Update Dockerfile

Dockerfile

@@ -1,8 +1,6 @@
-# This Dockerfile uses your original, fast-building pattern.
-
 FROM python:3.11-slim
 
-# Install system dependencies
+# Install build tools for llama.cpp
 RUN apt-get update && apt-get install -y \
     git curl build-essential cmake \
     && rm -rf /var/lib/apt/lists/*
@@ -17,24 +15,21 @@ ENV TRANSFORMERS_CACHE=/app/.cache \
     HF_HOME=/app/.cache \
     CHROMADB_DISABLE_TELEMETRY=true
 
-# Pre-install the specific, known-working version of llama-cpp-python
-# This version matches the tool version used to create your new GGUF file.
-RUN pip install --no-cache-dir llama-cpp-python==0.2.61
+# 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
 
-# Install the rest of the dependencies
+# Install all remaining dependencies
 COPY requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt
 
-# Copy the application code
+# Copy app files and data
 COPY . .
 
-# <-- UPDATED: Download your new, compatible GGUF model from the new repo
+# Download your quantized GGUF model
 RUN curl -fL -o /app/phi1.5_dop_q4_k_m.gguf \
     https://huggingface.co/Kalpokoch/Phi1.5QuantizedFineTuned/resolve/main/phi1.5_dop_q4_k_m.gguf \
     && echo "✅ Model downloaded."
 
-# Expose the application port
 EXPOSE 7860
 
-# Run the FastAPI application
-CMD ["uvicorn", "app.app:app", "--host", "0.0.0.0", "--port", "7860"]
+CMD ["uvicorn", "app.app:app", "--host", "0.0.0.0", "--port", "7860"]