grepai-ollama-setup

This skill covers installing and configuring Ollama as the local embedding provider for GrepAI. Ollama enables 100% private code search where your code never leaves your machine. GrepAI requires an embedding model to convert code into vectors. Specifications: After installing Ollama, configure GrepAI to use it: This is the default configuration when you run grepai init , so no changes are needed if using nomic-embed-text . Embedding models load into RAM: Ollama uses CPU by default. For faster embeddings: ❌ Problem: connection refused to localhost:11434 ✅ Solution: Start Ollama: ❌ Problem: Model not found ✅ Solution: Pull the model first: ❌ Problem: Slow embedding generation ✅ Solution: ❌ Problem: Out of memory ✅ Solution: Use a smaller model or increase system RAM After successful setup: - Setting up GrepAI with local, private embeddings - Installing Ollama for the first time - Choosing and downloading embedding models - Troubleshooting Ollama connection issues - Download from ollama.com - Open the .dmg and drag to Applications - Launch Ollama from Applications - Download installer from ollama.com - Run the installer - Ollama starts automatically as a service - Dimensions: 768 - Size: ~274 MB - Performance: Excellent for code search - Language: English-optimized - nomic-embed-text : ~500 MB RAM - bge-m3 : ~1.5 GB RAM - mxbai-embed-large : ~1 GB RAM - macOS: Uses Metal (Apple...