fix: update port to 5004, clean requirements.txt, add redirect to index.html

backend/Dockerfile

-# Lấy Python 3.11 slim (ít file, nhẹ)
+# Python 3.11 slim (nhẹ, ít file)
 FROM python:3.11-slim
 
 # Thư mục làm việc
@@ -8,17 +8,13 @@ ENV PYTHONUNBUFFERED=1 PYTHONDONTWRITEBYTECODE=1
 
 # Copy requirements rồi cài package
 COPY requirements.txt .
-RUN pip install -r requirements.txt
+RUN pip install --no-cache-dir -r requirements.txt
 
 # Copy code
 COPY . .
 
-# Copy entrypoint script (nếu có)
-COPY entrypoint.sh /app/entrypoint.sh
-RUN chmod +x /app/entrypoint.sh
+# Mở port (sẽ được override bởi docker-compose)
+EXPOSE 5004
 
-# Mở port 5003
-EXPOSE 5003
-
+# Chạy uvicorn với auto workers (2 * CPU cores + 1)
+CMD ["sh", "-c", "uvicorn server:app --host 0.0.0.0 --port ${PORT:-5004} --workers $(( $(nproc) * 2 + 1 ))"]
\ No newline at end of file
-# Chạy server
-CMD ["/app/entrypoint.sh"]
\ No newline at end of file

backend/api/recommend_image.py

@@ -49,13 +49,15 @@ async def recommend_by_image(
         # Chuyển vector sang định dạng string [v1, v2, ...] để gắn vào SQL
         v_str = "[" + ",".join(map(str, vector.tolist())) + "]"
         
-        # 2. Hardcoded SQL cho StarRocks (CTE + Grouping)
+        # 2. Optimized SQL cho StarRocks (sử dụng HNSW Vector Index)
         # Bảng đích: magento_product_dimension_with_image_embedding
         target_table = "shared_source.magento_product_dimension_with_image_embedding"
+        ef_search = 128  # HNSW ef_search parameter (higher = more accurate, slower)
         
         sql = f"""
         WITH top_sku_candidates AS (
             SELECT
+                /*+ SET_VAR(ann_params='{{"ef_search":{ef_search}}}') */
                 internal_ref_code,
                 product_name,
                 sale_price,
@@ -76,9 +78,8 @@ async def recommend_by_image(
                 form_sleeve,
                 product_line_vn,
                 product_color_name,
-                cosine_similarity(vector, {v_str}) as similarity_score
+                approx_cosine_similarity(vector, {v_str}) as similarity_score
             FROM {target_table}
-            WHERE vector IS NOT NULL
             ORDER BY similarity_score DESC
             LIMIT 50
         )

backend/config.py

@@ -73,7 +73,7 @@ JWT_SECRET: str | None = os.getenv("JWT_SECRET")
 JWT_ALGORITHM: str | None = os.getenv("JWT_ALGORITHM")
 
 # ====================== SERVER CONFIG ======================
-PORT: int = int(os.getenv("PORT", "5000"))
+PORT: int = int(os.getenv("PORT", "5004"))
 FIRECRAWL_API_KEY: str | None = os.getenv("FIRECRAWL_API_KEY")
 
 # ====================== LANGFUSE CONFIGURATION (DEPRECATED) ======================

backend/datadb/text.txt

-product_name: Pack 3 đôi tất bé gái cổ thấp. master_color: Xanh da trời/ Blue. product_image_url: https://2885371169.e.cdneverest.net/pub/media/catalog/product/1/a/1ax24a002-pb449-7-9-ghep-u.jpg. product_image_url_thumbnail: https://2885371169.e.cdneverest.net/pub/media/catalog/product/1/a/1ax24a002-pb449-7-9-ghep-u.jpg. product_web_url: https://canifa.com/tat-be-gai-1ax24a002?color=PB449&utm_source=chatbot&utm_medium=rsa&utm_campaign=testver25.9. description_text: Pack 3 đôi tất cổ thấp, họa tiết basic.
-Chất liệu cotton pha mềm mại, co giãn tốt, màu sắc đơn giản dễ phối mix đồ.. material: None. material_group: Yarn - Sợi. gender_by_product: female. age_by_product: others. season: Year. style: Feminine. fitting: Slim. size_scale: 4/6. form_neckline: None. form_sleeve: None. product_line_vn: Tất. product_color_name: Blue Strip 449
\ No newline at end of file

backend/docker-compose.yml

@@ -2,14 +2,14 @@ services:
   # --- Backend Service ---
   backend:
     build: .
-    container_name: canifa_backend
+    container_name: canifa_tool_test_recommend
     env_file: .env
     ports:
-      - "5003:5003"
+      - "5004:5004"
     volumes:
       - .:/app
     environment:
-      - PORT=5003
+      - PORT=5004
     restart: unless-stopped
     deploy:
       resources:

backend/entrypoint.sh

-#!/bin/bash
-NUM_CORES=$(nproc)
-WORKERS=$((2 * NUM_CORES + 1))
-
-echo "🔧 [STARTUP] CPU cores: $NUM_CORES"
-echo "🔧 [STARTUP] Gunicorn workers: $WORKERS"
-
-exec gunicorn \
-    server:app \
-    --workers "$WORKERS" \
-    --worker-class uvicorn.workers.UvicornWorker \
-    --worker-connections 1000 \
-    --max-requests 1000 \
-    --max-requests-jitter 100 \
-    --timeout 30 \
-    --access-logfile - \
-    --error-logfile - \
-    --bind 0.0.0.0:5000 \
-    --log-level info
\ No newline at end of file

backend/requirements.txt

 # Core Web Framework

backend/requirements_docker.txt

+annotated-doc==0.0.4
+annotated-types==0.7.0
+anyio==4.12.0
+attrs==25.4.0
+bidict==0.23.1
+blinker==1.9.0
+brotli==1.2.0
+certifi==2025.11.12
+cffi==2.0.0
+charset-normalizer==3.4.4
+click==8.3.1
+colorama==0.4.6
+ConfigArgParse==1.7.1
+cryptography==46.0.3
+distro==1.9.0
+et_xmlfile==2.0.0
+fastapi==0.128.0
+Flask==3.1.2
+flask-cors==6.0.2
+Flask-Login==0.6.3
+gevent==25.9.1
+geventhttpclient==2.3.7
+googleapis-common-protos==1.72.0
+greenlet==3.3.0
+grpcio==1.76.0
+h11==0.16.0
+httpcore==1.0.9
+httpx==0.28.1
+httpx-sse==0.4.3
+idna==3.11
+importlib_metadata==8.7.1
+iniconfig==2.3.0
+itsdangerous==2.2.0
+Jinja2==3.1.6
+jiter==0.12.0
+jsonschema==4.25.1
+jsonschema-specifications==2025.9.1
+locust==2.43.0
+MarkupSafe==3.0.3
+mcp==1.25.0
+msgpack==1.1.2
+numpy==2.4.0
+openai==2.15.0
+openpyxl==3.1.5
+opentelemetry-api==1.39.1
+opentelemetry-exporter-otlp==1.39.1
+opentelemetry-exporter-otlp-proto-common==1.39.1
+opentelemetry-exporter-otlp-proto-grpc==1.39.1
+opentelemetry-exporter-otlp-proto-http==1.39.1
+opentelemetry-proto==1.39.1
+opentelemetry-sdk==1.39.1
+opentelemetry-semantic-conventions==0.60b1
+packaging==25.0
+pandas==2.3.3
+pluggy==1.6.0
+protobuf==6.33.2
+psutil==7.2.1
+pycparser==2.23
+pydantic==2.12.5
+pydantic-settings==2.12.0
+pydantic_core==2.41.5
+Pygments==2.19.2
+PyJWT==2.10.1
+pytest==9.0.2
+python-dateutil==2.9.0.post0
+python-dotenv==1.2.1
+python-engineio==4.13.0
+python-multipart==0.0.21
+python-socketio==5.16.0
+pytz==2025.2
+pyzmq==27.1.0
+referencing==0.37.0
+requests==2.32.5
+rpds-py==0.30.0
+simple-websocket==1.1.0
+six==1.17.0
+sniffio==1.3.1
+sse-starlette==3.1.2
+starlette==0.50.0
+tqdm==4.67.1
+typing-inspection==0.4.2
+typing_extensions==4.15.0
+tzdata==2025.3
+urllib3==2.6.2
+uvicorn==0.40.0
+websocket-client==1.9.0
+Werkzeug==3.1.4
+wsproto==1.3.2
+zipp==3.23.0
+zope.event==6.1
+zope.interface==8.1.1

backend/run.txt

@@ -4,10 +4,10 @@
 
 .\.venv\Scripts\activate
 
-uvicorn server:app --host 0.0.0.0 --port 8000 --reload
 
 
-uvicorn server:app --host 0.0.0.0 --port 5000
+
+uvicorn server:app --host 0.0.0.0 --port 6000
 
 docker restart chatbot-backend
 

backend/server.py

@@ -71,9 +71,11 @@ try:
 except Exception as e:
     print(f"⚠️ Failed to mount static files: {e}")
 
+from fastapi.responses import RedirectResponse
+
 @app.get("/")
 async def root():
-    return {"message": "Contract AI Service is running!", "status": "healthy"}
+    return RedirectResponse(url="/static/index.html")
 
 if __name__ == "__main__":
     print("=" * 60)