Update Dockerfile

Dockerfile

@@ -1,30 +1,25 @@
-# Base image with Python
+# Base image
 FROM python:3.11-slim
 
 WORKDIR /app
 
-# Install system dependencies + Build tools for llama-cpp
-RUN apt-get update && apt-get install -y \
-    wget \
-    gcc \
-    g++ \
-    make \
-    cmake \
-    && rm -rf /var/lib/apt/lists/*
+# We still need wget for the model, but we can skip the heavy compilers!
+RUN apt-get update && apt-get install -y wget && rm -rf /var/lib/apt/lists/*
 
-# Install Python dependencies
-RUN pip install --no-cache-dir llama-cpp-python fastapi uvicorn[standard] requests
+# 1. Install pre-built llama-cpp-python (CPU version)
+# This bypasses the "Building wheel..." stage entirely
+RUN pip install llama-cpp-python \
+    --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
 
-# Create models folder
-RUN mkdir -p ./models
+# 2. Install your other web tools
+RUN pip install --no-cache-dir fastapi uvicorn[standard] requests
 
-# Download GPT-OSS-20B model (The brain you chose!)
+# 3. Setup models
+RUN mkdir -p ./models
 RUN wget -q -O ./models/gpt-oss-20b-Q3_K_M.gguf \
     https://huggingface.co/unsloth/gpt-oss-20b-GGUF/resolve/main/gpt-oss-20b-Q3_K_M.gguf
 
-# Copy your app code
 COPY app.py ./app.py
 
 EXPOSE 8000
-
 CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "8000"]