Configures OpenAI's embedding API as your GrepAI provider when you want high-quality semantic search without running local models. You get text-embedding-3-small (recommended, $0.00002/1K tokens) or text-embedding-3-large for maximum accuracy at higher cost. The tradeoff is straightforward: your code gets sent to OpenAI servers, so this isn't for sensitive codebases. Setup is just adding your API key to the config and setting parallelism based on your rate limit tier. Good for teams that want consistent embeddings without maintaining infrastructure, and the cost is genuinely low for most codebases (around $0.10 to index 1000 files). If privacy matters more than convenience, stick with Ollama instead.
npx skills add https://github.com/yoanbernabeu/grepai-skills --skill grepai-embeddings-openai