Update Dockerfile

Dockerfile

@@ -1,32 +1,27 @@
-# Use lightweight Python
-FROM python:3.9-slim
+FROM python:3.10-slim
 
-# Set working directory
-WORKDIR /code
+ENV PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1 \
+    PIP_NO_CACHE_DIR=1 \
+    PORT=7860
 
-# 1. FIX: Install System Build Tools (Required for llama-cpp-python)
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    cmake \
-    gcc \
-    && rm -rf /var/lib/apt/lists/*
+WORKDIR /app
 
-# Copy requirements
-COPY ./requirements.txt /code/requirements.txt
+# Runtime deps (libgomp helps llama-cpp wheels / OpenMP)
+RUN apt-get update \
+    ; apt-get install -y --no-install-recommends libgomp1 ca-certificates \
+    ; rm -rf /var/lib/apt/lists/*
 
-# 2. Install the easy packages
-RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+# Install deps first (better layer caching)
+COPY requirements.txt ./
+RUN pip install --upgrade pip \
+    ; pip install -r requirements.txt
 
-# 3. Install AI Engine (Now supports compiling if needed)
-RUN pip install llama-cpp-python \
-    --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
+# Copy app and model files
+COPY app.py ./
+COPY *.gguf ./
 
-# Copy the rest of the app
-COPY . .
+EXPOSE 7860
 
-# Permissions for Hugging Face
-RUN mkdir -p /code/.cache && chmod -R 777 /code/.cache
-ENV TRANSFORMERS_CACHE=/code/.cache
-
-# Start App
-CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]
+# HuggingFace expects the app to listen on 0.0.0.0:7860
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860", "--proxy-headers", "--forwarded-allow-ips", "*"]