Update Dockerfile

Dockerfile

@@ -1,35 +1,37 @@
 FROM python:3.11-slim
 
-# Install build tools for llama.cpp
+# Install required system dependencies
 RUN apt-get update && apt-get install -y \
     git curl build-essential cmake \
     && rm -rf /var/lib/apt/lists/*
 
+# Set working directory
 WORKDIR /app
 
-# Create writable directories
+# Create writable directories for caches and the database
 RUN mkdir -p /app/.cache /app/vector_database && chmod -R 777 /app
 
-# Set environment variables
+# Set environment variables for caching
 ENV TRANSFORMERS_CACHE=/app/.cache \
     HF_HOME=/app/.cache \
     CHROMADB_DISABLE_TELEMETRY=true
 
-# Install llama-cpp-python runtime-only version (0.2.75 for GGUF v3 inference)
-RUN pip install --no-cache-dir llama-cpp-python==0.2.75
+# Pre-install the specific, known-working version of llama-cpp-python
+RUN pip install --no-cache-dir llama-cpp-python==0.2.61
 
-# Install all remaining dependencies
+# Install other dependencies from requirements.txt
 COPY requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt
 
-# Copy app files and data
+# Copy the application code into the container
 COPY . .
 
-# Download your quantized GGUF model
-RUN curl -fL -o /app/dop-phi-1.5-Q4_K_M.gguf \
-    https://huggingface.co/Kalpokoch/Phi1.5QuantizedFineTuned/resolve/main/dop-phi-1.5-Q4_K_M.gguf \
-    && echo "✅ Model downloaded."
+# Download your fine-tuned TinyLlama GGUF model
+RUN curl -L -o /app/tinyllama_dop_q4_k_m.gguf \
+    https://huggingface.co/Kalpokoch/FinetunedQuantizedTinyLama/resolve/main/tinyllama_dop_q4_k_m.gguf
 
+# Expose the application port
 EXPOSE 7860
 
-CMD ["uvicorn", "app.app:app", "--host", "0.0.0.0", "--port", "7860"]
+# Run the FastAPI application using uvicorn
+CMD ["uvicorn", "app.app:app", "--host", "0.0.0.0", "--port", "7860"]