Dockerfile

# ────────────────────────────────────────────────────────────────────────────
# Dockerfile for FastAPI + RAG (with pre-created writable chroma_db_users)
# ────────────────────────────────────────────────────────────────────────────

FROM python:3.10-slim

# 1) Install system packages for building any native extensions
RUN apt-get update && \
    apt-get install -y --no-install-recommends \
        build-essential \
        git \
    && rm -rf /var/lib/apt/lists/*

WORKDIR /app

# 2) Copy requirements.txt first so pip layers can be cached
COPY requirements.txt .

# 3) Install PyTorch CPU + the rest of your Python deps
RUN pip install --upgrade pip && \
    pip install --no-cache-dir torch==2.1.2+cpu --index-url https://download.pytorch.org/whl/cpu && \
    pip install --no-cache-dir -r requirements.txt

# 4) Pre-create the HF cache folder and chroma_db_users folder, and make them writable
RUN mkdir -p /app/hf_cache && chmod 777 /app/hf_cache && \
    mkdir -p /app/chroma_db_users && chmod 777 /app/chroma_db_users

# 5) Tell all HuggingFace libs to use /app/hf_cache instead of .cache
ENV HF_HOME=/app/hf_cache
ENV TRANSFORMERS_CACHE=/app/hf_cache
ENV HF_DATASETS_CACHE=/app/hf_cache
ENV HF_METRICS_CACHE=/app/hf_cache
ENV SENTENCE_TRANSFORMERS_CACHE=/app/hf_cache

# 6) Copy the rest of your application code
COPY . .

# 7) Expose the default HF Spaces port (7860)
EXPOSE 7860

# 8) Launch Uvicorn against app.py (which defines `app = FastAPI()`)
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]