freeapi / Dockerfile
xtom0's picture
Simplify to single-model chat app: llama3.1:8b only. Add /api/chat SSE streaming, chatbot UI, remove model selection/download UI, build-time model pull
946d512
Raw
History Blame Contribute Delete
835 Bytes
FROM python:3.11-slim
RUN apt-get update && apt-get install -y curl zstd && \
curl -fsSL https://ollama.com/install.sh | sh && \
rm -rf /var/lib/apt/lists/*
WORKDIR /app
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt
COPY . .
RUN ollama serve > /tmp/ollama-build.log 2>&1 & \
sleep 5 && \
echo "Pulling llama3.1:8b..." && \
ollama pull llama3.1:8b 2>&1 || echo "WARNING: Build-time pull failed, will retry at runtime"
EXPOSE 7860
CMD ollama serve > /tmp/ollama.log 2>&1 & \
sleep 3 && \
if ! ollama list 2>/dev/null | grep -q llama3.1; then \
echo "llama3.1:8b not found, pulling in background..." && \
nohup ollama pull llama3.1:8b > /tmp/ollama-pull.log 2>&1 & \
fi && \
echo "Starting app..." && \
uvicorn app:app --host 0.0.0.0 --port 7860