Update Dockerfile

Dockerfile

@@ -1,19 +1,26 @@
-FROM python:3.10-slim
+# Use Python base image (with CUDA if GPU needed)
+FROM python:3.11-slim
 
-WORKDIR /home/user/app
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    cmake \
+    wget \
+    git \
+    && rm -rf /var/lib/apt/lists/*
 
-RUN pip install --no-cache-dir huggingface_hub
+# Set working directory
+WORKDIR /app
 
-# Install llama-cpp-python with OpenAI-style server support
-RUN pip install --no-cache-dir \
-    "llama-cpp-python[server]==0.2.30" \
-    --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
+# Copy your model and code into the container
+COPY . /app
 
-# Download model
-RUN python3 -c "from huggingface_hub import hf_hub_download; \
-    hf_hub_download(repo_id='cakebut/askvox_api', filename='llama-2-7b-chat.Q4_K_M.gguf', local_dir='.', local_dir_use_symlinks=False)"
+# Install Python dependencies
+RUN pip install --no-cache-dir --upgrade pip
+RUN pip install --no-cache-dir -r requirements.txt
 
-RUN mv llama-2-7b-chat.Q4_K_M.gguf model.gguf
+# Expose port for HF Space
+EXPOSE 7860
 
-# Start OpenAI-compatible server (fixed single-line CMD)
-CMD ["python3", "-m", "llama_cpp.server", "--model", "model.gguf", "--host", "0.0.0.0", "--port", "7860", "--chat_format", "llama-2", "--n_ctx", "2048"]
+# Command to run your app
+CMD ["python", "app.py"]