feat(scenegraph): refactor image scene graph query into reusable function

- Export ImageSceneGraphQueryResult and query_image_against_scene_graph from scenegraph module
- Replace inline hamming-distance-based image matching with dedicated query_image_against_scene_graph function
- Improve top_matches structure by extracting similarity scores and hash_bytes from matches
- Add .codegraph/ to gitignore (machine-local data, should not be committed)
- Add CodeGraph configuration for multi-language indexing

notebooks/verification.py

@@ -33,9 +33,14 @@ def base_dependencies():
 @app.cell
 def project_imports():
     """Project module imports using new architecture."""
-    from compressors import HashPipeline, hamming_distance
+    from compressors import HashPipeline
     from configs import cfg_manager
-    from scenegraph import ObjectNode, RoomNode, SimpleSceneGraph
+    from scenegraph import (
+        ObjectNode,
+        RoomNode,
+        SimpleSceneGraph,
+        query_image_against_scene_graph,
+    )
     from simulator import (
         HabitatSimulatorConfig,
         TopDownSceneElements,
@@ -57,8 +62,8 @@ def project_imports():
         cfg_manager,
         collect_room_views_by_room,
         create_habitat_simulator,
-        hamming_distance,
         numpy_to_pil,
+        query_image_against_scene_graph,
         render_topdown_scene_map,
         save_object_image,
         save_room_view,
@@ -362,13 +367,11 @@ def upload_query(mo):
 def query_matching(
     Image,
     file_upload,
-    hamming_distance,
-    np,
     mo,
     object_images,
     pipeline,
+    query_image_against_scene_graph,
     scene_graph,
-    torch,
 ):
     from io import BytesIO
 
@@ -393,49 +396,34 @@ def query_matching(
         "a door",
         "a plant",
     ]
-    _output = pipeline.process_batch([_query_image], _text_labels, batch_size=1)
-    _query_bits = (_output.hash_bits > 0).to(dtype=torch.int32)
+    _query_results = query_image_against_scene_graph(
+        image=_query_image,
+        pipeline=pipeline,
+        scene_graph=scene_graph,
+        text_labels=_text_labels,
+        top_k=5,
+        batch_size=1,
+    )
 
-    if _query_bits.numel() > 0 and scene_graph.objects:
-        _obj_ids = list(scene_graph.objects.keys())
-        _obj_hashes = []
-        for _obj_id in _obj_ids:
-            _obj = scene_graph.objects[_obj_id]
-            _bits = np.unpackbits(np.frombuffer(_obj.visual_hash, dtype=np.uint8))[
-                : pipeline.hash_bits
-            ].astype(np.int32)
-            _obj_hashes.append(_bits)
-
-        _db_tensor = torch.tensor(np.array(_obj_hashes), dtype=torch.int32).to(
-            _query_bits.device
+    if _query_results:
+        _best_result = max(
+            _query_results,
+            key=lambda result: result.matches[0].score if result.matches else -1,
         )
-
-        _distances = hamming_distance(_query_bits, _db_tensor)
-        _best_query_idx = int(_distances.min(dim=1).values.argmin().item())
-
-        _query_tensor = _query_bits[_best_query_idx]
-        query_cropped = _output.cropped_images[_best_query_idx]
-        _query_distances = _distances[_best_query_idx].cpu().numpy()
-        _query_hash_hex = (
-            np.packbits(_query_tensor.cpu().numpy().astype(np.uint8)).tobytes().hex()
-        )
-
-        _top_k = min(5, len(_obj_ids))
-        _top_indices = np.argsort(_query_distances)[:_top_k]
-
+        query_cropped = _best_result.query_crop
         top_matches = [
             {
-                "obj_id": _obj_ids[_i],
-                "distance": int(_query_distances[_i]),
-                "similarity": 1.0 - _query_distances[_i] / float(pipeline.hash_bits),
-                "hash_hex": scene_graph.objects[_obj_ids[_i]].visual_hash.hex(),
+                "obj_id": match.obj_id,
+                "distance": int(pipeline.hash_bits - match.score),
+                "similarity": match.similarity,
+                "hash_hex": match.hash_bytes.hex(),
             }
-            for _i in _top_indices
+            for match in _best_result.matches
         ]
 
         query_result = {
             "query_cropped": query_cropped,
-            "query_hash_hex": _query_hash_hex,
+            "query_hash_hex": _best_result.query_hash.hex(),
             "top_matches": top_matches,
         }