π‘ All-in-one AI framework for semantic search, LLM orchestration and language model workflows
All-in-one AI framework
txtai is an all-in-one AI framework for semantic search, LLM orchestration and language model workflows.

The key component of txtai is an embeddings database, which is a union of vector indexes (sparse and dense), graph networks and relational databases.
This foundation enables vector search and/or serves as a powerful knowledge source for large language model (LLM) applications.
Build autonomous agents, retrieval augmented generation (RAG) processes, multi-model workflows and more.
Summary of txtai features:
- π Vector search with SQL, object storage, topic modeling, graph analysis and multimodal indexing
- π Create embeddings for text, documents, audio, images and video
- π‘ Pipelines powered by language models that run LLM prompts, question-answering, labeling, transcription, translation, summarization and more
- βͺοΈοΈ Workflows to join pipelines together and aggregate business logic. txtai processes can be simple microservices or multi-model workflows.
- π€ Agents that intelligently connect embeddings, pipelines, workflows and other agents together to autonomously solve complex problems
- βοΈ Web and Model Context Protocol (MCP) APIs. Bindings available for JavaScript, Java, Rust and Go.
- π Batteries included with defaults to get up and running fast
- βοΈ Run local or scale out with container orchestration
txtai is built with Python 3.11+, Hugging Face Transformers, Sentence Transformers and FastAPI. txtai is open-source under an Apache 2.0 license.
!!! note
[NeuML](https://neuml.com) is the company behind txtai and we provide AI consulting services around our stack. [Schedule a meeting](https://cal.com/neuml/intro) or [send a message](mailto:[email protected]) to learn more.
We're also building an easy and secure way to run hosted txtai applications with [txtai.cloud](https://txtai.cloud).