Initial commit

backend/requirements.txt

@@ -0,0 +1,59 @@
+# --- Web API ---
+fastapi>=0.115.0
+uvicorn[standard]>=0.30.6
+pydantic>=2.9.2
+python-multipart>=0.0.6
+
+# --- Config ---
+python-dotenv>=1.0.1
+
+# --- Database / pgvector ---
+psycopg[binary]>=3.2.3
+pgvector>=0.2.5
+
+# --- Embeddings (RAG retrieval) ---
+# sentence-transformers pulls in its own CPU-friendly torch wheel
+# automatically - no need to pin torch separately. Imports are LAZY
+# (see app/services/embeddings_service.py) so the API still boots fast
+# even before this is installed/loaded.
+sentence-transformers>=3.0.1
+
+# --- HTTP clients ---
+requests>=2.31.0
+aiohttp>=3.9.5
+httpx>=0.27.2
+
+# --- Catalog ingestion pipeline (discovery / images / pricing) ---
+# Only required if you plan to run cli/ingest_brand.py or
+# POST /api/catalog/generate to pull in NEW brands. If you only ever use
+# the bundled seed data (scripts/seed_sample_data.py) + RAG chat/search,
+# you can skip everything below this line.
+beautifulsoup4>=4.12.3
+lxml>=4.9.3
+python-slugify>=8.0.4
+ddgs>=9.14.4
+Pillow>=10.0.0
+aiofiles>=23.2.1
+
+# Playwright (Python) - last-resort image-search fallback only.
+# Run `playwright install chromium` once after pip install to enable it;
+# the pipeline works fine without it (just one fewer fallback source).
+playwright>=1.47.0
+
+# --- S3 / DigitalOcean Spaces (optional product image storage) ---
+boto3>=1.34.162
+
+# --- ML / analytics (app/intelligence/*, incl. nutrition similarity & ---
+# --- clustering) - CPU-only estimators only (GradientBoosting/Random- ---
+# --- Forest/KMeans/NearestNeighbors), no GPU dependency, per the 8GB ---
+# --- RAM / CPU-only environment this project targets. Was already an ---
+# --- implicit dependency (app/intelligence/*.py imports these) but was ---
+# --- missing from this file - declared explicitly now. ---
+scikit-learn>=1.5.2
+pandas>=2.2.2
+numpy>=1.26.4
+scipy>=1.13.1
+joblib>=1.4.2
+
+# --- Dev/test tooling ---
+pytest>=8.3.3