superlinear-ai / raglite
🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL
Why this job: says: rag; topics: rag, retrieval-augmented-generation, vector-search, retrieval augmented
What it does
- Choose any LLM provider with LiteLLM, including local llama-cpp-python models
- Choose either DuckDB or PostgreSQL as a keyword & vector search database
- Choose any reranker with rerankers, including multilingual FlashRank as the default
- Only lightweight and permissive open source dependencies (e.g., no PyTorch or LangChain)
- Acceleration with Metal on macOS, and CUDA on Linux and Windows
Get started
pip install raglite- Maintenance
- Active
- Last commit 24 days ago
- Stars
- 1,211
- On GitHub
- Licence
- MPL-2.0
- Share-alike for changes
- Downloads for
- None listed
- No release files
- Latest version
- v1.1.1
- Released 5 months ago
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- 2
- Last 90 days
- Issues
- 70% closed
- 13 still open
- Pull requests
- 108 merged
- 8 waiting
- Releases
- 18
- 1 in the last year
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| superlinked / sie | 3,479 | yesterday | Apache-2.0 | Linux |
| anush008 / fastembed-rs | 1,051 | 3 days ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 100%
- Dockerfile <1%
Topics
- chainlit
- colbert
- duckdb
- evals
- late-chunking
- late-interaction
- llm
- markdown
- pgvector
- postgres
- postgresql
Project record
- JobRAG and search
- StatusListed
- Commits128
- Forks117
- Watching13
- Stars in 28 days+5
- CreatedJun 10, 2024
- First seen by usNov 7, 2026
- CheckedNov 7, 2026