image vector dimensionality reduction

app/infrastructure/settings.py

@@ -381,27 +381,41 @@ USE_PLAYWRIGHT_FALLBACK = _bool("USE_PLAYWRIGHT_FALLBACK", "true")
 MIN_IMAGE_BYTES = int(os.getenv("MIN_IMAGE_BYTES", "3000"))
 
 # ---------------------------------------------------------------------------
-# img_vector - a 32x32 RGB pixel thumbnail of each product's primary image,
-# stored on its brand table (app/services/image_vector.py)
+# img_vector - a MobileNetV3-Small image embedding (1024 floats, L2-normalised)
+# of each product's primary image, stored on its brand table
+# (app/services/image_vector.py owns the column, image_embedder.py the model)
 # ---------------------------------------------------------------------------
 # Computed off the request path by one bounded worker thread after every
 # catalog write, and by scripts/backfill_image_vectors.py for existing rows.
-# Default on: the work is one small download per row just written, never on
-# a request. tests/conftest.py pins it OFF so the suite never dials the
-# database named in a developer's .env.
+# Default on: the work is one small download and one ~30ms inference per row
+# just written, never on a request. tests/conftest.py pins it OFF so the
+# suite never dials the database named in a developer's .env.
 ENABLE_IMAGE_VECTORS = _bool("ENABLE_IMAGE_VECTORS", "true")
 # A download past this many bytes is abandoned - a wrong URL to a video must
 # not fill the container.
 IMAGE_VECTOR_MAX_BYTES = int(os.getenv("IMAGE_VECTOR_MAX_BYTES", str(8 * 1024 * 1024)))
 # Refused before decoding when the header claims more pixels than this
-# (decompression-bomb guard; 40MP is well past any product photo).
-IMAGE_VECTOR_MAX_PIXELS = int(os.getenv("IMAGE_VECTOR_MAX_PIXELS", "40000000"))
+# (decompression-bomb guard; 25MP is well past any product photo, and the
+# embedder decodes at full resolution - ~75MB of RGB at this cap).
+IMAGE_VECTOR_MAX_PIXELS = int(os.getenv("IMAGE_VECTOR_MAX_PIXELS", "25000000"))
 IMAGE_VECTOR_TIMEOUT_SECONDS = float(os.getenv("IMAGE_VECTOR_TIMEOUT_SECONDS", "15"))
 # Minimum gap between two requests to the same image host.
 IMAGE_VECTOR_HOST_PAUSE_SECONDS = float(os.getenv("IMAGE_VECTOR_HOST_PAUSE_SECONDS", "0.5"))
 # Writes waiting for the worker; beyond this a write's rows are left for the
 # backfill script rather than queued.
 IMAGE_VECTOR_QUEUE_MAX = int(os.getenv("IMAGE_VECTOR_QUEUE_MAX", "64"))
+# The TFLite embedder (mobilenet_v3_small_embedder.tflite, input [1,224,224,3]
+# float32, output [1,1024]). Lives under app/, NOT data/: /app/data is a named
+# volume on every deployment (see BUNDLED_ASSETS_DIR), and a file added to
+# the image under a mounted path is invisible on any volume that already
+# exists. app/ is copied into the image and never mounted.
+IMAGE_EMBED_MODEL_PATH = _dir(
+    "IMAGE_EMBED_MODEL_PATH",
+    _BACKEND_ROOT / "app" / "services" / "models" / "mobilenet" / "mobilenet_v3_small_embedder.tflite",
+)
+# Intra-op threads for one inference. 2 on the prod host; inference itself is
+# serialised by a lock (a TFLite interpreter is not thread-safe).
+IMAGE_EMBED_NUM_THREADS = int(os.getenv("IMAGE_EMBED_NUM_THREADS", "2"))
 
 # ---------------------------------------------------------------------------
 # USDA FoodData Central - nutrition for loose, unbranded commodities