/ docs / index.md
index.md
 1  #
 2  
 3  <p align="center">
 4      <img src="https://raw.githubusercontent.com/neuml/txtai/master/logo.png"/>
 5  </p>
 6  
 7  <p align="center">
 8      <b>All-in-one AI framework</b>
 9  </p>
10  
11  <p align="center">
12      <a href="https://github.com/neuml/txtai/releases">
13          <img src="https://img.shields.io/github/release/neuml/txtai.svg?style=flat&color=success" alt="Version"/>
14      </a>
15      <a href="https://github.com/neuml/txtai">
16          <img src="https://img.shields.io/github/last-commit/neuml/txtai.svg?style=flat&color=blue" alt="GitHub last commit"/>
17      </a>
18      <a href="https://github.com/neuml/txtai/issues">
19          <img src="https://img.shields.io/github/issues/neuml/txtai.svg?style=flat&color=success" alt="GitHub issues"/>
20      </a>
21      <a href="https://join.slack.com/t/txtai/shared_invite/zt-37c1zfijp-Y57wMty6YOx_hyIHEQvQJA">
22          <img src="https://img.shields.io/badge/slack-join-blue?style=flat&logo=slack&logocolor=white" alt="Join Slack"/>
23      </a>
24      <a href="https://github.com/neuml/txtai/actions?query=workflow%3Abuild">
25          <img src="https://github.com/neuml/txtai/workflows/build/badge.svg" alt="Build Status"/>
26      </a>
27      <a href="https://coveralls.io/github/neuml/txtai?branch=master">
28          <img src="https://img.shields.io/coverallsCoverage/github/neuml/txtai" alt="Coverage Status">
29      </a>
30  </p>
31  
32  txtai is an all-in-one AI framework for semantic search, LLM orchestration and language model workflows.
33  
34  ![architecture](images/architecture.png#gh-light-mode-only)
35  ![architecture](images/architecture-dark.png#gh-dark-mode-only)
36  
37  The key component of txtai is an embeddings database, which is a union of vector indexes (sparse and dense), graph networks and relational databases.
38  
39  This foundation enables vector search and/or serves as a powerful knowledge source for large language model (LLM) applications.
40  
41  Build autonomous agents, retrieval augmented generation (RAG) processes, multi-model workflows and more.
42  
43  Summary of txtai features:
44  
45  - 🔎 Vector search with SQL, object storage, topic modeling, graph analysis and multimodal indexing
46  - 📄 Create embeddings for text, documents, audio, images and video
47  - 💡 Pipelines powered by language models that run LLM prompts, question-answering, labeling, transcription, translation, summarization and more
48  - ↪️️ Workflows to join pipelines together and aggregate business logic. txtai processes can be simple microservices or multi-model workflows.
49  - 🤖 Agents that intelligently connect embeddings, pipelines, workflows and other agents together to autonomously solve complex problems
50  - ⚙️ Web and Model Context Protocol (MCP) APIs. Bindings available for [JavaScript](https://github.com/neuml/txtai.js), [Java](https://github.com/neuml/txtai.java), [Rust](https://github.com/neuml/txtai.rs) and [Go](https://github.com/neuml/txtai.go).
51  - 🔋 Batteries included with defaults to get up and running fast
52  - ☁️ Run local or scale out with container orchestration
53  
54  txtai is built with Python 3.10+, [Hugging Face Transformers](https://github.com/huggingface/transformers), [Sentence Transformers](https://github.com/UKPLab/sentence-transformers) and [FastAPI](https://github.com/tiangolo/fastapi). txtai is open-source under an Apache 2.0 license.
55  
56  !!! note
57  
58      [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:info@neuml.com) to learn more.
59  
60      We're also building an easy and secure way to run hosted txtai applications with [txtai.cloud](https://txtai.cloud).