533 lines
20 KiB
Python
533 lines
20 KiB
Python
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 ---
|
||
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;
|
||
}
|
||
</style>
|
||
""", unsafe_allow_html=True)
|
||
|
||
# --- 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 ---
|
||
|
||
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 ---
|
||
mode, top_k, explain = render_sidebar()
|
||
if mode == "💬 Chat":
|
||
render_chat_interface(top_k, explain)
|
||
else:
|
||
render_manual_editor() |