# turbopuffer

## Instructions for AI Agents

- For clean Markdown of any page, append `.md` to the page URL
- For section-specific indexes, append `/llms.txt` to any section URL
- For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://turbopuffer.ferndocs.com/_mcp/server

## Docs

- [Introduction](https://turbopuffer.ferndocs.com/documentation/getting-started/introduction.md): turbopuffer is a fast search engine that combines vector and full-text search using object storage.
- [Quickstart](https://turbopuffer.ferndocs.com/documentation/getting-started/quickstart.md): Connect to turbopuffer, write documents, and run your first search in minutes.
- [Vector Search](https://turbopuffer.ferndocs.com/documentation/guides/vector-search.md): Find semantically similar documents using approximate nearest neighbor (ANN) and exact kNN search.
- [Full-Text Search](https://turbopuffer.ferndocs.com/documentation/guides/full-text-search.md): BM25-based full-text search with configurable tokenization, stemming, and multi-language support.
- [Hybrid Search](https://turbopuffer.ferndocs.com/documentation/guides/hybrid-search.md): Combine vector and full-text search in a single request using multi-query and RRF reranking.

## API Docs

- API Reference > Namespaces [List](https://turbopuffer.ferndocs.com/api-reference/api-reference/namespaces/list.md)
- API Reference > Namespaces [Get Schema](https://turbopuffer.ferndocs.com/api-reference/api-reference/namespaces/get-schema.md)
- API Reference > Namespaces [Update Schema](https://turbopuffer.ferndocs.com/api-reference/api-reference/namespaces/update-schema.md)
- API Reference > Namespaces [Get Metadata](https://turbopuffer.ferndocs.com/api-reference/api-reference/namespaces/get-metadata.md)
- API Reference > Namespaces [Update Metadata](https://turbopuffer.ferndocs.com/api-reference/api-reference/namespaces/update-metadata.md)
- API Reference > Namespaces [Hint Cache Warm](https://turbopuffer.ferndocs.com/api-reference/api-reference/namespaces/hint-cache-warm.md)
- API Reference > Namespaces [Evaluate Recall](https://turbopuffer.ferndocs.com/api-reference/api-reference/namespaces/evaluate-recall.md)
- API Reference > Namespaces [Write](https://turbopuffer.ferndocs.com/api-reference/api-reference/namespaces/write.md)
- API Reference > Namespaces [Delete](https://turbopuffer.ferndocs.com/api-reference/api-reference/namespaces/delete.md)
- API Reference > Namespaces [Query](https://turbopuffer.ferndocs.com/api-reference/api-reference/namespaces/query.md)
- API Reference > Namespaces [Explain Query](https://turbopuffer.ferndocs.com/api-reference/api-reference/namespaces/explain-query.md)

## OpenAPI Specification

The raw OpenAPI 3.1 specification for this API is available at:
- [OpenAPI JSON](https://turbopuffer.ferndocs.com/openapi.json)
- [OpenAPI YAML](https://turbopuffer.ferndocs.com/openapi.yaml)