fix(lama.cpp): Add prebuilt lamma.cpp to docker

Dockerfile

@@ -1,34 +1,38 @@
-# Use full Python image for compatibility with prebuilt wheels
+# Use full Python 3.12 image for maximum compatibility
 FROM python:3.12
 
-# Set workdir
+# Set working directory
 WORKDIR /app
 
-# Install basic system dependencies
+# Install system dependencies needed for llama-cpp-python and general Python packages
 RUN apt-get update && apt-get install -y \
     wget \
     curl \
     git \
+    build-essential \
+    cmake \
     && rm -rf /var/lib/apt/lists/*
 
 # Upgrade pip
 RUN pip install --upgrade pip
 
-# # 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 prebuilt llama-cpp-python (CPU) and Hugging Face hub for from_pretrained()
+RUN pip install --no-cache-dir \
+    llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu \
+    huggingface-hub
 
-# Copy project requirements and install
+# Copy requirements and install other dependencies
 COPY ./requirements.txt /app/requirements.txt
 RUN pip install --no-cache-dir -r requirements.txt
 
-# Copy application code
+# Copy the application code
 COPY . /app
 
-# Ensure models folder exists (optional)
+# Ensure models folder exists (optional, can store HF cache here)
 RUN mkdir -p /app/models
 
-# Expose port (change if needed)
+# Expose FastAPI port
 EXPOSE 7860
 
-# Start FastAPI app with Uvicorn workers
+# Use Gunicorn with Uvicorn workers for production
 CMD ["gunicorn", "app.main:app", "-k", "uvicorn.workers.UvicornWorker", "--bind", "0.0.0.0:7860", "--workers", "2"]

requirements.txt

@@ -72,7 +72,6 @@ language_data==1.3.0
 lazy_loader==0.4
 libclang==18.1.1
 librosa==0.11.0
-llama_cpp_python==0.3.16
 llvmlite==0.44.0
 loguru==0.7.3
 marisa-trie==1.2.1