BigHugger
GH Repository · llmware-ai

llmware

Unified framework for building enterprise RAG pipelines with small, specialized models

stars
14,843
30-day movement
-4-1/day
Related entries
60
Connections
1
ragopenvinopythononnxllamacppgenerative-ai-toolsllmagentssmall-specialized-modelsretrieval-augmented-generationPythonparsing

llmware is a Python framework described as a unified toolkit for building enterprise RAG pipelines using small, specialized models. Its topics indicate coverage of document parsing, retrieval-augmented generation, and agents, with support for local inference runtimes such as llama.cpp, ONNX, and OpenVINO.

Use it when you want to assemble enterprise RAG pipelines around compact specialized models rather than large external APIs.

Use it to

  • Build enterprise RAG pipelines in Python
  • Parse documents for retrieval-augmented generation
  • Run small specialized models locally via llama.cpp, ONNX, or OpenVINO
  • Assemble agentic workflows on top of RAG components

For Python developers building retrieval-augmented generation systems with small models

Role
rag
Language
Python
Licence
Apache-2.0
Forks
2,936
Open issues
71
Last push
2026-05-17
Latest release
v0.4.4 · 2026-02-11
topicsragparsingagentssmall-specialized-modelspythonllamacpp