feat(python): Change Python version to 3.11-bullseye for llama-cpp-python prebuilt wheel

Dockerfile

@@ -1,36 +1,34 @@
-FROM python:3.12-slim
+# Use full Python image for compatibility with prebuilt wheels
+FROM python:3.11-bullseye
 
-# Create non-root user
-RUN useradd -m -u 1000 user
-USER user
-ENV PATH="/home/user/.local/bin:$PATH"
+# Set workdir
+WORKDIR /app
 
-# Install system dependencies
-USER root
+# Install basic system dependencies
 RUN apt-get update && apt-get install -y \
-    build-essential \
-    cmake \
     wget \
     curl \
     git \
     && rm -rf /var/lib/apt/lists/*
 
-# Back to non-root
-USER user
-WORKDIR /app
-
 # Upgrade pip
 RUN pip install --upgrade pip
 
-# Install llama-cpp prebuilt wheel (FAST, no compiling)
+# Install llama-cpp-python prebuilt wheel (CPU)
 RUN pip install llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
 
-# Install project requirements
-COPY --chown=user ./requirements.txt requirements.txt
+# Copy project requirements and install
+COPY ./requirements.txt /app/requirements.txt
 RUN pip install --no-cache-dir -r requirements.txt
 
 # Copy application code
-COPY --chown=user . /app
+COPY . /app
+
+# Ensure models folder exists (optional)
+RUN mkdir -p /app/models
+
+# Expose port (change if needed)
+EXPOSE 7860
 
-# Start app
+# Start FastAPI app with Uvicorn workers
 CMD ["gunicorn", "app.main:app", "-k", "uvicorn.workers.UvicornWorker", "--bind", "0.0.0.0:7860", "--workers", "2"]

models.sh

@@ -1,9 +0,0 @@
-#!/bin/bash
-echo "Creating models directory..."
-mkdir -p /app/models/
-
-echo "Downloading Qwen3-8B-GGUF model..."
-wget -c https://huggingface.co/Qwen/Qwen3-8B-GGUF/resolve/main/Qwen3-8B-Q5_K_M.gguf?download=true \
-    -O /app/models/Qwen3-8B-Q5_K_M.gguf
-
-echo "All models downloaded!"