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

mini-nav/scenegraph/__init__.py

@@ -13,12 +13,14 @@ from .hash_codec import (
     hash_bytes_to_cam_row,
 )
 from .objectnode import ObjectNode
+from .query import ImageSceneGraphQueryResult, query_image_against_scene_graph
 from .roomnode import RoomNode
 from .scenegraph import SceneGraphMatch, SimpleSceneGraph
 from .software_cam import CamMatch, SoftwareCamIndex, xnor_popcount_score
 
 __all__ = [
     "CamMatch",
+    "ImageSceneGraphQueryResult",
     "ObjectNode",
     "RoomNode",
     "SceneGraphMatch",
@@ -29,5 +31,6 @@ __all__ = [
     "cam_row_to_hash_bytes",
     "hash_bytes_to_bits_array",
     "hash_bytes_to_cam_row",
+    "query_image_against_scene_graph",
     "xnor_popcount_score",
 ]

mini-nav/scenegraph/query.py

@@ -0,0 +1,57 @@
+from __future__ import annotations
+
+from dataclasses import dataclass
+from typing import Any
+
+from PIL import Image
+
+from .hash_codec import bits_tensor_to_hash_bytes
+from .scenegraph import SceneGraphMatch, SimpleSceneGraph
+
+
+@dataclass(frozen=True)
+class ImageSceneGraphQueryResult:
+    query_crop_index: int
+    query_hash: bytes
+    query_crop: Image.Image
+    matches: list[SceneGraphMatch]
+
+
+def query_image_against_scene_graph(
+    image: Image.Image,
+    pipeline: Any,
+    scene_graph: SimpleSceneGraph,
+    text_labels: list[str],
+    *,
+    top_k: int = 1,
+    batch_size: int = 1,
+) -> list[ImageSceneGraphQueryResult]:
+    output = pipeline.process_batch([image], text_labels, batch_size=batch_size)
+    hash_bits = output.hash_bits
+    cropped_images = list(output.cropped_images)
+
+    if hash_bits.numel() == 0:
+        if cropped_images:
+            raise ValueError("hash_bits and cropped_images must align")
+        return []
+
+    if hash_bits.dim() == 1:
+        hash_bits = hash_bits.unsqueeze(0)
+
+    if hash_bits.shape[0] != len(cropped_images):
+        raise ValueError("hash_bits and cropped_images must align")
+
+    results: list[ImageSceneGraphQueryResult] = []
+    for crop_index, query_bits in enumerate(hash_bits):
+        query_hash = bits_tensor_to_hash_bytes(query_bits)
+        matches = scene_graph.query_by_visual_hash(query_hash, top_k=top_k)
+        results.append(
+            ImageSceneGraphQueryResult(
+                query_crop_index=crop_index,
+                query_hash=query_hash,
+                query_crop=cropped_images[crop_index],
+                matches=matches,
+            )
+        )
+
+    return results