Lars/mindnet
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 21 Wiki Activity

WP11 #8

Merged
Lars merged 30 commits from WP11 into main 2025-12-11 17:00:38 +01:00
Conversation 0 Commits 30 Files Changed 24 +43 -29
4 changed files with 43 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files
Showing only changes of commit 565d34fb7b - Show all commits

12
app/core/note_payload.py
View File

@ -2,7 +2,7 @@
# -*- coding: utf-8 -*-
"""
Modul: app/core/note_payload.py
Version: 2.0.0
Version: 2.1.0 (WP-11 Update: Aliases support)
Zweck
-----
@ -145,6 +145,7 @@ def make_note_payload(note: Any, *args, **kwargs) -> Dict[str, Any]:
- 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)
"""
n = _as_dict(note)
path_arg, types_cfg_explicit = _pick_args(*args, **kwargs)
@ -214,12 +215,21 @@ def make_note_payload(note: Any, *args, **kwargs) -> Dict[str, Any]:
if tags:
payload["tags"] = _ensure_list(tags)
# WP-11: Aliases übernehmen (für Discovery Service)
aliases = fm.get("aliases")
if aliases:
payload["aliases"] = _ensure_list(aliases)
# Zeitliche Metadaten (sofern vorhanden)
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)
if "body" in n and n["body"]:
payload["fulltext"] = str(n["body"])
# JSON-Roundtrip zur harten Validierung (ASCII beibehalten)
json.loads(json.dumps(payload, ensure_ascii=False))

6
app/main.py
View File

@ -11,8 +11,8 @@ from .routers.query import router as query_router
from .routers.graph import router as graph_router
from .routers.tools import router as tools_router
from .routers.feedback import router as feedback_router
# NEU: Chat Router (WP-05)
from .routers.chat import router as chat_router
# NEU: Ingest Router (WP-11)
from .routers.ingest import router as ingest_router
@ -36,9 +36,11 @@ def create_app() -> FastAPI:
app.include_router(graph_router, prefix="/graph", tags=["graph"])
app.include_router(tools_router, prefix="/tools", tags=["tools"])
app.include_router(feedback_router, prefix="/feedback", tags=["feedback"])
# NEU: Chat Endpoint
app.include_router(chat_router, prefix="/chat", tags=["chat"])
# NEU: Registrierung des Ingest-Routers
# NEU: Ingest Endpoint
app.include_router(ingest_router, prefix="/ingest", tags=["ingest"])
if admin_router:

14
app/routers/ingest.py
View File

@ -21,8 +21,8 @@ class AnalyzeRequest(BaseModel):
class SaveRequest(BaseModel):
markdown_content: str
filename: Optional[str] = None # Optional, fallback auf Timestamp/Titel
folder: str = "00_Inbox" # Zielordner im Vault
filename: Optional[str] = None # Optional, fallback auf Timestamp
folder: str = "00_Inbox" # Zielordner
class SaveResponse(BaseModel):
status: str
@ -31,7 +31,6 @@ class SaveResponse(BaseModel):
stats: Dict[str, Any]
# --- Services ---
# Instanzierung hier oder via Dependency Injection
discovery_service = DiscoveryService()
@router.post("/analyze")
@ -53,8 +52,10 @@ async def save_note(req: SaveRequest):
# 1. Vault Root ermitteln
vault_root = os.getenv("MINDNET_VAULT_ROOT", "./vault")
if not os.path.exists(vault_root):
# Fallback für Dev-Umgebungen
if os.path.exists("../vault"):
# Fallback relative paths
if os.path.exists("vault"):
vault_root = "vault"
elif os.path.exists("../vault"):
vault_root = "../vault"
else:
raise HTTPException(status_code=500, detail="Vault root not configured or missing")
@ -62,11 +63,10 @@ async def save_note(req: SaveRequest):
# 2. Filename generieren falls fehlend
final_filename = req.filename
if not final_filename:
# Einfacher Fallback: Timestamp
final_filename = f"draft_{int(time.time())}.md"
# 3. Ingestion Service nutzen
ingest_service = IngestionService() # nutzt Default-Prefix oder aus Env
ingest_service = IngestionService()
result = ingest_service.create_from_text(
markdown_content=req.markdown_content,

36
app/services/discovery.py
View File

@ -1,7 +1,6 @@
"""
app/services/discovery.py
Service für Link-Vorschläge und Knowledge-Discovery (WP-11).
Analysiert Drafts auf Keywords und semantische Ähnlichkeiten.
"""
import logging
from typing import List, Dict, Any, Set
@ -14,21 +13,21 @@ from app.core.retriever import hybrid_retrieve
logger = logging.getLogger(__name__)
class DiscoveryService:
def __init__(self, collection_prefix: str = "mindnet"):
self.prefix = collection_prefix
def __init__(self, collection_prefix: str = None):
self.cfg = QdrantConfig.from_env()
self.cfg.prefix = collection_prefix
# Prefix Priorität: Argument > Env > Default
self.prefix = collection_prefix or self.cfg.prefix or "mindnet"
self.client = get_client(self.cfg)
async def analyze_draft(self, text: str, current_type: str) -> Dict[str, Any]:
"""
Analysiert einen Draft-Text und schlägt Verlinkungen vor.
Kombiniert Exact Match (Titel) und Semantic Match (Vektor).
Kombiniert Exact Match (Titel/Alias) und Semantic Match (Vektor).
"""
suggestions = []
# 1. Exact Match: Finde Begriffe im Text, die als Notiz-Titel existieren
# (Bei sehr großen Vaults >10k sollte dies gecached werden)
# (Holt alle Titel aus Qdrant - bei riesigen Vaults später cachen)
known_entities = self._fetch_all_titles_and_aliases()
found_entities = self._find_entities_in_text(text, known_entities)
@ -42,23 +41,23 @@ class DiscoveryService:
"target_title": entity["title"],
"target_id": entity["id"],
"confidence": 1.0,
"reason": "Existierender Notiz-Titel"
"reason": "Existierender Notiz-Titel/Alias"
})
# 2. Semantic Match: Finde inhaltlich ähnliche Notizen via Vektor-Suche
# Wir filtern Ergebnisse heraus, die wir schon per Exact Match gefunden haben.
semantic_hits = self._get_semantic_suggestions(text)
for hit in semantic_hits:
# Duplikate vermeiden (wenn wir es schon per Titel gefunden haben)
if hit.node_id in existing_target_ids:
continue
# Schwellwert: Nur relevante Vorschläge anzeigen (z.B. > 0.65)
# Wir nutzen den total_score, der bereits Typ-Gewichte enthält.
# Schwellwert: Nur relevante Vorschläge
# total_score beinhaltet bereits Typ-Gewichte aus dem Retriever
if hit.total_score > 0.65:
suggestions.append({
"type": "semantic_match",
"text_found": (hit.source.get("text") or "")[:50] + "...", # Snippet
"text_found": (hit.source.get("text") or "")[:50] + "...",
"target_title": hit.payload.get("title", "Unbekannt"),
"target_id": hit.node_id,
"confidence": round(hit.total_score, 2),
@ -79,7 +78,6 @@ class DiscoveryService:
try:
while True:
# Scroll API nutzen, um effizient alle Metadaten zu laden
res, next_page = self.client.scroll(
collection_name=col_name,
limit=1000,
@ -89,10 +87,15 @@ class DiscoveryService:
)
for point in res:
pl = point.payload or {}
# Aliases robust lesen
aliases = pl.get("aliases") or []
if isinstance(aliases, str): aliases = [aliases]
notes.append({
"id": pl.get("note_id"),
"title": pl.get("title"),
"aliases": pl.get("aliases", [])
"aliases": aliases
})
if next_page is None:
@ -105,7 +108,7 @@ class DiscoveryService:
def _find_entities_in_text(self, text: str, entities: List[Dict]) -> List[Dict]:
"""
Sucht Vorkommen von Titeln im Text (Case-Insensitive).
Sucht Vorkommen von Titeln/Alias im Text (Case-Insensitive).
"""
found = []
text_lower = text.lower()
@ -119,7 +122,7 @@ class DiscoveryService:
"title": title,
"id": entity["id"]
})
continue # Wenn Titel gefunden, Aliases nicht mehr prüfen (Prio)
continue # Wenn Titel gefunden, Aliases nicht mehr prüfen
# 2. Aliases prüfen
aliases = entity.get("aliases")
@ -136,14 +139,13 @@ class DiscoveryService:
def _get_semantic_suggestions(self, text: str):
"""Wrapper um den Hybrid Retriever."""
# Wir nutzen eine vereinfachte Query
req = QueryRequest(
query=text,
top_k=5,
explain=False
)
try:
# hybrid_retrieve ist sync, wird aber schnell genug sein für diesen Kontext
# hybrid_retrieve nutzen (sync Wrapper)
res = hybrid_retrieve(req)
return res.results
except Exception as e: