Update Dockerfile

Dockerfile

@@ -1,31 +1,30 @@
-FROM python:3.11-slim
+FROM python:3.10-slim
 
 WORKDIR /app
 
-# Install dependencies for building llama.cpp with HTTP server support
+# Install system dependencies
 RUN apt-get update && apt-get install -y \
-    build-essential wget git cmake libcurl4-openssl-dev \
+    build-essential \
+    cmake \
+    wget \
     && rm -rf /var/lib/apt/lists/*
 
-# Clone llama.cpp
-RUN git clone https://github.com/ggerganov/llama.cpp
+# Copy requirements and install Python dependencies
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
 
-# Build llama.cpp with CURL enabled
-WORKDIR /app/llama.cpp
-RUN cmake -B build -DLLAMA_CURL=ON && cmake --build build --config Release
-
-# Back to /app
-WORKDIR /app
+# Download the model file
+RUN wget -O capybarahermes-2.5-mistral-7b.Q5_K_M.gguf \
+    https://huggingface.co/TheBloke/CapybaraHermes-2.5-Mistral-7B-GGUF/resolve/main/capybarahermes-2.5-mistral-7b.Q5_K_M.gguf
 
-# Copy Python app
+# Copy application code
 COPY app.py .
 
-# Download model file
-RUN wget -O /app/model.gguf \
-    https://huggingface.co/TheBloke/CapybaraHermes-2.5-Mistral-7B-GGUF/resolve/main/capybarahermes-2.5-mistral-7b.Q5_K_M.gguf
+# Expose Streamlit port
+EXPOSE 8501
 
-# Expose the llama.cpp HTTP server port
-EXPOSE 7860
+# Health check
+HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
 
-# Run the HTTP server
-CMD ["/app/llama.cpp/build/bin/llama-server", "-m", "/app/model.gguf", "-c", "2048", "-t", "2", "--host", "0.0.0.0", "--port", "7860"]
+# Run the application
+CMD ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0"]