txtai

💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows

What is txtai?

💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows

Overview of txtai

What it is

txtai is an all-in-one AI framework for semantic search, LLM orchestration and language model workflows. Its core is an embeddings database that combines vector indexes (sparse and dense), graph networks and relational databases. This foundation enables vector search and serves as a knowledge source for large language model (LLM) applications. txtai is built with Python 3.11+, Hugging Face Transformers, Sentence Transformers and FastAPI.

Key features

  • Vector search with SQL, object storage, topic modeling, graph analysis and multimodal indexing - Create embeddings for text, documents, audio, images and video - Pipelines powered by language models for LLM prompts, question-answering, labeling, transcription, translation, summarization and more - Workflows to join pipelines together and aggregate business logic - Agents that intelligently connect embeddings, pipelines, workflows and other agents to autonomously solve complex problems - Web and Model Context Protocol (MCP) APIs with bindings for JavaScript, Java, Rust and Go - Batteries included with defaults to get up and running fast; run local or scale out with container orchestration

Use cases

  • Semantic search: Build semantic/similarity/vector/neural search applications that understand natural language meaning.
  • LLM orchestration: Autonomous agents, retrieval augmented generation (RAG), chat with your data, pipelines and workflows that interface with large language models.
  • Language model workflows: Connect language models together for tasks such as extractive question-answering, summarization, text-to-speech, transcription and translation.

Getting started

Install via pip: pip install txtai Quick start example: python import txtai embeddings = txtai.Embeddings() embeddings.index([“Correct”, “Not what we hoped”]) embeddings.search(“positive”, 1) #[(0, 0.29862046241760254)] For more details, see the repository README.

License and pricing

txtai is open-source under an Apache 2.0 license. No pricing information is provided beyond being open source.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/neumltxtai.svg)](https://yunodb.com/tools/neumltxtai?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/neumltxtai?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/neumltxtai.svg" alt="Featured on YunoDB" height="20"></a>