Install and configure Ollama for local embeddings with GrepAI. Use this skill when setting up private, local embedding generation.

Ollama Setup for GrepAI 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. When to Use This Skill Setting up GrepAI with local, private embeddings Installing Ollama for the first time Choosing and downloading embedding models Troubleshooting Ollama connection issues Why Ollama? Benefit Description 🔒 Privacy Code never leaves your machine 💰 Free No API costs ⚡ Fast Local processing, no network latency 🔌 Offline Works without internet Installation macOS (Homebrew) macOS (Direct Download) 1. Download from [ollama.com](https://ollama.com) 2. Open the .dmg and drag to Applications 3. Launch Ollama from Applications Linux Windows 1. Download installer from [ollama.com](https://ollama.com/download/windows) 2. Run the installer 3. Ollama starts automatically as a service Downloading Embedding Models GrepAI requires an embedding model to convert code into vectors. Recommended Model: nomic embed text Specifications: Dimensions: 768 Size: ~274 MB Performance: Excellent for code search Language: English optimized Alternative Models Model Dimensions Size Best For nomic embed text 768 274 MB General code search nomic embed text v2 moe 768 500 MB Multilingual codebases bge m3 1024 1.2 GB Large codebases mxbai embed large 1024 670 MB Maximum accuracy Verifying Installation Check Ollama is Running List Downloaded Models Test Embedding Generation Configuring GrepAI for Ollama 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 . Running Ollama Foreground (Development) Background (macOS/Linux) Check Status Resource Considerations Memory Usage Embedding models load into RAM: nomic embed text : ~500 MB RAM bge m3 : ~1.5 GB RAM mxbai embed large : ~1 GB RAM CPU vs GPU Ollama uses CPU by default. For faster embeddings: macOS: Uses Metal (Apple Silicon) automatically Linux/Windows: Install CUDA for NVIDIA GPU support Common Issues ❌ Problem: connection refused to localhost:11434 ✅ Solution: Start Ollama: ❌ Problem: Model not found ✅ Solution: Pull the model first: ❌ Problem: Slow embedding generation ✅ Solution: Use a smaller model Ensure Ollama is using GPU (check ollama ps ) Close other memory intensive applications ❌ Problem: Out of memory ✅ Solution: Use a smaller model or increase system RAM Best Practices 1. Start Ollama before GrepAI: Ensure ollama serve is running 2. Use recommended model: nomic embed text offers best balance 3. Keep Ollama running: Leave it as a background service 4. Update periodically: ollama pull nomic embed text for updates Output Format After successful setup:

grepai-ollama-setup