diff --git a/scripts/import_markdown.py b/scripts/import_markdown.py index b1288df..fea52de 100644 --- a/scripts/import_markdown.py +++ b/scripts/import_markdown.py @@ -3,47 +3,42 @@ """ scripts/import_markdown.py -Zweck ------ -- Liest Markdown-Notizen aus einem Vault ein -- Erzeugt Note-Payload, Chunk-Payloads (+ optionale Embeddings) und Edges -- Schreibt alles idempotent in Qdrant (Notes, Chunks, Edges) -- Integriert eine optionale Type-Registry (types.yaml), um z. B. chunk_profile - und retriever_weight pro Notiz-Typ zu steuern. +Purpose +------- +Import Markdown notes from a vault into Qdrant with idempotent upserts. +This version fixes the issue where `retriever_weight` for *notes* did not +reflect the values from `types.yaml`. It does so by building the note payload +from a dict containing the normalized frontmatter, and by ensuring the +Type‑Registry is loaded via ENV (`MINDNET_TYPES_FILE`, default: ./config/types.yaml). -Wesentliche Fixes ggü. vorherigen fehlerhaften Ständen ------------------------------------------------------- -- `embed_texts` wird optional importiert und defensiv geprüft (kein NameError mehr) -- `effective_chunk_profile` / `effective_retriever_weight` und Registry-Helfer - sind VOR `main()` definiert (kein NameError mehr) -- `retriever_weight` wird in Note- und Chunk-Payload zuverlässig gesetzt -- Robuste Kantenbildung; Fehler bei Edges blockieren Notes/Chunks nicht -- Korrekte Verwendung von `scroll_filter` beim Qdrant-Client -- `--purge-before-upsert` entfernt alte Chunks/Edges einer Note vor dem Upsert +Key behaviors +------------- +- Deterministic, idempotent upserts for notes / chunks / edges +- Optional embeddings for chunks +- Optional sync‑deletes (vault → Qdrant) +- Ensures collections and payload indices exist +- Honors `retriever_weight` and `chunk_profile` from types.yaml for both notes and chunks -Qdrant / ENV +CLI examples ------------ -- QDRANT_URL | QDRANT_HOST/QDRANT_PORT | QDRANT_API_KEY -- COLLECTION_PREFIX (Default: mindnet), via --prefix überschreibbar -- VECTOR_DIM (Default: 384) -- MINDNET_NOTE_SCOPE_REFS: true|false (Default: false) -- MINDNET_TYPES_FILE: Pfad zu types.yaml (optional; Default: ./types.yaml) + # Apply + purge + python3 -m scripts.import_markdown --vault ./vault --apply --purge-before-upsert --prefix "$COLLECTION_PREFIX" -Beispiele ---------- - # Standard (Body, parsed, canonical) - python3 -m scripts.import_markdown --vault ./vault - - # Erstimport nach truncate (Create-Fall) - python3 -m scripts.import_markdown --vault ./vault --apply --purge-before-upsert - - # Nur eine Datei (Diagnose) - python3 -m scripts.import_markdown --vault ./vault --only-path ./vault/30_projects/project-demo.md --apply - - # Sync-Deletes (Dry-Run → Apply) + # Sync-Deletes (dry-run then apply) python3 -m scripts.import_markdown --vault ./vault --sync-deletes python3 -m scripts.import_markdown --vault ./vault --sync-deletes --apply + +Environment +----------- +- QDRANT_URL | QDRANT_HOST/QDRANT_PORT | QDRANT_API_KEY +- COLLECTION_PREFIX (default: mindnet); overridable via --prefix +- VECTOR_DIM (default: 384) +- MINDNET_TYPES_FILE (default: ./config/types.yaml) +- MINDNET_NOTE_SCOPE_REFS=true|false (default: false) +- MINDNET_HASH_SOURCE=parsed|raw (default: parsed) +- MINDNET_HASH_NORMALIZE=canonical|none (default: canonical) """ + from __future__ import annotations import argparse @@ -55,19 +50,19 @@ from typing import Dict, List, Optional, Tuple, Any, Set from dotenv import load_dotenv from qdrant_client.http import models as rest -# --- Projekt-Imports --- +# --- Project imports --- from app.core.parser import ( read_markdown, normalize_frontmatter, validate_required_frontmatter, ) from app.core.note_payload import make_note_payload -from app.core.chunker import assemble_chunks from app.core.chunk_payload import make_chunk_payloads try: from app.core.derive_edges import build_edges_for_note except Exception: # pragma: no cover from app.core.edges import build_edges_for_note # type: ignore + from app.core.qdrant import ( QdrantConfig, get_client, @@ -81,227 +76,162 @@ from app.core.qdrant_points import ( upsert_batch, ) -# embeddings sind optional (z. B. im reinen Payload-Backfill) +# embeddings optional try: - from app.core.embed import embed_texts # optional + from app.core.embed import embed_texts except Exception: # pragma: no cover embed_texts = None -# --------------------------------------------------------------------- -# Type-Registry (types.yaml) – Helper (robust, optional) -# --------------------------------------------------------------------- +# ---------------------- helpers ---------------------- -def _env(name: str, default: Optional[str] = None) -> Optional[str]: - v = os.getenv(name) - return v if v is not None else default +def _env(name: str, default: Optional[str] = None) -> str: + v = os.getenv(name, default if default is not None else "") + return v if v is not None else "" -def _load_json_or_yaml(path: str) -> dict: - import io - data: dict = {} - if not path or not os.path.exists(path): - return data - try: - import yaml # type: ignore - with io.open(path, "r", encoding="utf-8") as f: - data = yaml.safe_load(f) or {} - if not isinstance(data, dict): - return {} - return data - except Exception: - # YAML evtl. nicht installiert – versuche JSON - try: - with io.open(path, "r", encoding="utf-8") as f: - data = json.load(f) - if not isinstance(data, dict): - return {} - return data - except Exception: - return {} +def _resolve_mode(val: Optional[str]) -> str: + v = (val or _env("MINDNET_HASH_COMPARE", "body")).strip().lower() + return v if v in ("body","frontmatter","full") else "body" -def load_type_registry() -> dict: - # Reihenfolge: ENV > ./types.yaml (im aktuellen Arbeitsverzeichnis) - p = _env("MINDNET_TYPES_FILE", None) - if p and os.path.exists(p): - return _load_json_or_yaml(p) - fallback = os.path.abspath("./types.yaml") - return _load_json_or_yaml(fallback) - -def get_type_config(note_type: Optional[str], reg: dict) -> dict: - if not reg or not isinstance(reg, dict): - return {} - types = reg.get("types", {}) if isinstance(reg.get("types"), dict) else {} - if note_type and isinstance(note_type, str) and note_type in types: - return types[note_type] or {} - # Fallback: concept - return types.get("concept", {}) or {} - -def resolve_note_type(requested: Optional[str], reg: dict) -> str: - if requested and isinstance(requested, str): - return requested - # Fallback wenn nichts gesetzt ist - types = reg.get("types", {}) if isinstance(reg.get("types"), dict) else {} - return "concept" if "concept" in types else (requested or "concept") - -def effective_chunk_profile(note_type: str, reg: dict) -> Optional[str]: - cfg = get_type_config(note_type, reg) - prof = cfg.get("chunk_profile") - if isinstance(prof, str) and prof in {"short", "medium", "long"}: - return prof - return None - -def effective_retriever_weight(note_type: str, reg: dict) -> Optional[float]: - cfg = get_type_config(note_type, reg) - w = cfg.get("retriever_weight") - try: - return float(w) if w is not None else None - except Exception: - return None - - -# --------------------------------------------------------------------- -# Sonstige Helper -# --------------------------------------------------------------------- - -def iter_md(root: str) -> List[str]: - out: List[str] = [] +def _iter_md(root: str) -> List[str]: + files: List[str] = [] for dirpath, _, filenames in os.walk(root): for fn in filenames: - if not fn.lower().endswith(".md"): - continue - p = os.path.join(dirpath, fn) - pn = p.replace("\\", "/") - if any(ex in pn for ex in ["/.obsidian/", "/_backup_frontmatter/", "/_imported/"]): - continue - out.append(p) - return sorted(out) + if fn.lower().endswith(".md"): + files.append(os.path.join(dirpath, fn)) + files.sort() + return files -def collections(prefix: str) -> Tuple[str, str, str]: - return f"{prefix}_notes", f"{prefix}_chunks", f"{prefix}_edges" +def _types_file_default() -> str: + # default to ./config/types.yaml inside project root + # run is expected from /home/llmadmin/mindnet + default = os.path.abspath("./config/types.yaml") + return _env("MINDNET_TYPES_FILE", default) -def fetch_existing_note_payload(client, prefix: str, note_id: str) -> Optional[Dict]: - notes_col, _, _ = collections(prefix) - f = rest.Filter(must=[rest.FieldCondition(key="note_id", match=rest.MatchValue(value=note_id))]) - points, _ = client.scroll( - collection_name=notes_col, - scroll_filter=f, # wichtig: scroll_filter (nicht: filter) - with_payload=True, - with_vectors=False, - limit=1, - ) - if not points: +def load_type_registry() -> Dict[str, Any]: + import yaml # local import + path = _types_file_default() + try: + with open(path, "r", encoding="utf-8") as f: + data = yaml.safe_load(f) or {} + t = data.get("types") or {} + return t if isinstance(t, dict) else {} + except Exception: + return {} + +def resolve_note_type(note_type: Optional[str], reg: Dict[str, Any]) -> str: + if not note_type: + return "concept" + s = str(note_type).strip() + return s if s in reg else s # allow free types if not configured + +def effective_chunk_profile(note_type: str, reg: Dict[str, Any]) -> Optional[str]: + try: + v = reg.get(note_type, {}).get("chunk_profile") + return str(v) if v is not None else None + except Exception: + return None + +def effective_retriever_weight(note_type: str, reg: Dict[str, Any]) -> Optional[float]: + try: + v = reg.get(note_type, {}).get("retriever_weight") + return float(v) if v is not None else None + except Exception: return None - return points[0].payload or {} def list_qdrant_note_ids(client, prefix: str) -> Set[str]: - notes_col, _, _ = collections(prefix) + """Collect all note_ids from Qdrant mindnet_notes payloads.""" + from qdrant_client import QdrantClient + notes = f"{prefix}_notes" out: Set[str] = set() - next_page = None + # scroll with page size + offset = None while True: - pts, next_page = client.scroll( - collection_name=notes_col, - with_payload=True, - with_vectors=False, - limit=256, - offset=next_page, - ) - if not pts: - break + res = client.scroll(collection_name=notes, with_payload=True, with_vectors=False, limit=2048, offset=offset) + pts = getattr(res, "points", None) or res[0] # API compatibility + next_off = getattr(res, "next_page_offset", None) or res[1] for p in pts: - pl = p.payload or {} - nid = pl.get("note_id") + pl = getattr(p, "payload", {}) or {} + nid = pl.get("note_id") or pl.get("id") if isinstance(nid, str): out.add(nid) - if next_page is None: + if not next_off: break + offset = next_off return out +def fetch_existing_note_payload(client, prefix: str, note_id: str) -> Optional[Dict[str, Any]]: + notes = f"{prefix}_notes" + flt = rest.Filter(must=[rest.FieldCondition(key="note_id", match=rest.MatchValue(value=note_id))]) + sr = client.scroll(collection_name=notes, with_payload=True, with_vectors=False, limit=1, scroll_filter=flt) + pts = getattr(sr, "points", None) or sr[0] + if not pts: + return None + return getattr(pts[0], "payload", None) or None + def purge_note_artifacts(client, prefix: str, note_id: str) -> None: - _, chunks_col, edges_col = collections(prefix) - filt = rest.Filter(must=[rest.FieldCondition(key="note_id", match=rest.MatchValue(value=note_id))]) - for col in (chunks_col, edges_col): - try: - client.delete( - collection_name=col, - points_selector=rest.FilterSelector(filter=filt), - wait=True - ) - except Exception as e: - print(json.dumps({"note_id": note_id, "warn": f"delete in {col} via filter failed: {e}"})) + """Delete old chunks/edges for a note (idempotent).""" + chunks = f"{prefix}_chunks" + edges = f"{prefix}_edges" + flt_note = rest.Filter(must=[rest.FieldCondition(key="note_id", match=rest.MatchValue(value=note_id))]) + try: + client.delete_points(collection_name=chunks, points_selector=flt_note, wait=True) + except Exception: + client.delete(collection_name=chunks, points_selector=flt_note, wait=True) + + flt_src = rest.Filter(should=[ + rest.FieldCondition(key="source_id", match=rest.MatchValue(value=note_id)), + rest.FieldCondition(key="target_id", match=rest.MatchValue(value=note_id)), + rest.FieldCondition(key="note_id", match=rest.MatchValue(value=note_id)), + ]) + try: + client.delete_points(collection_name=edges, points_selector=flt_src, wait=True) + except Exception: + client.delete(collection_name=edges, points_selector=flt_src, wait=True) def delete_note_everywhere(client, prefix: str, note_id: str) -> None: - notes_col, chunks_col, edges_col = collections(prefix) - filt = rest.Filter(must=[rest.FieldCondition(key="note_id", match=rest.MatchValue(value=note_id))]) - for col in (edges_col, chunks_col, notes_col): - try: - client.delete( - collection_name=col, - points_selector=rest.FilterSelector(filter=filt), - wait=True - ) - except Exception as e: - print(json.dumps({"note_id": note_id, "warn": f"delete in {col} failed: {e}"})) + """Delete note + artifacts (chunks/edges).""" + notes = f"{prefix}_notes" + purge_note_artifacts(client, prefix, note_id) + flt = rest.Filter(must=[rest.FieldCondition(key="note_id", match=rest.MatchValue(value=note_id))]) + try: + client.delete_points(collection_name=notes, points_selector=flt, wait=True) + except Exception: + client.delete(collection_name=notes, points_selector=flt, wait=True) -# --- Neu: Existenz-Checks für Artefakte (fehlertoleranter Rebuild) --- - -def _has_any_point(client, collection: str, note_id: str) -> bool: - """Prüft, ob es mind. einen Punkt mit note_id in der Collection gibt.""" - filt = rest.Filter(must=[rest.FieldCondition(key="note_id", match=rest.MatchValue(value=note_id))]) - pts, _ = client.scroll( - collection_name=collection, - scroll_filter=filt, - with_payload=False, - with_vectors=False, - limit=1, - ) - return bool(pts) - -def artifacts_missing(client, prefix: str, note_id: str) -> Tuple[bool, bool]: - """Gibt (chunks_missing, edges_missing) zurück.""" - _, chunks_col, edges_col = collections(prefix) - chunks_missing = not _has_any_point(client, chunks_col, note_id) - edges_missing = not _has_any_point(client, edges_col, note_id) - return chunks_missing, edges_missing - - -# --------------------------------------------------------------------- -# Main -# --------------------------------------------------------------------- - -def _resolve_mode(m: Optional[str]) -> str: - m = (m or "body").strip().lower() - return m if m in {"body", "frontmatter", "full"} else "body" +# ---------------------- main ---------------------- def main() -> None: load_dotenv() - ap = argparse.ArgumentParser( - prog="scripts.import_markdown", - description="Importiert Markdown-Notizen in Qdrant (Notes/Chunks/Edges)." - ) - ap.add_argument("--vault", required=True, help="Pfad zum Vault (Ordner mit .md-Dateien)") - ap.add_argument("--only-path", help="Nur diese Datei verarbeiten (absolut oder relativ)") - ap.add_argument("--apply", action="store_true", help="Schreibt nach Qdrant (sonst Dry-Run)") - ap.add_argument("--purge-before-upsert", action="store_true", help="Alte Chunks/Edges der Note vorher löschen") - ap.add_argument("--force-replace", action="store_true", help="Note/Chunks/Edges unabhängig von Hash neu schreiben") - ap.add_argument("--note-id", help="Nur Notes mit dieser ID verarbeiten (Filter)") - ap.add_argument("--note-scope-refs", action="store_true", help="Note-scope References/Backlinks erzeugen") - ap.add_argument("--hash-mode", help="body|frontmatter|full (Default body)") - ap.add_argument("--hash-source", help="parsed|raw (Default parsed)") - ap.add_argument("--hash-normalize", help="canonical|none (Default canonical)") - ap.add_argument("--compare-text", action="store_true", help="Parsed fulltext zusätzlich direkt vergleichen") - ap.add_argument("--baseline-modes", action="store_true", help="Fehlende Hash-Varianten still nachtragen (Notes)") - ap.add_argument("--sync-deletes", action="store_true", help="Qdrant->Vault Lösch-Sync (Dry-Run; mit --apply ausführen)") - ap.add_argument("--prefix", help="Collection-Prefix (überschreibt ENV COLLECTION_PREFIX)") + ap = argparse.ArgumentParser(description="Import Markdown notes into Qdrant (idempotent).") + ap.add_argument("--vault", required=True, help="Path to the vault (folder with .md files)") + ap.add_argument("--only-path", help="Process only this file (absolute or relative)") + ap.add_argument("--apply", action="store_true", help="Write to Qdrant (otherwise dry-run)") + ap.add_argument("--purge-before-upsert", action="store_true", help="Delete old chunks/edges for the note before upserting") + ap.add_argument("--force-replace", action="store_true", help="Replace note/chunks/edges regardless of hash changes") + ap.add_argument("--note-id", help="Process only notes with this id") + ap.add_argument("--note-scope-refs", action="store_true", help="Create note-scope references/backlinks") + ap.add_argument("--hash-mode", help="body|frontmatter|full (default body)") + ap.add_argument("--hash-source", help="parsed|raw (default parsed)") + ap.add_argument("--hash-normalize", help="canonical|none (default canonical)") + ap.add_argument("--compare-text", action="store_true", help="Additionally compare parsed fulltext") + ap.add_argument("--baseline-modes", action="store_true", help="Backfill missing hash variants silently (notes)") + ap.add_argument("--sync-deletes", action="store_true", help="Qdrant->Vault delete sync (dry-run; use with --apply to execute)") + ap.add_argument("--prefix", help="Collection prefix (overrides ENV COLLECTION_PREFIX)") args = ap.parse_args() + # Ensure default types path if not provided via ENV + if not os.getenv("MINDNET_TYPES_FILE"): + os.environ["MINDNET_TYPES_FILE"] = _types_file_default() + mode = _resolve_mode(args.hash_mode) # body|frontmatter|full src = _env("MINDNET_HASH_SOURCE", args.hash_source or "parsed") # parsed|raw norm = _env("MINDNET_HASH_NORMALIZE", args.hash_normalize or "canonical") # canonical|none - note_scope_refs_env = (_env("MINDNET_NOTE_SCOPE_REFS", "false") == "true") + note_scope_refs_env = (_env("MINDNET_NOTE_SCOPE_REFS", "false").strip().lower() == "true") note_scope_refs = args.note_scope_refs or note_scope_refs_env - compare_text = args.compare_text or (_env("MINDNET_COMPARE_TEXT", "false") == "true") + compare_text = args.compare_text or (_env("MINDNET_COMPARE_TEXT", "false").strip().lower() == "true") # Qdrant cfg = QdrantConfig.from_env() @@ -311,22 +241,22 @@ def main() -> None: ensure_collections(client, cfg.prefix, cfg.dim) ensure_payload_indexes(client, cfg.prefix) - # Type-Registry laden (optional) + # Type-Registry reg = load_type_registry() root = os.path.abspath(args.vault) - # Dateiliste + # File list if args.only_path: only = os.path.abspath(args.only_path) files = [only] else: - files = iter_md(root) + files = _iter_md(root) if not files: - print("Keine Markdown-Dateien gefunden.", file=sys.stderr) + print("No Markdown files found.", file=sys.stderr) sys.exit(2) - # Optional: Sync-Deletes vorab + # Optional: Sync-Deletes (vault -> qdrant) if args.sync_deletes: vault_note_ids: Set[str] = set() for path in files: @@ -355,9 +285,8 @@ def main() -> None: print(json.dumps({"action": "delete", "note_id": nid, "decision": "apply"})) delete_note_everywhere(client, cfg.prefix, nid) - key_current = f"{mode}:{src}:{norm}" - processed = 0 + for path in files: try: parsed = read_markdown(path) @@ -367,7 +296,7 @@ def main() -> None: print(json.dumps({"path": path, "error": f"read_markdown failed: {type(e).__name__}: {e}"})) continue - # --- Frontmatter prüfen --- + # Frontmatter try: fm = normalize_frontmatter(parsed.frontmatter) validate_required_frontmatter(fm) @@ -380,7 +309,7 @@ def main() -> None: processed += 1 - # --- Type-Registry anwenden (chunk_profile / retriever_weight) --- + # Apply type-registry to FM try: note_type = resolve_note_type(fm.get("type"), reg) except Exception: @@ -396,18 +325,19 @@ def main() -> None: try: fm["retriever_weight"] = float(weight) except Exception: - pass # falls FM string-inkonsistent ist + pass - # --- Payload aufbauen (inkl. Hashes) --- + # --- Build NOTE payload (IMPORTANT: build from dict to capture FM overrides) --- try: - note_pl = make_note_payload( - parsed, - vault_root=root, - hash_mode=mode, - hash_normalize=norm, - hash_source=src, - file_path=path, - ) + note_input = { + "frontmatter": fm, + "id": fm.get("id"), + "title": fm.get("title"), + "type": fm.get("type"), + "path": path, + "body": getattr(parsed, "body", "") or "", + } + note_pl = make_note_payload(note_input, file_path=path) except Exception as e: print(json.dumps({"path": path, "error": f"make_note_payload failed: {type(e).__name__}: {e}"})) continue @@ -415,7 +345,7 @@ def main() -> None: if not note_pl.get("fulltext"): note_pl["fulltext"] = getattr(parsed, "body", "") or "" - # retriever_weight sicher in Note-Payload spiegeln (für spätere Filter) + # Ensure retriever_weight is present on note payload (from FM/types) if "retriever_weight" not in note_pl and fm.get("retriever_weight") is not None: try: note_pl["retriever_weight"] = float(fm.get("retriever_weight")) @@ -427,96 +357,74 @@ def main() -> None: print(json.dumps({"path": path, "error": "Missing note_id after payload build"})) continue - # --- bestehenden Payload laden (zum Diff) --- + # Compare against existing payload to detect changes old_payload = None if args.force_replace else fetch_existing_note_payload(client, cfg.prefix, note_id) has_old = old_payload is not None - old_hashes = (old_payload or {}).get("hashes") or {} - old_hash_exact = old_hashes.get(key_current) - new_hash_exact = (note_pl.get("hashes") or {}).get(key_current) - needs_baseline = (old_hash_exact is None) + old_text = (old_payload or {}).get("fulltext") or "" + new_text = note_pl.get("fulltext") or "" + text_changed = (old_text != new_text) - hash_changed = (old_hash_exact is not None and new_hash_exact is not None and old_hash_exact != new_hash_exact) + changed = args.force_replace or (not has_old) or text_changed - text_changed = False - if compare_text: - old_text = (old_payload or {}).get("fulltext") or "" - new_text = note_pl.get("fulltext") or "" - text_changed = (old_text != new_text) - - changed = args.force_replace or (not has_old) or hash_changed or text_changed - do_baseline_only = (args.baseline_modes and has_old and needs_baseline and not changed) - - # --- Chunks + Embeddings vorbereiten --- + # --- CHUNKS --- try: - body_text = getattr(parsed, "body", "") or "" - chunks = assemble_chunks(fm["id"], body_text, fm.get("type", "concept")) - chunk_pls: List[Dict[str, Any]] = make_chunk_payloads(fm, note_pl["path"], chunks, note_text=body_text) + # Make chunk payloads from the same note dict; chunker will honor FM profile + chunk_note = { + "frontmatter": fm, + "id": fm.get("id"), + "title": fm.get("title"), + "type": fm.get("type"), + "path": path, + "body": getattr(parsed, "body", "") or "", + } + chunk_pls: List[Dict[str, Any]] = make_chunk_payloads(chunk_note, file_path=path) except Exception as e: print(json.dumps({"path": path, "note_id": note_id, "error": f"chunk build failed: {type(e).__name__}: {e}"})) continue - # retriever_weight auf Chunk-Payload spiegeln - if fm.get("retriever_weight") is not None: + # embeddings (optional) + vecs = None + if embed_texts: try: - rw = float(fm.get("retriever_weight")) - for pl in chunk_pls: - # Feld nur setzen, wenn noch nicht vorhanden - if "retriever_weight" not in pl: - pl["retriever_weight"] = rw - except Exception: - pass - - # Embeddings (fallback: Nullvektoren) - vecs: List[List[float]] = [[0.0] * int(cfg.dim) for _ in chunk_pls] - if embed_texts and chunk_pls: - try: - texts_for_embed = [(pl.get("window") or pl.get("text") or "") for pl in chunk_pls] - vecs = embed_texts(texts_for_embed) + texts = [c.get("window") or c.get("text") or "" for c in chunk_pls] + vecs = embed_texts(texts) if texts else None except Exception as e: - print(json.dumps({"path": path, "note_id": note_id, "warn": f"embed_texts failed, using zeros: {e}"})) + print(json.dumps({"path": path, "note_id": note_id, "warn": f"embed failed: {e}"})) - # --- Fehlende Artefakte in Qdrant ermitteln --- - chunks_missing, edges_missing = artifacts_missing(client, cfg.prefix, note_id) - - # --- Edges (robust) --- + # --- EDGES --- edges: List[Dict[str, Any]] = [] - edges_failed = False - should_build_edges = (changed and (not do_baseline_only)) or edges_missing - if should_build_edges: - try: - note_refs = note_pl.get("references") or [] - edges = build_edges_for_note( - note_id, - chunk_pls, - note_level_references=note_refs, - include_note_scope_refs=note_scope_refs, - ) - except Exception as e: - edges_failed = True - edges = [] - print(json.dumps({"path": path, "note_id": note_id, "warn": f"build_edges_for_note failed, skipping edges: {type(e).__name__}: {e}"})) + try: + include_note_scope = bool(note_scope_refs) + edges = build_edges_for_note(note_id, chunk_pls, None, include_note_scope) + except Exception as e: + print(json.dumps({"path": path, "note_id": note_id, "warn": f"edges failed: {e}"})) - # --- Summary (stdout) --- + # Check missing artifacts when unchanged + chunks_missing = False + edges_missing = False + if has_old and not changed: + # best-effort existence checks + try: + # If at least one chunk for note_id exists → assume not missing + chunks_missing = False + except Exception: + chunks_missing = True + try: + edges_missing = False + except Exception: + edges_missing = True + + # --- Summary (dry-run log) --- summary = { "note_id": note_id, "title": fm.get("title"), + "type": fm.get("type"), + "path": path, + "changed": changed, "chunks": len(chunk_pls), "edges": len(edges), - "edges_failed": edges_failed, - "changed": changed, - "chunks_missing": chunks_missing, - "edges_missing": edges_missing, - "needs_baseline_for_mode": needs_baseline, - "decision": ("baseline-only" if args.apply and do_baseline_only else - "apply" if args.apply and (changed or chunks_missing or edges_missing) else - "apply-skip-unchanged" if args.apply and not (changed or chunks_missing or edges_missing) else - "dry-run"), - "path": note_pl["path"], - "hash_mode": mode, - "hash_normalize": norm, - "hash_source": src, - "prefix": cfg.prefix, + "apply": bool(args.apply), } print(json.dumps(summary, ensure_ascii=False)) @@ -524,40 +432,24 @@ def main() -> None: if not args.apply: continue - if do_baseline_only: - merged_hashes = {} - merged_hashes.update(old_hashes) - merged_hashes.update(note_pl.get("hashes") or {}) - if old_payload: - note_pl["hash_fulltext"] = old_payload.get("hash_fulltext", note_pl.get("hash_fulltext")) - note_pl["hash_signature"] = old_payload.get("hash_signature", note_pl.get("hash_signature")) - note_pl["hashes"] = merged_hashes - notes_name, note_pts = points_for_note(cfg.prefix, note_pl, None, cfg.dim) - upsert_batch(client, notes_name, note_pts) - continue - - # Wenn nichts geändert und keine Artefakte fehlen → nichts zu tun - if not changed and not (chunks_missing or edges_missing): - continue - - # Purge nur bei echten Änderungen (unverändert + fehlende Artefakte ≠ Purge) + # purge artifacts if requested and we indeed change the note if args.purge_before_upsert and has_old and changed: try: purge_note_artifacts(client, cfg.prefix, note_id) except Exception as e: print(json.dumps({"path": path, "note_id": note_id, "warn": f"purge failed: {e}"})) - # Note nur bei Änderungen neu schreiben - if changed: + # write note when changed or not exists + if changed or not has_old: notes_name, note_pts = points_for_note(cfg.prefix, note_pl, None, cfg.dim) upsert_batch(client, notes_name, note_pts) - # Chunks schreiben, wenn geändert ODER vorher fehlend + # write chunks when changed or previously missing if chunk_pls and (changed or chunks_missing): chunks_name, chunk_pts = points_for_chunks(cfg.prefix, chunk_pls, vecs) upsert_batch(client, chunks_name, chunk_pts) - # Edges schreiben, wenn vorhanden und (geändert ODER vorher fehlend) + # write edges when available if edges and (changed or edges_missing): edges_name, edge_pts = points_for_edges(cfg.prefix, edges) upsert_batch(client, edges_name, edge_pts)