feat: Kodingo inference service with Qwen2.5-Coder-7B

Dockerfile

@@ -0,0 +1,12 @@
+FROM ollama/ollama:latest
+
+# Install curl for healthcheck
+RUN apt-get update && apt-get install -y curl && rm -rf /var/lib/apt/lists/*
+
+# Copy startup script
+COPY start.sh /start.sh
+RUN chmod +x /start.sh
+
+EXPOSE 11434
+
+CMD ["/start.sh"]

README.md

@@ -1,11 +1,16 @@
 ---
 title: Kodingo Infer
-emoji: 🐠
+emoji: 🧠
 colorFrom: blue
-colorTo: pink
+colorTo: cyan
 sdk: docker
 pinned: false
-license: mit
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Kodingo Inference Service
+
+Runs Qwen2.5-Coder-7B via Ollama for Kodingo decision memory inference.
+
+## Endpoint
+
+`POST /api/generate` — Ollama generate endpoint

start.sh

@@ -0,0 +1,18 @@
+#!/bin/bash
+
+# Start Ollama in background
+ollama serve &
+
+# Wait for Ollama to be ready
+echo "Waiting for Ollama to start..."
+until curl -s http://localhost:11434/api/tags > /dev/null 2>&1; do
+  sleep 2
+done
+
+echo "Ollama ready. Pulling Qwen2.5-Coder-7B..."
+ollama pull qwen2.5-coder:7b
+
+echo "Model ready. Kodingo inference service is live."
+
+# Keep container running
+wait