Update Dockerfile

Dockerfile

@@ -1,33 +1,56 @@
-# Use a Python base image
-FROM python:3.9-slim-buster
+# Use Ubuntu as base image for better Ollama compatibility
+FROM ubuntu:22.04
 
-# Set working directory inside the container
+# Prevent interactive prompts during package installation
+ENV DEBIAN_FRONTEND=noninteractive
+
+# Set working directory
 WORKDIR /app
 
-# Create a virtual environment and activate it.
-# This ensures a clean and isolated environment for your dependencies.
-RUN python -m venv /opt/venv
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    curl \
+    python3 \
+    python3-pip \
+    python3-venv \
+    wget \
+    ca-certificates \
+    && rm -rf /var/lib/apt/lists/*
+
+# Create and activate virtual environment
+RUN python3 -m venv /opt/venv
 ENV PATH="/opt/venv/bin:$PATH"
 
-# Create a dedicated directory for Hugging Face cache and ensure permissions.
-# This prevents 'PermissionError' issues when downloading models by directing
-# Hugging Face to a location with guaranteed write access.
-ENV HF_HOME=/app/.hf_cache
-RUN mkdir -p ${HF_HOME} && chmod -R 777 ${HF_HOME}
-
-# Install dependencies from requirements.txt into the virtual environment
+# Install Python dependencies
 COPY requirements.txt .
-RUN pip install --no-cache-dir -r requirements.txt
+RUN pip install --no-cache-dir --upgrade pip && \
+    pip install --no-cache-dir -r requirements.txt
+
+# Install Ollama
+RUN curl -fsSL https://ollama.ai/install.sh | sh
 
-RUN python -c "from transformers import AutoTokenizer, AutoModelForMaskedLM; AutoTokenizer.from_pretrained('boltuix/NeuroBERT-Tiny'); AutoModelForMaskedLM.from_pretrained('boltuix/NeuroBERT-Tiny')"
+# Create ollama user and directories
+RUN useradd -m -s /bin/bash ollama && \
+    mkdir -p /home/ollama/.ollama && \
+    chown -R ollama:ollama /home/ollama/.ollama
 
-# Copy your application code
+# Copy application files
 COPY app.py .
+COPY startup.sh .
+
+# Make startup script executable
+RUN chmod +x startup.sh
+
+# Set environment variables
+ENV OLLAMA_HOST=0.0.0.0:11434
+ENV OLLAMA_MODELS=/home/ollama/.ollama/models
+
+# Expose ports
+EXPOSE 7860 11434
 
-# Expose the port your API will run on
-# Hugging Face Spaces typically uses port 8000 for custom Docker builds
-EXPOSE 7860
+# Health check
+HEALTHCHECK --interval=30s --timeout=30s --start-period=60s --retries=3 \
+    CMD curl -f http://localhost:7860/health || exit 1
 
-# Command to start the FastAPI application using Uvicorn as a Python module.
-# This is more robust as it explicitly invokes 'python' to run the 'uvicorn' module.
-CMD ["python", "-m", "uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]
+# Start both Ollama server and FastAPI app
+CMD ["./startup.sh"]