grepai-embeddings-ollama
Keep your code-search embeddings on your machine.
What it does
Configures GrepAI to generate code-search embeddings locally with Ollama.
When to use it
Use when setting up private local embeddings, choosing an Ollama model, optimizing performance, or troubleshooting connections.
How to use it
Give it a project to configure; it sets GrepAI's embedding provider, model, and local Ollama endpoint.
What you provide
- An existing project
Uses
Good to know
- cannot be undone: .grepai/index.gob
What you need · 2
Requires Ollama installed and running, with an embedding model downloaded; the skill also shows setup commands.
Requires sufficient RAM for the chosen model; the recommended nomic-embed-text model is listed as needing about 500 MB.
Access · 3
This skill
.grepai/index.gob
Deletes the existing search index (irreversible)
Ollama
Starts Ollama and downloads a model
Sends a local embedding test