#!/usr/bin/env python3 # -*- coding: utf-8 -*- """ Script: scripts/import_markdown.py - Markdown -> Qdrant (Notes, Chunks, Edges) Version: 3.7.3 Date: 2025-11-08 Summary ------- - Reads Markdown files and creates Notes/Chunks/Edges idempotently. - Change detection "Option C": multiple hash variants are stored in note payload (field `hashes` with keys `::`). Comparison uses ONLY the current-mode key. Switching modes no longer triggers bulk "changed". - "First import" fix: if Qdrant is empty for the note, we treat it as changed. - `--baseline-modes`: silently add any missing hash variants (notes only). - `--sync-deletes`: selective deletes (Dry-Run + Apply). - `--only-path`: process exactly one file (useful for diagnostics). - NEW in 3.7.3: Type registry (if present) is loaded and the derived `retriever_weight` is written to both note and chunk payload. If the registry defines a `chunk_profile`, it is injected into frontmatter for payloads (does NOT change the chunking behavior here). Hash/Compare configuration -------------------------- - Compare mode: --hash-mode body|frontmatter|full or ENV: MINDNET_HASH_MODE | MINDNET_HASH_COMPARE - Source: --hash-source parsed|raw (ENV: MINDNET_HASH_SOURCE, Default parsed) - Normalization: --hash-normalize canonical|none (ENV: MINDNET_HASH_NORMALIZE, Default canonical) - Optional: --compare-text (or ENV MINDNET_COMPARE_TEXT=true) compares parsed body text, in addition to the hash. Qdrant / ENV ------------ - QDRANT_URL | QDRANT_HOST/QDRANT_PORT | QDRANT_API_KEY - COLLECTION_PREFIX (Default: mindnet), can be overridden with --prefix - VECTOR_DIM (Default: 384) - MINDNET_NOTE_SCOPE_REFS: true|false (Default: false) - MINDNET_TYPES_PATH: optional path to config/types.yaml Examples -------- # Standard (Body, parsed, canonical) python3 -m scripts.import_markdown --vault ./vault # First import after truncate (create case) python3 -m scripts.import_markdown --vault ./vault --apply --purge-before-upsert # Single file (diagnostics) python3 -m scripts.import_markdown --vault ./vault --only-path ./vault/30_projects/project-demo.md --apply # Sync-Deletes (Dry-Run -> Apply) python3 -m scripts.import_markdown --vault ./vault --sync-deletes python3 -m scripts.import_markdown --vault ./vault --sync-deletes --apply """ from __future__ import annotations import argparse import json import os import sys from typing import Dict, List, Optional, Tuple, Any, Set from dotenv import load_dotenv from qdrant_client.http import models as rest 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, ensure_collections, ensure_payload_indexes, ) from app.core.qdrant_points import ( points_for_chunks, points_for_note, points_for_edges, upsert_batch, ) # ---- Type-Registry (optional) ------------------------------------------------ try: # Expected API from app.core.type_registry import load_type_registry # type: ignore except Exception: # pragma: no cover def load_type_registry(path: str) -> dict: """Fallback loader if module is absent. Returns empty dict.""" return {} # --------------------------------------------------------------------- # Helper # --------------------------------------------------------------------- def iter_md(root: str) -> List[str]: out: 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) def collections(prefix: str) -> Tuple[str, str, str]: return f"{prefix}_notes", f"{prefix}_chunks", f"{prefix}_edges" 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, with_payload=True, with_vectors=False, limit=1, ) if not points: return None return points[0].payload or {} def list_qdrant_note_ids(client, prefix: str) -> Set[str]: notes_col, _, _ = collections(prefix) out: Set[str] = set() next_page = 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 for p in pts: pl = p.payload or {} nid = pl.get("note_id") if isinstance(nid, str): out.add(nid) if next_page is None: break return out 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}"})) 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}"})) def _resolve_mode(val: Optional[str]) -> str: v = (val or os.environ.get("MINDNET_HASH_MODE") or os.environ.get("MINDNET_HASH_COMPARE") or "body").strip().lower() if v in ("full", "fulltext", "body+frontmatter", "bodyplusfrontmatter"): return "full" if v in ("frontmatter", "fm"): return "frontmatter" return "body" def _env(key: str, default: str) -> str: return (os.environ.get(key) or default).strip().lower() # --- Type-Registry helpers (pure) -------------------------------------------- def _effective_chunk_profile(note_type: str, registry: dict) -> Optional[str]: try: types = (registry or {}).get("types", {}) if isinstance(registry, dict) else {} cfg = types.get(note_type) or types.get("concept") or {} prof = cfg.get("chunk_profile") if isinstance(prof, str) and prof in {"short", "medium", "long"}: return prof except Exception: pass return None def _effective_retriever_weight(note_type: str, registry: dict) -> Optional[float]: try: types = (registry or {}).get("types", {}) if isinstance(registry, dict) else {} cfg = types.get(note_type) or types.get("concept") or {} w = cfg.get("retriever_weight") if w is None: return None return float(w) except Exception: # be tolerant return None # --------------------------------------------------------------------- # Main # --------------------------------------------------------------------- def main() -> None: load_dotenv() ap = argparse.ArgumentParser() ap.add_argument("--vault", required=True, help="Path to the Obsidian vault (root folder)") ap.add_argument("--apply", action="store_true", help="Write to Qdrant; otherwise Dry-Run") ap.add_argument("--purge-before-upsert", action="store_true", help="Before upsert, delete Chunks & Edges of the CHANGED note") ap.add_argument("--note-id", help="Process only a specific note-id") ap.add_argument("--only-path", help="Process exactly this Markdown path (ignores --note-id)") ap.add_argument("--embed-note", action="store_true", help="Optionally embed the full note text") ap.add_argument("--force-replace", action="store_true", help="Ignore change detection and always upsert (+ optional purge)") ap.add_argument("--hash-mode", choices=["body", "frontmatter", "full"], default=None, help="Compare mode (Body | Frontmatter | Full)") ap.add_argument("--hash-normalize", choices=["canonical", "none"], default=None) ap.add_argument("--hash-source", choices=["parsed", "raw"], default=None, help="Source for hash calculation (Default: parsed)") ap.add_argument("--note-scope-refs", action="store_true", help="(Optional) also create references:note/backlink:note (Default: off)") ap.add_argument("--debug-hash-diff", action="store_true", help="(reserved) optional body diff") ap.add_argument("--compare-text", action="store_true", help="Additionally compare parsed fulltext (beyond the hash)") ap.add_argument("--baseline-modes", action="store_true", help="Add missing hash variants in 'hashes' silently (Upsert notes only)") ap.add_argument("--sync-deletes", action="store_true", help="Delete notes/chunks/edges that exist in Qdrant but are missing in the vault (Dry-Run; use --apply to execute)") ap.add_argument("--prefix", help="Collection prefix (overrides ENV COLLECTION_PREFIX)") args = ap.parse_args() 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 = args.note_scope_refs or note_scope_refs_env compare_text = args.compare_text or (_env("MINDNET_COMPARE_TEXT", "false") == "true") # Prepare Qdrant client cfg = QdrantConfig.from_env() if args.prefix: cfg.prefix = args.prefix.strip() client = get_client(cfg) ensure_collections(client, cfg.prefix, cfg.dim) ensure_payload_indexes(client, cfg.prefix) # Load type registry (optional) types_path = os.environ.get("MINDNET_TYPES_PATH") or os.path.join(os.getcwd(), "config", "types.yaml") try: type_registry = load_type_registry(types_path) or {} except Exception as e: # tolerant print(json.dumps({"warn": f"type-registry load failed ({types_path}): {type(e).__name__}: {e}"})) type_registry = {} root = os.path.abspath(args.vault) # Build file list if args.only_path: only = os.path.abspath(args.only_path) files = [only] else: files = iter_md(root) if not files: print("No Markdown files found.", file=sys.stderr) sys.exit(2) # Optional: Sync-Deletes upfront if args.sync_deletes: vault_note_ids: Set[str] = set() for path in files: try: parsed = read_markdown(path) if not parsed: continue fm = normalize_frontmatter(parsed.frontmatter) nid = fm.get("id") if isinstance(nid, str): vault_note_ids.add(nid) except Exception: continue qdrant_note_ids = list_qdrant_note_ids(client, cfg.prefix) to_delete = sorted(qdrant_note_ids - vault_note_ids) print(json.dumps({ "action": "sync-deletes", "prefix": cfg.prefix, "qdrant_total": len(qdrant_note_ids), "vault_total": len(vault_note_ids), "to_delete_count": len(to_delete), "to_delete": to_delete[:50] + (["…"] if len(to_delete) > 50 else []) }, ensure_ascii=False)) if args.apply and to_delete: for nid in to_delete: 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: # -------- Parse & Validate -------- try: parsed = read_markdown(path) except Exception as e: print(json.dumps({"path": path, "error": f"read_markdown failed: {type(e).__name__}: {e}"})) continue if parsed is None: print(json.dumps({"path": path, "error": "read_markdown returned None"})) continue try: fm = normalize_frontmatter(parsed.frontmatter) validate_required_frontmatter(fm) except Exception as e: print(json.dumps({"path": path, "error": f"Frontmatter invalid: {type(e).__name__}: {e}"})) continue if args.note_id and not args.only_path and fm.get("id") != args.note_id: continue processed += 1 # -------- Type-Registry derivation (tolerant) -------- note_type = (fm.get("type") or "concept").strip().lower() prof = _effective_chunk_profile(note_type, type_registry) if prof and not fm.get("chunk_profile"): fm["chunk_profile"] = prof weight = _effective_retriever_weight(note_type, type_registry) if weight is not None: fm["retriever_weight"] = weight # -------- Build new payload (includes 'hashes') -------- note_pl = make_note_payload( parsed, vault_root=root, hash_mode=mode, hash_normalize=norm, hash_source=src, file_path=path, ) if not note_pl.get("fulltext"): note_pl["fulltext"] = getattr(parsed, "body", "") or "" if weight is not None: note_pl["retriever_weight"] = weight note_id = note_pl.get("note_id") or fm.get("id") if not note_id: print(json.dumps({"path": path, "error": "Missing note_id after payload build"})) continue # -------- Fetch old payload -------- 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 {} key_current = f"{mode}:{src}:{norm}" 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) hash_changed = (old_hash_exact is not None and new_hash_exact is not None and old_hash_exact != new_hash_exact) 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 -------- chunk_pls: List[Dict[str, Any]] = [] try: body_text = getattr(parsed, "body", "") or "" chunks = assemble_chunks(fm["id"], body_text, note_type) chunk_pls = make_chunk_payloads(fm, note_pl["path"], chunks, note_text=body_text) if weight is not None: for pl in chunk_pls: if pl.get("retriever_weight") is None: pl["retriever_weight"] = weight except Exception as e: print(json.dumps({"path": path, "note_id": note_id, "error": f"chunk build failed: {type(e).__name__}: {e}"})) continue vecs: List[List[float]] = [[0.0] * 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) except Exception as e: print(json.dumps({"path": path, "note_id": note_id, "warn": f"embed_texts failed, using zeros: {e}"})) # -------- Edges (robust) -------- edges: List[Dict[str, Any]] = [] edges_failed = False if changed and (not do_baseline_only): 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}"})) # -------- Summary -------- summary = { "note_id": note_id, "title": fm.get("title"), "type": note_type, "chunk_profile": fm.get("chunk_profile"), "retriever_weight": weight, "chunks": len(chunk_pls), "edges": len(edges), "edges_failed": edges_failed, "changed": changed, "needs_baseline_for_mode": needs_baseline, "decision": ("baseline-only" if args.apply and do_baseline_only else "apply" if args.apply and changed else "apply-skip-unchanged" if args.apply and not changed else "dry-run"), "path": note_pl["path"], "hash_mode": mode, "hash_normalize": norm, "hash_source": src, "prefix": cfg.prefix, } print(json.dumps(summary, ensure_ascii=False)) # -------- Writes -------- 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 if not changed: continue if args.purge_before_upsert and has_old: 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}"})) notes_name, note_pts = points_for_note(cfg.prefix, note_pl, None, cfg.dim) upsert_batch(client, notes_name, note_pts) if chunk_pls: chunks_name, chunk_pts = points_for_chunks(cfg.prefix, chunk_pls, vecs) upsert_batch(client, chunks_name, chunk_pts) if edges: edges_name, edge_pts = points_for_edges(cfg.prefix, edges) upsert_batch(client, edges_name, edge_pts) print(f"Done. Processed notes: {processed}") if __name__ == "__main__": main()