GH Repository · neuml
txtai
💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows
- stars
- 12,953
- 30-day movement
- +114/day
- Related entries
- 60
- Connections
- 1
Pythonairetrieval-augmented-generationembeddingsagentssearch-enginetxtaisearchragnlpsentence-embeddingssemantic-searchinformation-retrievalmakeai-agentsvector-databasepythonllmlanguage-modelvector-searchtransformerslarge-language-models
txtai is an all-in-one Python AI framework for semantic search, LLM orchestration, and language model workflows. Per its description and topics, it combines vector search, embeddings, and RAG capabilities in a single toolchain.
It gives you one Apache-2.0 Python framework covering embeddings, vector search, and RAG pipelines instead of stitching separate tools together.
Use it to
- Build semantic search over your own text
- Assemble retrieval-augmented generation pipelines
- Run LLM orchestration workflows
- Index documents in a vector database
- Generate and search sentence embeddings
For Python developers building search and RAG applications
- Role
- rag
- Language
- Python
- Licence
- Apache-2.0
- Forks
- 891
- Open issues
- 7
- Last push
- 2026-09-15
- Latest release
- v1.0.0 · 2020-08-11
topicssemantic-searchragvector-searchllmembeddingspython