md`, `Active Roadmap`
|
||||
|
||||
**Status:** Abgeschlossen / Implementiert.
|
||||
Dieses Dokument dient als Referenz für die Entstehungsgeschichte von Mindnet v2.6.
|
||||
|
||||
## Phase A: Fundament (WP01-03)
|
||||
|
||||
### WP-01 – Wissensdesign
|
||||
* **Ziel:** Definition der Datenstruktur.
|
||||
* **Ergebnis:** Entscheidung gegen komplexe Ontologien (RDF/OWL), für pragmatische Typen (`project`, `concept`). Definition der YAML-Frontmatter-Pflichtfelder.
|
||||
* **Artefakt:** `01_knowledge_design.md`.
|
||||
|
||||
### WP-02 – Chunking & Hash-Strategie
|
||||
* **Ziel:** Texte suchbar machen und Änderungen erkennen.
|
||||
* **Ergebnis:** Implementierung des `SlidingWindowChunker`. Einführung von UUIDv5 für deterministische IDs.
|
||||
* **Learning:** Starre Chunking-Grenzen zerschneiden oft den Kontext. Daher Einführung von Overlap (50 Tokens).
|
||||
|
||||
### WP-03 – Import-Pipeline & Edge-System
|
||||
* **Ziel:** Markdown in Vektoren wandeln.
|
||||
* **Ergebnis:** Der "Importer" (`import_markdown.py`). Entscheidung, Kanten (`_edges`) als eigene Collection zu führen statt als Payload in Chunks (für bessere Graphen-Algorithmen wie Centrality).
|
||||
|
||||
---
|
||||
|
||||
## Phase B: Semantik (WP04)
|
||||
|
||||
### WP-04a – Retriever & Graph-Scoring
|
||||
* **Ziel:** Bessere Suchergebnisse als reines Vektor-Matching.
|
||||
* **Ergebnis:** Die Formel `Score = Semantik + GraphBonus + TypGewicht`.
|
||||
* **Learning:** Reine Vektorsuche reichte nicht, um den Kontext ("Warum ist das wichtig?") zu erfassen. Der "Graph Bonus" war der Durchbruch für assoziatives Finden.
|
||||
|
||||
### WP-04b – Explanation Layer ("Why-Layer")
|
||||
* **Ziel:** Transparenz.
|
||||
* **Ergebnis:** `explain=True` Parameter. Die API liefert menschenlesbare Gründe ("Gefunden, weil Projekt Alpha davon abhängt").
|
||||
|
||||
### WP-04c – Feedback Logging
|
||||
* **Ziel:** Datenbasis für zukünftiges Lernen schaffen.
|
||||
* **Ergebnis:** Das "Data Flywheel". Jede Suche und Bewertung wird in JSONL-Dateien geloggt (`search_history.jsonl`, `feedback.jsonl`).
|
||||
|
||||
---
|
||||
|
||||
## Phase C: Persönlichkeit (WP05-07)
|
||||
|
||||
### WP-05 – RAG-Chat
|
||||
* **Ziel:** Natürliche Sprache statt Suchergebnisse.
|
||||
* **Ergebnis:** Integration von Ollama (`phi3`).
|
||||
* **Tech:** Prompt-Engineering (`prompts.yaml`) statt Fine-Tuning, um flexibel zu bleiben.
|
||||
|
||||
### WP-06 – Decision Engine
|
||||
* **Ziel:** Strategische Beratung statt nur Fakten.
|
||||
* **Ergebnis:** Der Hybrid Router.
|
||||
* **Konzept:** Unterscheidung von *Fragen* (RAG) und *Handlungen* (Interview). Strategisches Laden von Werten (`type: value`), um Entscheidungen moralisch zu begründen.
|
||||
|
||||
### WP-07 – Interview-Assistent
|
||||
* **Ziel:** Bekämpfung des "Writer's Block".
|
||||
* **Ergebnis:** One-Shot Extraction. Der Chatbot generiert aus einem losen Satz ("Neues Projekt Alpha") einen strukturierten Markdown-Draft.
|
||||
|
||||
---
|
||||
|
||||
## Phase D: Interaktion (WP10-15)
|
||||
|
||||
### WP-10/10a – Web UI & Draft Editor
|
||||
* **Ziel:** Usability für Nicht-Techniker.
|
||||
* **Ergebnis:** Streamlit App. Ablösung des Terminals.
|
||||
* **Feature:** "Healing Parser", der defektes JSON vom LLM repariert.
|
||||
|
||||
### WP-11 – Backend Intelligence
|
||||
* **Ziel:** Automatisierung der Vernetzung.
|
||||
* **Ergebnis:** AsyncIO Umstellung für Performance. Einführung von `nomic-embed-text` (768d) für präzise Semantik. Matrix-Logik für automatische Kanten-Typisierung.
|
||||
|
||||
### WP-15 – Smart Edge Allocation (Meilenstein)
|
||||
* **Problem:** "Broadcasting". Ein Chunk erbte alle Links der Note, auch irrelevante. Das verwässerte die Suchergebnisse.
|
||||
* **Lösung:** LLM prüft jeden Chunk auf Link-Relevanz.
|
||||
* **Tech:** Einführung von **Traffic Control** (Semaphore), um Import und Chat zu parallelisieren, ohne die Hardware zu überlasten.
|
||||
|
||||
---
|
||||
|
||||
## Phase E: Visualisierung & Maintenance (WP19)
|
||||
|
||||
### WP-19 – Graph Visualisierung & Modularisierung
|
||||
* **Ziel:** Transparenz über die Datenstruktur schaffen und technische Schulden (Monolith) abbauen.
|
||||
* **Ergebnis:**
|
||||
* **Modularisierung:** Aufsplittung der `ui.py` in Router, Services und Views (`ui_*.py`).
|
||||
* **Graph Explorer:** Einführung von `st-cytoscape` für stabile, nicht-überlappende Layouts (COSE) als Ergänzung zur Legacy-Engine (Agraph).
|
||||
* **Single Source of Truth:** Der Editor lädt Inhalte nun direkt vom Dateisystem statt aus (potenziell veralteten) Vektor-Payloads.
|
||||
* **UX:** Einführung von URL-Persistenz für Layout-Settings und CSS-basiertes Highlighting zur Vermeidung von Re-Renders.
|
||||
File renamed without changes.
+85
-48
@@ -1,5 +1,5 @@
|
||||
# mindnet v2.4 — Programmplan
|
||||
**Version:** 2.6.0 (Inkl. WP-15 Smart Edge Allocation)
|
||||
**Version:** 2.7.0 (Post-WP15: Roadmap Erweiterung für Graph-Health & Visualisierung)
|
||||
**Stand:** 2025-12-12
|
||||
**Status:** Aktiv
|
||||
|
||||
@@ -36,6 +36,9 @@
|
||||
- [WP-15 – Smart Edge Allocation \& Chunking Strategies (abgeschlossen)](#wp-15--smart-edge-allocation--chunking-strategies-abgeschlossen)
|
||||
- [WP-16 – Auto-Discovery \& Enrichment (geplant)](#wp-16--auto-discovery--enrichment-geplant)
|
||||
- [WP-17 – Conversational Memory (Dialog-Gedächtnis) (geplant)](#wp-17--conversational-memory-dialog-gedächtnis-geplant)
|
||||
- [WP-18 – Graph Health \& Maintenance (NEU, geplant)](#wp-18--graph-health--maintenance-neu-geplant)
|
||||
- [WP-19 – Graph Visualisierung \& Explorer (NEU, geplant)](#wp-19--graph-visualisierung--explorer-neu-geplant)
|
||||
- [WP-20 – Cloud Hybrid Mode (Gemini) (NEU, geplant)](#wp-20--cloud-hybrid-mode-gemini-neu-geplant)
|
||||
- [7. Abhängigkeiten (vereinfacht, aktualisiert)](#7-abhängigkeiten-vereinfacht-aktualisiert)
|
||||
- [8. Laufzeit- \& Komplexitätsindikatoren (aktualisiert)](#8-laufzeit---komplexitätsindikatoren-aktualisiert)
|
||||
- [9. Programmfortschritt (Ampel, aktualisiert)](#9-programmfortschritt-ampel-aktualisiert)
|
||||
@@ -194,7 +197,7 @@ Die folgenden Prinzipien steuern alle Workpackages und Entscheidungen:
|
||||
Phase B – Semantik, Graph & Lernen (Fertig)
|
||||
Phase C – Persönlichkeitsmodell & KI-Zwilling (Fertig)
|
||||
Phase D – Agenten, MCP & Interaktion (Aktiv)
|
||||
Phase E – Review, Refactoring, Dokumentation
|
||||
Phase E – Maintenance, Visualisierung & Scaling (Neu)
|
||||
|
||||
Alle Workpackages sind einer Phase zugeordnet. WP-01 bis WP-07 und WP-10/10a/11 sind erfolgreich abgeschlossen.
|
||||
|
||||
@@ -556,6 +559,7 @@ Automatisches Erkennen und Vorschlagen von fehlenden Kanten in "dummem" Text (oh
|
||||
- Komplexität: Hoch
|
||||
|
||||
---
|
||||
|
||||
### WP-17 – Conversational Memory (Dialog-Gedächtnis) (geplant)
|
||||
|
||||
**Phase:** D
|
||||
@@ -573,19 +577,76 @@ Erweiterung des Chat-Backends von einem statischen Request-Response-Modell zu ei
|
||||
**Aufwand / Komplexität:**
|
||||
- Aufwand: Mittel
|
||||
- Komplexität: Mittel
|
||||
|
||||
---
|
||||
|
||||
### WP-18 – Graph Health & Maintenance (NEU, geplant)
|
||||
|
||||
**Phase:** E
|
||||
**Status:** 🟡 geplant (Prio 2)
|
||||
|
||||
**Ziel:**
|
||||
Sicherstellung der Konsistenz des Wissensgraphen bei Löschungen oder Umbenennungen von Notizen ("Dangling Edges").
|
||||
|
||||
**Architektur-Idee:**
|
||||
- **Health-Check Script:** Ein Cronjob (`scripts/check_graph_integrity.py`), der alle Kanten prüft, ob ihre `target_id` noch in `mindnet_notes` existiert.
|
||||
- **Report:** Ausgabe von "Broken Links" als Liste für den User.
|
||||
- **Auto-Heal (Optional):** Markieren von defekten Kanten als `broken` statt hartem Löschen.
|
||||
|
||||
**Aufwand / Komplexität:**
|
||||
- Aufwand: Niedrig
|
||||
- Komplexität: Mittel
|
||||
|
||||
---
|
||||
|
||||
### WP-19 – Graph Visualisierung & Explorer (NEU, geplant)
|
||||
|
||||
**Phase:** E
|
||||
**Status:** 🟡 geplant (Prio 1)
|
||||
|
||||
**Ziel:**
|
||||
Schaffung von Vertrauen und Transparenz durch Visualisierung der vom "Smart Chunker" erzeugten Verbindungen.
|
||||
|
||||
**Architektur-Idee:**
|
||||
- **Frontend-Erweiterung:** Neuer Tab "🕸️ Graph" in Streamlit.
|
||||
- **Tech-Stack:** Integration von `streamlit-agraph` oder `pyvis`.
|
||||
- **Feature:** Visualisierung der Nachbarschaft einer Notiz (Ego-Graph) oder eines Suchergebnisses.
|
||||
- **Nutzen:** Schnelle Validierung, ob Smart Edges korrekt gesetzt wurden.
|
||||
|
||||
**Aufwand / Komplexität:**
|
||||
- Aufwand: Mittel
|
||||
- Komplexität: Mittel
|
||||
|
||||
---
|
||||
|
||||
### WP-20 – Cloud Hybrid Mode (Gemini) (NEU, geplant)
|
||||
|
||||
**Phase:** E
|
||||
**Status:** ⚪ optional
|
||||
|
||||
**Ziel:**
|
||||
Optionale Beschleunigung ("Turbo-Modus") für Massen-Imports oder komplexe Analysen durch Nutzung externer High-Performance LLMs (Google Gemini 1.5 Flash), unter Beachtung des Datenschutzes.
|
||||
|
||||
**Architektur-Idee:**
|
||||
- **Provider-Switch:** Erweiterung des `LLMService` um einen Provider-Parameter (`ollama` vs. `gemini`).
|
||||
- **Konfiguration:** `types.yaml` oder `.env` erlaubt Umschalten pro Umgebung (z.B. Dev=Cloud, Prod=Local).
|
||||
- **Privacy:** Warnhinweis im UI, wenn Daten die lokale Umgebung verlassen.
|
||||
|
||||
**Aufwand / Komplexität:**
|
||||
- Aufwand: Mittel
|
||||
- Komplexität: Niedrig
|
||||
|
||||
---
|
||||
|
||||
## 7. Abhängigkeiten (vereinfacht, aktualisiert)
|
||||
|
||||
WP01 → WP02 → WP03 → WP04a
|
||||
WP04a → WP04b → WP04c → WP08
|
||||
WP03 → WP05 → WP06 → WP07
|
||||
WP07 → WP10a
|
||||
WP03 → WP09
|
||||
WP01/WP03 → WP10 → WP11 → WP12
|
||||
WP10 → WP17
|
||||
WP11 → WP15 → WP16
|
||||
WP03/WP04 → WP13
|
||||
Alles → WP14
|
||||
WP01-03 → WP04-06 (Core)
|
||||
WP11 → WP15 (Smart Edges)
|
||||
WP15 → WP19 (Visualisierung - zur Kontrolle)
|
||||
WP15 → WP16 (Auto-Discovery)
|
||||
WP03 → WP18 (Maintenance)
|
||||
WP10 → WP17 (Memory)
|
||||
WP20 (Cloud) ist unabhängig/optional.
|
||||
|
||||
---
|
||||
|
||||
@@ -593,50 +654,26 @@ Erweiterung des Chat-Backends von einem statischen Request-Response-Modell zu ei
|
||||
|
||||
| WP | Aufwand | Komplexität |
|
||||
|-------|----------------|------------------|
|
||||
| WP04b | Mittel | Hoch |
|
||||
| WP04c | Mittel | Mittel/Hoch |
|
||||
| WP05 | Mittel | Mittel |
|
||||
| WP06 | Mittel | Hoch |
|
||||
| WP07 | Niedrig/Mittel | Mittel |
|
||||
| WP08 | Hoch | Hoch |
|
||||
| WP09 | Mittel | Niedrig/Mittel |
|
||||
| WP10 | Hoch | Hoch |
|
||||
| WP10a | Mittel | Mittel |
|
||||
| WP11 | Hoch | Hoch |
|
||||
| WP12 | Niedrig/Mittel | Mittel |
|
||||
| WP13 | Mittel | Mittel |
|
||||
| WP14 | Mittel | Niedrig/Mittel |
|
||||
| WP15 | Mittel | Hoch |
|
||||
| WP16 | Mittel | Hoch |
|
||||
| WP17 | Mittel | Mittel |
|
||||
| WP18 | Niedrig | Mittel |
|
||||
| WP19 | Mittel | Mittel |
|
||||
| WP20 | Mittel | Niedrig |
|
||||
|
||||
---
|
||||
|
||||
## 9. Programmfortschritt (Ampel, aktualisiert)
|
||||
|
||||
| WP | Status |
|
||||
|-------|--------|
|
||||
| WP01 | 🟢 |
|
||||
| WP02 | 🟢 |
|
||||
| WP03 | 🟢 |
|
||||
| WP04a | 🟢 |
|
||||
| WP04b | 🟢 |
|
||||
| WP04c | 🟢 |
|
||||
| WP05 | 🟢 |
|
||||
| WP05b | ⚪ |
|
||||
| WP06 | 🟢 |
|
||||
| WP07 | 🟢 |
|
||||
| WP08 | 🟡 |
|
||||
| WP09 | 🟡 |
|
||||
| WP10 | 🟢 |
|
||||
| WP10a | 🟢 |
|
||||
| WP11 | 🟢 |
|
||||
| WP12 | 🟡 |
|
||||
| WP13 | 🟡 |
|
||||
| WP14 | 🟡 |
|
||||
| WP15 | 🟢 |
|
||||
| WP16 | 🟡 |
|
||||
| WP17 | 🟡 |
|
||||
| WP | Status | Titel |
|
||||
|-------|--------|-------|
|
||||
| WP01-14| 🟢 | (Basis-System) |
|
||||
| WP15 | 🟢 | Smart Edge Allocation |
|
||||
| WP16 | 🟡 | Auto-Discovery |
|
||||
| WP17 | 🟡 | Conversational Memory |
|
||||
| WP18 | 🟡 | Graph Health (Neu) |
|
||||
| WP19 | 🟡 | Visualization (Neu) |
|
||||
| WP20 | ⚪ | Cloud Mode (Neu) |
|
||||
|
||||
---
|
||||
|
||||
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
@@ -194,9 +194,12 @@ Damit das Chaos nicht wächst, löschen wir den fertigen Branch.
|
||||
| Wo? | Befehl | Was tut es? |
|
||||
| :--- | :--- | :--- |
|
||||
| **Beelink** | `sudo systemctl restart mindnet-dev` | **Neustart Dev-Backend (Port 8002).** |
|
||||
| **Beelink** | `sudo systemctl restart mindnet-ui-dev` | **Neustart Dev-Frontend (Port 8002).** |
|
||||
| **Beelink** | `journalctl -u mindnet-dev -f` | **Live-Logs Backend.** |
|
||||
| **Beelink** | `python debug_analysis.py` | **Prüft Aliases & Scores.** |
|
||||
| **Beelink** | `python -m scripts.reset_qdrant ...` | **Löscht & Repariert DB.** |
|
||||
| **Beelink** | `python3 -m scripts.reset_qdrant --mode wipe --prefix "mindnet_dev" --yes` | **Löscht & Repariert DB.** |
|
||||
| **Beelink** | `python3 -m scripts.import_markdown --vault ./vault_master --prefix "mindnet_dev" --apply --force` | **Löscht & Repariert DB.** |
|
||||
| **Beelink** | `source .venv/bin/activate` | **Aktivieren des virtual environments** |
|
||||
|
||||
---
|
||||
|
||||
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
+5
-1
@@ -30,4 +30,8 @@ tqdm>=4.67.1
|
||||
pytest>=8.4.2
|
||||
|
||||
# --- Frontend (WP-10) ---
|
||||
streamlit>=1.39.0
|
||||
streamlit>=1.39.0
|
||||
|
||||
# Visualization (Parallelbetrieb)
|
||||
streamlit-agraph>=0.0.45
|
||||
st-cytoscape
|
||||
@@ -1,90 +0,0 @@
|
||||
{
|
||||
"$schema": "https://json-schema.org/draft/2020-12/schema",
|
||||
"title": "mindnet_chunk",
|
||||
"type": "object",
|
||||
"description": "Chunk-Payload (Qdrant). Kompatibel mit Alt-Feldern und neuen Feldern für Export/Roundtrip.",
|
||||
"required": ["id", "note_id", "chunk_index", "path"],
|
||||
"properties": {
|
||||
"id": { "type": "string" },
|
||||
"scope": { "type": "string", "enum": ["chunk"] },
|
||||
"note_id": { "type": "string" },
|
||||
"note_title": { "type": "string" },
|
||||
"note_type": { "type": "string" },
|
||||
"note_status": { "type": "string" },
|
||||
"type": { "type": "string", "description": "Legacy: früherer Chunk-Typ; kann dem Note-Typ entsprechen" },
|
||||
"area": { "type": "string" },
|
||||
"project": { "type": "string" },
|
||||
"tags": { "type": "array", "items": { "type": "string" } },
|
||||
|
||||
"note_path": { "type": "string" },
|
||||
"path": { "type": "string" },
|
||||
|
||||
"chunk_index": { "type": "integer" },
|
||||
"section_title":{ "type": ["string","null"] },
|
||||
"section_path": { "type": ["string","null"] },
|
||||
|
||||
"char_start": { "type": ["integer","null"] },
|
||||
"char_end": { "type": ["integer","null"] },
|
||||
"char_len": { "type": "integer" },
|
||||
|
||||
"token_count": { "type": "integer", "description": "Legacy: frühere Token-Zahl" },
|
||||
"token_est": { "type": "integer", "description": "Neue grobe Token-Schätzung (≈ len(text)/4)" },
|
||||
|
||||
"neighbors": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"prev": { "type": ["string","null"] },
|
||||
"next": { "type": ["string","null"] }
|
||||
},
|
||||
"additionalProperties": false
|
||||
},
|
||||
|
||||
"text": { "type": "string" },
|
||||
"text_sha256": { "type": "string", "pattern": "^sha256:[0-9a-fA-F]{64}$" },
|
||||
"lang": { "type": "string" },
|
||||
|
||||
"wikilinks": { "type": "array", "items": { "type": "string" } },
|
||||
"external_links": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"anyOf": [
|
||||
{ "type": "string" },
|
||||
{
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"href": { "type": "string" },
|
||||
"label": { "type": ["string","null"] }
|
||||
},
|
||||
"required": ["href"],
|
||||
"additionalProperties": false
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"references": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"target_id": { "type": "string" },
|
||||
"kind": { "type": "string" }
|
||||
},
|
||||
"required": ["target_id","kind"],
|
||||
"additionalProperties": true
|
||||
}
|
||||
},
|
||||
|
||||
"embed_model": { "type": "string" },
|
||||
"embed_dim": { "type": "integer" },
|
||||
"embed_version": { "type": "integer" },
|
||||
|
||||
"created_at": { "type": "string" }
|
||||
},
|
||||
|
||||
"allOf": [
|
||||
{ "anyOf": [ { "required": ["token_count"] }, { "required": ["token_est"] } ] },
|
||||
{ "anyOf": [ { "required": ["type"] }, { "required": ["note_type"] } ] }
|
||||
],
|
||||
|
||||
"additionalProperties": true
|
||||
}
|
||||
@@ -1,31 +0,0 @@
|
||||
{
|
||||
"$schema": "https://json-schema.org/draft/2020-12/schema",
|
||||
"title": "mindnet_edge",
|
||||
"type": "object",
|
||||
"description": "Edge-Payload (Qdrant). Unterstützt Legacy (edge_type/src_id/dst_id) und neues Schema (kind/source_id/target_id/note_id/status).",
|
||||
|
||||
"properties": {
|
||||
"scope": { "type": "string", "enum": ["note","chunk"] },
|
||||
|
||||
"edge_type": { "type": "string", "description": "Legacy: z. B. references/backlink/belongs_to/prev/next" },
|
||||
"src_id": { "type": "string", "description": "Legacy: source_id" },
|
||||
"dst_id": { "type": "string", "description": "Legacy: target_id" },
|
||||
|
||||
"kind": { "type": "string", "description": "Neu: z. B. references/backlink/belongs_to/prev/next" },
|
||||
"source_id": { "type": "string" },
|
||||
"target_id": { "type": "string" },
|
||||
"note_id": { "type": "string", "description": "Owner-Note für diesen Edge (Filter/Purge)" },
|
||||
"status": { "type": "string", "description": "optional, z. B. 'unresolved'" },
|
||||
|
||||
"weight": { "type": "number" },
|
||||
"meta": { "type": "object" },
|
||||
"created_at":{ "type": "string" }
|
||||
},
|
||||
|
||||
"anyOf": [
|
||||
{ "required": ["src_id", "dst_id", "edge_type", "scope"] },
|
||||
{ "required": ["source_id", "target_id", "kind", "scope"] }
|
||||
],
|
||||
|
||||
"additionalProperties": true
|
||||
}
|
||||
Loaded 100 of 102 files, more files were not shown because too many files have changed in this diff.
Show more
Reference in new issue
Block a user