Dateien nach "app/core" hochladen

app/core/qdrant_points.py

@@ -217,3 +217,84 @@ def search_chunks_by_vector(client: QdrantClient, prefix: str, vector: List[floa
     for r in res:
         out.append((str(r.id), float(r.score), dict(r.payload or {})))
     return out
+
+
+# --- Edge retrieval helper ---
+
+def get_edges_for_sources(
+    client: QdrantClient,
+    prefix: str,
+    source_ids: Iterable[str],
+    edge_types: Optional[Iterable[str]] = None,
+    limit: int = 2048,
+) -> List[Dict[str, Any]]:
+    """Retrieve edge payloads from the <prefix>_edges collection.
+
+    Args:
+        client: QdrantClient instance.
+        prefix: Mindnet collection prefix (e.g. "mindnet").
+        source_ids: Iterable of source_id values (typically chunk_ids or note_ids).
+        edge_types: Optional iterable of edge kinds (e.g. ["references", "depends_on"]). If None,
+            all kinds are returned.
+        limit: Maximum number of edge payloads to return.
+
+    Returns:
+        A list of edge payload dicts, e.g.:
+        {
+            "note_id": "...",
+            "chunk_id": "...",
+            "kind": "references" | "depends_on" | ...,
+            "scope": "chunk",
+            "source_id": "...",
+            "target_id": "...",
+            "rule_id": "...",
+            "confidence": 0.7,
+            ...
+        }
+    """
+    source_ids = list(source_ids)
+    if not source_ids or limit <= 0:
+        return []
+
+    # Resolve collection name
+    _, _, edges_col = _names(prefix)
+
+    # Build filter: source_id IN source_ids
+    src_filter = _filter_any("source_id", [str(s) for s in source_ids])
+
+    # Optional: kind IN edge_types
+    kind_filter = None
+    if edge_types:
+        kind_filter = _filter_any("kind", [str(k) for k in edge_types])
+
+    flt = _merge_filters(src_filter, kind_filter)
+
+    out: List[Dict[str, Any]] = []
+    next_page = None
+    remaining = int(limit)
+
+    # Use paginated scroll API; we don't need vectors, only payloads.
+    while remaining > 0:
+        batch_limit = min(256, remaining)
+        res, next_page = client.scroll(
+            collection_name=edges_col,
+            scroll_filter=flt,
+            limit=batch_limit,
+            with_payload=True,
+            with_vectors=False,
+            offset=next_page,
+        )
+
+        if not res:
+            break
+
+        for r in res:
+            out.append(dict(r.payload or {}))
+            remaining -= 1
+            if remaining <= 0:
+                break
+
+        if next_page is None or remaining <= 0:
+            break
+
+    return out