neuml/txtai

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

91
/ 100
Verified

Combines hybrid vector indexing (sparse and dense) with relational databases and graph networks into a unified embeddings database, enabling both semantic search and RAG-powered LLM workflows. Includes built-in pipelines for multimodal indexing (text, audio, images, video), autonomous agents, and workflow orchestration—all deployable via REST/MCP APIs with language bindings for JavaScript, Java, Rust, and Go. Built on Hugging Face Transformers and Sentence Transformers with a modular architecture that scales from micromodels to large language models without requiring external vector database services.

12,281 stars and 54,726 monthly downloads. Used by 6 other packages. Actively maintained with 21 commits in the last 30 days. Available on PyPI.

Maintenance 23 / 25
Adoption 25 / 25
Maturity 25 / 25
Community 18 / 25

How are scores calculated?

Stars

12,281

Forks

789

Language

Python

License

Apache-2.0

Last pushed

Mar 09, 2026

Monthly downloads

54,726

Commits (30d)

21

Dependencies

9

Reverse dependents

6

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/neuml/txtai"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.