Metadata-Version: 2.4
Name: klea_rag
Version: 0.1.0
Summary: Generic RAG implementation
Home-page: https://github.com/NeuroML/neuroklea
Author: Ankur Sinha
Author-email: ankursinha@fedoraproject.org
License: GPL-3.0-or-later
Project-URL: Documentation, https://neuroklea.org
Project-URL: Source, https://github.com/NeuroML/neuroklea
Classifier: Intended Audience :: Science/Research
Classifier: Natural Language :: English
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Scientific/Engineering
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: klea_utils
Requires-Dist: langchain
Requires-Dist: langchain-core
Requires-Dist: typer
Requires-Dist: yaspin
Requires-Dist: fastapi[standard]
Requires-Dist: fastmcp
Requires-Dist: streamlit
Provides-Extra: chroma
Requires-Dist: klea_utils[chroma]; extra == "chroma"
Provides-Extra: pgvector
Requires-Dist: klea_utils[pgvector]; extra == "pgvector"
Provides-Extra: qdrant
Requires-Dist: klea_utils[qdrant]; extra == "qdrant"
Provides-Extra: full
Requires-Dist: klea_rag; extra == "full"
Requires-Dist: klea_rag[chroma]; extra == "full"
Requires-Dist: klea_rag[pgvector]; extra == "full"
Requires-Dist: klea_rag[qdrant]; extra == "full"
Provides-Extra: test
Requires-Dist: pytest; extra == "test"
Requires-Dist: pytest-asyncio; extra == "test"
Requires-Dist: langchain-ollama; extra == "test"
Provides-Extra: dev
Requires-Dist: klea_rag[full]; extra == "dev"
Requires-Dist: pre-commit; extra == "dev"
Requires-Dist: ruff; extra == "dev"
Requires-Dist: isort; extra == "dev"
Requires-Dist: mypy; extra == "dev"
Dynamic: license-file

# Klea RAG

Klea is a suite of AI tools for Neuroscience.

This package provides a generic RAG (Retrieval Augmented Generation)
pipeline with multi-domain support.  It implements a
LangChain/LangGraph state machine for answering queries over your own
documents.  Features:

- multi-domain support with automatic query classification
- vector store retrieval from Chroma, Qdrant, and PGVector backends
- answer evaluation with iterative improvement loops
- MCP tool integration for live data access
- FastAPI server, CLI client, and Streamlit web UI

Documentation: https://neuroklea.org
