dd

Dockerfile

@@ -1,24 +1,24 @@
-FROM python:3.10-slim
+FROM ollama/ollama:latest
 
-# Install system dependencies
+# Install Python and dependencies
 RUN apt-get update && apt-get install -y \
+    python3 \
+    python3-pip \
+    python3-venv \
     curl \
-    ca-certificates \
     && rm -rf /var/lib/apt/lists/*
 
-# Install Ollama (more robust way)
-RUN curl -fsSL https://ollama.ai/install.sh | sh
-
-# Create Ollama directory with proper permissions (important for HF)
-RUN mkdir -p /root/.ollama && chmod 777 /root/.ollama
-
 WORKDIR /app
 
-# Copy requirements first (better caching)
+# Create virtual environment (safer)
+RUN python3 -m venv /opt/venv
+ENV PATH="/opt/venv/bin:$PATH"
+
+# Copy requirements and install
 COPY requirements.txt .
 RUN pip install --no-cache-dir --upgrade -r requirements.txt
 
-# Copy the rest of the files
+# Copy app files
 COPY . .
 
 # Make start script executable
@@ -26,4 +26,5 @@ RUN chmod +x start.sh
 
 EXPOSE 7860
 
+# Use our start script
 CMD ["./start.sh"]

start.sh

@@ -1,38 +1,29 @@
 #!/bin/bash
 
 echo "=== [HF Space] Starting Ollama + FastAPI ==="
-echo "Current time: $(date)"
 
-# Optimization
-export OMP_NUM_THREADS=4
-export MKL_NUM_THREADS=4
-export OLLAMA_HOST=0.0.0.0
-
-# Start Ollama
+# Start Ollama in background (official image already has it)
 echo "Starting Ollama server..."
 ollama serve &
-OLLAMA_PID=$!
+sleep 5
 
 # Wait for Ollama
-echo "Waiting for Ollama to start..."
-for i in {1..60}; do
-    if curl -s http://localhost:11434/api/tags >/dev/null 2>&1; then
-        echo "✅ Ollama is ready!"
+echo "Waiting for Ollama..."
+for i in {1..40}; do
+    if curl -s http://127.0.0.1:11434/api/tags >/dev/null; then
+        echo "✅ Ollama ready!"
         break
     fi
     sleep 3
-    if [ $i -eq 30 ]; then
-        echo "⚠️ Taking long... still waiting"
-    fi
 done
 
-# Pull model
+# Pull model (only first time)
 if ! ollama list | grep -q "tinyllama"; then
-    echo "📥 Downloading tinyllama (first build only - this takes time)..."
+    echo "📥 Pulling tinyllama... (this can take 2-5 mins on first build)"
     ollama pull tinyllama
 else
-    echo "✅ Model tinyllama already exists"
+    echo "✅ tinyllama already available"
 fi
 
-echo "🚀 Starting FastAPI on port ${PORT:-7860}"
+echo "🚀 Starting FastAPI..."
 uvicorn app:app --host 0.0.0.0 --port ${PORT:-7860} --workers 2