grepai-embeddings-ollama

This skill covers using Ollama as the embedding provider for GrepAI, enabling 100% private, local code search. Configuration: Best for codebases with non-English comments/documentation. Configuration: Best for large, complex codebases where accuracy is critical. Configuration: Configuration: Models load into RAM. Ensure sufficient memory: Ollama automatically uses: Check GPU usage: By default, Ollama unloads models after 5 minutes of inactivity. Keep loaded: Ollama app runs automatically on login. Run Ollama on a powerful server and connect remotely: ❌ Problem: Connection refused ✅ Solution: ❌ Problem: Model not found ✅ Solution: ❌ Problem: Slow embedding generation ✅ Solutions: ❌ Problem: Out of memory ✅ Solutions: ❌ Problem: Embeddings differ after model update ✅ Solution: Re-index after model updates: Successful Ollama configuration: - Setting up private, local embeddings - Choosing the right Ollama model - Optimizing Ollama performance - Troubleshooting Ollama connection issues - Ollama installed and running - An embedding model downloaded - macOS: Metal (Apple Silicon) - Linux/Windows: CUDA (NVIDIA GPUs) - Use a smaller model ( nomic-embed-text ) - Ensure GPU is being used ( ollama ps ) - Close memory-intensive applications - Consider a remote server with better hardware - Use a smaller model - Close other applications - Upgrade RAM - Use remote Ollama server - Start with...