This commit is contained in:
1 parent
e93bab6ea7
commit
876ee898d8
2 files changed
+185
-101
No files matched your search
@@ -78,7 +78,7 @@ class GraphExplorerService:
|
||||
# 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
|
||||
orig_title = getattr(nodes_dict[center_note_id], 'title', None) or getattr(nodes_dict[center_note_id], 'label', '')
|
||||
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}..."
|
||||
@@ -91,7 +91,8 @@ class GraphExplorerService:
|
||||
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}..."
|
||||
current_title = getattr(node_obj, 'title', None) or getattr(node_obj, 'label', '')
|
||||
node_obj.title = f"{current_title}\n\n🔍 VORSCHAU:\n{clean_prev}..."
|
||||
|
||||
# Graphen bauen (Nodes & Edges finalisieren)
|
||||
final_edges = []
|
||||
@@ -167,27 +168,28 @@ class GraphExplorerService:
|
||||
|
||||
results = []
|
||||
|
||||
if not note_ids:
|
||||
return 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)
|
||||
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 erhöht, um alle Kanten zu finden
|
||||
res_out, _ = self.client.scroll(self.edges_col, scroll_filter=out_filter, limit=2000, 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 der aktuellen Notes holen (Limit erhöht)
|
||||
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]
|
||||
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=1000, with_payload=False)
|
||||
chunk_ids = [c.id for c in chunks]
|
||||
|
||||
shoulds = []
|
||||
# Case A: Edge zeigt auf einen unserer Chunks
|
||||
@@ -195,42 +197,66 @@ class GraphExplorerService:
|
||||
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)))
|
||||
shoulds.append(models.FieldCondition(key="target_id", match=models.MatchAny(any=note_ids)))
|
||||
|
||||
# Case C: Edge zeigt auf unseren Titel (Wikilinks)
|
||||
# Case C: Edge zeigt auf unseren Titel (Wikilinks) - auch wenn note_title None ist, versuchen wir es mit den Titeln der Notes
|
||||
if note_title:
|
||||
shoulds.append(models.FieldCondition(key="target_id", match=models.MatchValue(value=note_title)))
|
||||
else:
|
||||
# Fallback: Lade Titel der Notes, wenn note_title nicht übergeben wurde
|
||||
for nid in note_ids:
|
||||
note = self._fetch_note_cached(nid)
|
||||
if note and note.get("title"):
|
||||
shoulds.append(models.FieldCondition(key="target_id", match=models.MatchValue(value=note.get("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)
|
||||
# Limit erhöht, um alle eingehenden Kanten zu finden
|
||||
res_in, _ = self.client.scroll(self.edges_col, scroll_filter=in_filter, limit=2000, 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)
|
||||
# Wrapper für Level 2 Suche - lade Titel für alle Notes
|
||||
note_titles = []
|
||||
for nid in note_ids:
|
||||
note = self._fetch_note_cached(nid)
|
||||
if note and note.get("title"):
|
||||
note_titles.append(note.get("title"))
|
||||
# Verwende den ersten Titel als Fallback (oder None, wenn keine gefunden)
|
||||
title = note_titles[0] if note_titles else None
|
||||
return self._find_connected_edges(note_ids, note_title=title)
|
||||
|
||||
def _process_edge(self, record, nodes_dict, unique_edges, current_depth):
|
||||
"""Verarbeitet eine rohe Edge, löst IDs auf und fügt sie den Dictionaries hinzu."""
|
||||
if not record or not record.payload:
|
||||
return None, None
|
||||
|
||||
payload = record.payload
|
||||
src_ref = payload.get("source_id")
|
||||
tgt_ref = payload.get("target_id")
|
||||
kind = payload.get("kind")
|
||||
provenance = payload.get("provenance", "explicit")
|
||||
|
||||
# Prüfe, ob beide Referenzen vorhanden sind
|
||||
if not src_ref or not tgt_ref:
|
||||
return None, None
|
||||
|
||||
# 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']
|
||||
src_id = src_note.get('note_id')
|
||||
tgt_id = tgt_note.get('note_id')
|
||||
|
||||
# Prüfe, ob beide IDs vorhanden sind
|
||||
if not src_id or not tgt_id:
|
||||
return None, None
|
||||
|
||||
if src_id != tgt_id:
|
||||
# Nodes hinzufügen
|
||||
@@ -245,7 +271,7 @@ class GraphExplorerService:
|
||||
# Bevorzuge explizite Kanten vor Smart Kanten
|
||||
is_current_explicit = (provenance in ["explicit", "rule"])
|
||||
if existing:
|
||||
is_existing_explicit = (existing['provenance'] in ["explicit", "rule"])
|
||||
is_existing_explicit = (existing.get('provenance', '') in ["explicit", "rule"])
|
||||
if is_existing_explicit and not is_current_explicit:
|
||||
should_update = False
|
||||
|
||||
@@ -275,25 +301,49 @@ class GraphExplorerService:
|
||||
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
|
||||
if res and res[0].payload:
|
||||
note_id = res[0].payload.get("note_id")
|
||||
if note_id:
|
||||
note = self._fetch_note_cached(note_id)
|
||||
if note: return note
|
||||
except Exception:
|
||||
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)
|
||||
note = self._fetch_note_cached(possible_note_id)
|
||||
if note: return note
|
||||
|
||||
# Fall B: Note ID direkt
|
||||
if self._fetch_note_cached(ref_str): return self._fetch_note_cached(ref_str)
|
||||
note = self._fetch_note_cached(ref_str)
|
||||
if note: return note
|
||||
|
||||
# Fall C: Titel (exakte Übereinstimmung)
|
||||
try:
|
||||
res, _ = self.client.scroll(
|
||||
collection_name=self.notes_col,
|
||||
scroll_filter=models.Filter(must=[models.FieldCondition(key="title", match=models.MatchValue(value=str(ref_str)))]),
|
||||
limit=1, with_payload=True
|
||||
)
|
||||
if res and res[0].payload:
|
||||
self._note_cache[res[0].payload['note_id']] = res[0].payload
|
||||
return res[0].payload
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
# Fall D: Titel (Text-Suche für Fuzzy-Matching, falls exakte Suche fehlschlägt)
|
||||
try:
|
||||
res, _ = self.client.scroll(
|
||||
collection_name=self.notes_col,
|
||||
scroll_filter=models.Filter(must=[models.FieldCondition(key="title", match=models.MatchText(text=str(ref_str)))]),
|
||||
limit=1, with_payload=True
|
||||
)
|
||||
if res and res[0].payload:
|
||||
self._note_cache[res[0].payload['note_id']] = res[0].payload
|
||||
return res[0].payload
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
# 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):
|
||||
|
||||
Reference in new issue
Block a user