Image vector embedding

app/infrastructure/settings.py

@@ -380,6 +380,29 @@ USE_PLAYWRIGHT_FALLBACK = _bool("USE_PLAYWRIGHT_FALLBACK", "true")
 # out 1x1 tracking pixels / broken placeholder images)
 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)
+# ---------------------------------------------------------------------------
+# 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.
+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"))
+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"))
+
 # ---------------------------------------------------------------------------
 # USDA FoodData Central - nutrition for loose, unbranded commodities
 # ---------------------------------------------------------------------------