Dateien nach "scripts" hochladen

scripts/import_markdown.py

@@ -4,27 +4,6 @@
 Script: scripts/import_markdown.py — Markdown → Qdrant (Notes, Chunks, Edges)
 Version: 3.7.2
 Datum: 2025-09-30
-# ---- helpers ----
-def effective_chunk_profile(note_type: str, registry: dict) -> str | None:
-    try:
-        tcfg = (registry or {}).get("types", {}).get(note_type) or (registry or {}).get("types", {}).get("concept")
-        prof = (tcfg or {}).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) -> float | None:
-    try:
-        tcfg = (registry or {}).get("types", {}).get(note_type) or (registry or {}).get("types", {}).get("concept")
-        w = (tcfg or {}).get("retriever_weight")
-        if w is None:
-            return None
-        return float(w)
-    except Exception:
-        return None
-
 
 Kurzbeschreibung
 ----------------
@@ -372,39 +351,11 @@ 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 --------
         chunk_pls: List[Dict[str, Any]] = []
         try:
             body_text = getattr(parsed, "body", "") or ""
-            # ---- Type-Registry integration ----
-            try:
-                note_type = resolve_note_type(fm.get("type"), reg)
-            except Exception:
-                note_type = (fm.get("type") or "concept")
-            fm["type"] = note_type or "concept"
-            try:
-                cfg_type = get_type_config(note_type, reg)
-            except Exception:
-                cfg_type = {}
-            prof = effective_chunk_profile(note_type, reg)
-            if prof:
-                fm["chunk_profile"] = prof
-            weight = cfg_type.get("retriever_weight")
-            if weight is not None:
-                fm["retriever_weight"] = float(weight)
-
-            # Ensure note-level payload reflects registry fields
-            try:
-                if isinstance(note_pl, dict):
-                    if fm.get("type"):
-                        note_pl["type"] = fm["type"]
-                    if fm.get("chunk_profile"):
-                        note_pl["chunk_profile"] = fm["chunk_profile"]
-                    if "retriever_weight" in fm:
-                        note_pl["retriever_weight"] = fm["retriever_weight"]
-            except Exception:
-                pass
-
             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)
         except Exception as e:
@@ -419,7 +370,6 @@ def main() -> None:
             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
@@ -498,3 +448,31 @@ def main() -> None:
 
 if __name__ == "__main__":
     main()
+
+
+# --- Type-Registry helper shims (safe if unused) ---
+
+def effective_chunk_profile(note_type: str, registry: dict) -> str | None:
+    try:
+        reg = registry or {}
+        types = reg.get("types", {}) if isinstance(reg, dict) else {}
+        # take exact type or fallback to concept
+        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) -> float | None:
+    try:
+        reg = registry or {}
+        types = reg.get("types", {}) if isinstance(reg, 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:
+        return None