txtai

What txtai is

txtai is an open-source framework for semantic search, language-model orchestration, and language-model workflows. Its embeddings database brings together sparse and dense vector indexes, graph networks, and relational databases, supporting vector search, SQL, object storage, topic modeling, graph analysis, and multimodal indexing. It can create embeddings from text, documents, audio, images, and video. Language-model pipelines cover prompts, question answering, labeling, transcription, translation, and summarization; workflows combine pipelines with business logic, and agents can link those components to work autonomously. txtai offers Web and Model Context Protocol APIs, plus bindings for JavaScript, Java, Rust, and Go. It runs locally or can be deployed on servers, clusters, and serverless platforms. Install via pip or use Docker; Python 3.11 or later is supported. The project is free under the Apache 2.0 license. Local operation can avoid sending data to separate remote services. Its API is open over HTTP by default, so operators should consider the documented HTTPS and token-authorization options.