# Infino

> Infino is an open-source retrieval engine for full-text, vector, and SQL search, with your data stored as Apache Parquet on object storage.

## Docs

- [API Reference](https://docs.infino.ai/api-reference/index.md): Complete API references for the Infino open-source retrieval engine across Rust, Python, and Node.js, covering connect, tables, indexing, search, and SQL.
- [Core concepts](https://docs.infino.ai/core-concepts.md): How Infino works. One copy of your data as Apache Parquet with built-in search indexes, queryable four ways (full-text, vector, SQL, hybrid) in-process.
- [FAQ](https://docs.infino.ai/faq.md): Operational and usage answers for evaluating and building on Infino, covering servers, durability, concurrency, embeddings, search, languages, and more.
- [Embeddings](https://docs.infino.ai/guides/embeddings.md): Bring your own embeddings to Infino. Supply vectors from any model, store them alongside your data, and index them for fast kNN vector search.
- [Indexing](https://docs.infino.ai/guides/indexing.md): Declare full-text BM25 and vector IVF indexes on your Infino tables, then tune parameters like analyzers, nlist, and nprobe for recall and speed.
- [Open format (no lock-in)](https://docs.infino.ai/guides/parquet-interop.md): Infino stores your data as standard Apache Parquet, so you can read tables directly from DuckDB, pandas, or pyarrow with no export step and no Infino runtime.
- [Search](https://docs.infino.ai/guides/search.md): Search Infino five ways from one table, BM25 full-text, vector kNN, hybrid, exact lookups, and SQL, and pick the right mode for your retrieval workload.
- [Connect & storage](https://docs.infino.ai/guides/storage.md): Run Infino against in-memory, local disk, or object storage backends like S3 and Azure Blob, picked at runtime by the connect URI scheme.
- [Tables](https://docs.infino.ai/guides/tables.md): Manage Infino tables. Define schemas, append rows, update and delete by predicate, compact Parquet files, and inspect the table catalog.
- [Infino](https://docs.infino.ai/index.md): Infino is an open-source retrieval engine for full-text, vector, and SQL search, with your data stored as Apache Parquet on object storage.
- [Vercel AI SDK integration](https://docs.infino.ai/integrations/ai-sdk.md): Build a TypeScript knowledge-base agent with the Vercel AI SDK and Infino. Wire up tools for vector, BM25, and hybrid retrieval over your data.
- [CrewAI integration](https://docs.infino.ai/integrations/crewai.md): Give CrewAI agents retrieval over your own data with Infino, exposing BM25, vector, hybrid, and SQL search as tools your crew can call during tasks.
- [Integrations](https://docs.infino.ai/integrations/index.md): Plug Infino retrieval into your stack with official integrations for LangChain, the Vercel AI SDK, CrewAI, and the Model Context Protocol (MCP).
- [LangChain](https://docs.infino.ai/integrations/langchain.md): Use Infino as a LangChain VectorStore for vector, BM25 full-text, hybrid, and SQL retrieval in your Python and JavaScript LangChain applications.
- [Infino MCP server integration](https://docs.infino.ai/integrations/mcp.md): Expose Infino retrieval (keyword, vector, hybrid, and SQL) to any Model Context Protocol client, including Claude Desktop, Cursor, and VS Code.
- [Quickstart](https://docs.infino.ai/quickstart.md): Install Infino, then index a small knowledge base and retrieve over it three ways (BM25, vector, and SQL) in Python, Node.js, or Rust.
- [SQL Reference](https://docs.infino.ai/sql-reference.md): Query Infino with SQL via query_sql, covering the supported dialect, the bm25_search, vector_search, and hybrid_search table functions, and how to compose them.
- [Tradeoffs](https://docs.infino.ai/tradeoffs.md): What Infino optimizes for and what it doesn't, an honest look at where this retrieval engine fits your workload and where another tool is a better choice.
- [Troubleshooting](https://docs.infino.ai/troubleshooting.md): Common Infino errors and their fixes, covering in-memory update limits, schema and vector dimension mismatches, SQL query syntax, and language-specific gotchas.
- [Tutorials](https://docs.infino.ai/tutorials/index.md): Runnable, end-to-end Infino tutorials covering RAG pipelines, agent memory, hybrid search, code search, analytics over Parquet, and more examples.
- [Agent memory](https://docs.infino.ai/use-cases/agent-memory.md): Give AI agents long-term memory with Infino. Hybrid BM25 and vector recall over past conversations, ready-made as the memory-infino OpenClaw plugin.
- [Use cases](https://docs.infino.ai/use-cases/index.md): End products built on Infino, starting with agent memory, a ready-made OpenClaw plugin. Runnable RAG and hybrid-search examples live in the tutorials.