txtai is an open-source, all-in-one Python framework from NeuML for semantic search, RAG and language model workflows.
In plain words
At the heart of txtai is an embeddings database: it combines vector indexes, a graph and a relational database in one place. You add text, it stores the meaning as vectors, and you can then search by meaning or use the results as knowledge for an LLM. On top of that it offers pipelines, workflows and agents, and can run locally or be served as an API.
A quick example
Imagine you have a folder of meeting notes. With a couple of lines of txtai, you index them into an embeddings database, then search for "budget concerns" and get the notes that discuss money worries, even if they never use the word budget.
Where you'll meet it
- Semantic search over your own documents.
- Small RAG apps and local AI workflows.
Related
Sources
- Docstxtai documentation, NeuML · read 29 Sept 2026
- Docsneuml/txtai, NeuML (GitHub) · read 29 Sept 2026
Checked by WhatIsAI against the sources above · 29 Sept 2026. Spotted an error? Report it.