Fix: Remove duplicate torch, remove healthcheck, add logging

Dockerfile

@@ -19,16 +19,18 @@ ENV HOME=/home/user \
 # Set working directory for user
 WORKDIR $HOME/app
 
-# Install torch CPU first (smaller download)
+# Install torch CPU first (smaller download ~200MB vs 2GB)
 RUN pip install --no-cache-dir --upgrade pip && \
-    pip install --no-cache-dir torch --index-url https://download.pytorch.org/whl/cpu
+    pip install --no-cache-dir torch --index-url https://download.pytorch.org/whl/cpu && \
+    echo "Torch installed successfully"
 
 # Copy requirements and install Python dependencies
 COPY --chown=user requirements.txt .
-RUN pip install --no-cache-dir -r requirements.txt
+RUN pip install --no-cache-dir -r requirements.txt && \
+    echo "All requirements installed successfully"
 
 # Pre-download the lightweight embedding model to avoid timeout at startup
-RUN python -c "from sentence_transformers import SentenceTransformer; SentenceTransformer('all-MiniLM-L6-v2')"
+RUN python -c "from sentence_transformers import SentenceTransformer; print('Downloading model...'); SentenceTransformer('all-MiniLM-L6-v2'); print('Model downloaded!')"
 
 # Copy application files
 COPY --chown=user . .
@@ -39,15 +41,10 @@ RUN mkdir -p /tmp/chroma_db /tmp/data_cache
 # Set environment variables
 ENV PYTHONUNBUFFERED=1
 ENV SPACE_ID=1
-ENV GRADIO_SERVER_NAME=0.0.0.0
-ENV GRADIO_SERVER_PORT=7860
 
 # Expose port for Streamlit (HuggingFace Spaces uses 7860)
 EXPOSE 7860
 
-# Health check - increase timeout
-HEALTHCHECK --interval=30s --timeout=30s --start-period=60s --retries=3 \
-    CMD curl --fail http://localhost:7860/_stcore/health || exit 1
-
-# Run Streamlit
-CMD ["streamlit", "run", "streamlit_app.py", "--server.port=7860", "--server.address=0.0.0.0", "--server.enableCORS=false", "--server.enableXsrfProtection=false"]
+# No healthcheck - let HF Spaces handle it
+# Run Streamlit with logging
+CMD ["streamlit", "run", "streamlit_app.py", "--server.port=7860", "--server.address=0.0.0.0", "--server.enableCORS=false", "--server.enableXsrfProtection=false", "--logger.level=info"]

requirements.txt

@@ -9,7 +9,7 @@ openai>=1.12.0
 # Embeddings and Vector Store
 sentence-transformers>=2.2.0
 transformers>=4.35.0
-torch
+# torch installed separately in Dockerfile with CPU-only version
 chromadb>=0.4.0
 qdrant-client>=1.7.0