Dateien nach "scripts" hochladen

scripts/import_markdown.py

@@ -351,40 +351,40 @@ def main() -> None:
 
         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 --------
+        # -------- Chunks / Embeddings --------
-chunk_pls: List[Dict[str, Any]] = []
+        chunk_pls: List[Dict[str, Any]] = []
-try:
+        try:
-    body_text = getattr(parsed, "body", "") or ""
+            body_text = getattr(parsed, "body", "") or ""
-    # ---- Type-Registry integration ----
+            # ---- Type-Registry integration ----
-    try:
+            try:
-        note_type = resolve_note_type(fm.get("type"), reg)
+                note_type = resolve_note_type(fm.get("type"), reg)
-    except Exception:
+            except Exception:
-        note_type = (fm.get("type") or "concept")
+                note_type = (fm.get("type") or "concept")
-    fm["type"] = note_type or "concept"
+            fm["type"] = note_type or "concept"
-    try:
+            try:
-        cfg_type = get_type_config(note_type, reg)
+                cfg_type = get_type_config(note_type, reg)
-    except Exception:
+            except Exception:
-        cfg_type = {}
+                cfg_type = {}
-    prof = effective_chunk_profile(note_type, reg)
+            prof = effective_chunk_profile(note_type, reg)
-    if prof:
+            if prof:
-        fm["chunk_profile"] = prof
+                fm["chunk_profile"] = prof
-    weight = cfg_type.get("retriever_weight")
+            weight = cfg_type.get("retriever_weight")
-    if weight is not None:
+            if weight is not None:
-        fm["retriever_weight"] = float(weight)
+                fm["retriever_weight"] = float(weight)
 
-    chunks = assemble_chunks(fm["id"], body_text, fm.get("type", "concept"))
+            chunks = assemble_chunks(fm["id"], body_text, fm.get("type", "concept"))
-    chunk_pls = make_chunk_payloads(fm, note_pl["path"], chunks, note_text=body_text)
+            chunk_pls = make_chunk_payloads(fm, note_pl["path"], chunks, note_text=body_text)
-except Exception as e:
+        except Exception as e:
-    print(json.dumps({"path": path, "note_id": note_id, "error": f"chunk build failed: {type(e).__name__}: {e}"}))
+            print(json.dumps({"path": path, "note_id": note_id, "error": f"chunk build failed: {type(e).__name__}: {e}"}))
-    continue
+            continue
 
-vecs: List[List[float]] = [[0.0] * cfg.dim for _ in chunk_pls]
+        vecs: List[List[float]] = [[0.0] * cfg.dim for _ in chunk_pls]
-if embed_texts and chunk_pls:
+        if embed_texts and chunk_pls:
-    try:
+            try:
-        texts_for_embed = [(pl.get("window") or pl.get("text") or "") for pl in chunk_pls]
+                texts_for_embed = [(pl.get("window") or pl.get("text") or "") for pl in chunk_pls]
-        vecs = embed_texts(texts_for_embed)
+                vecs = embed_texts(texts_for_embed)
-    except Exception as e:
+            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_texts failed, using zeros: {e}"}))
 
 
         # -------- Edges (robust) --------