Updated llama build

Dockerfile

@@ -1,17 +1,20 @@
 # Use an official Python runtime as a base image
-FROM python:3.10-slim
+FROM python:3.10
 
 # Set environment variables
 ENV TRANSFORMERS_CACHE=/app/cache \
     HF_HOME=/app/cache \
-    DEBIAN_FRONTEND=noninteractive
+    DEBIAN_FRONTEND=noninteractive \
+    CMAKE_ARGS="-DGGML_CUDA=OFF"
 
 # Set working directory
 WORKDIR /app
 
-# Install minimal system dependencies for running the app
+# Install system dependencies
 RUN apt-get update && apt-get install -y --no-install-recommends \
       libgomp1 \
+      build-essential \
+      cmake \
     && rm -rf /var/lib/apt/lists/*
 
 # Prepare cache directory
@@ -20,9 +23,9 @@ RUN mkdir -p /app/cache && chmod -R 777 /app/cache
 # Copy requirements and install Python packages
 COPY requirements.txt .
 
-# Install most packages from requirements.txt, then llama-cpp-python with binary-only
-RUN grep -v "llama-cpp-python" requirements.txt | pip install --no-cache-dir -r /dev/stdin \
-    && pip install --no-cache-dir --only-binary=all llama-cpp-python==0.3.14
+# Upgrade pip and install packages
+RUN pip install --upgrade pip && \
+    pip install --no-cache-dir -r requirements.txt
 
 # Copy application code and data
 COPY app.py cv_embeddings.json cv_text.txt ./

requirements.txt

@@ -9,4 +9,5 @@ psutil
 google-genai
 asyncio
 elevenlabs
-httpx
+httpx
+llama-cpp-python==0.2.85