Update Dockerfile

Dockerfile

@@ -2,18 +2,34 @@ FROM python:3.10-slim
 
 WORKDIR /app
 
-RUN apt-get update && apt-get install -y \
+ENV PYTHONUNBUFFERED=1 \
+    PIP_NO_CACHE_DIR=1 \
+    HF_HOME=/data/.huggingface \
+    TRANSFORMERS_CACHE=/data/.huggingface \
+    XDG_CACHE_HOME=/data/.cache
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
     curl \
+    git \
+    ca-certificates \
+    build-essential \
     && rm -rf /var/lib/apt/lists/*
 
 COPY requirements.txt .
+
+RUN pip install --upgrade pip
+
+# CUDA wheels para llama.cpp
+RUN pip install \
+    --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cu124
+
 RUN pip install --no-cache-dir -r requirements.txt
 
-COPY app.py .
+COPY . .
 
 EXPOSE 7860
 
 HEALTHCHECK --interval=30s --timeout=10s --start-period=120s --retries=3 \
     CMD curl -f http://localhost:7860/health || exit 1
 
-CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]
+CMD ["uvicorn","app:app","--host","0.0.0.0","--port","7860"]