Skip to main content

Generic RAG implementation

Project description

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

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

klea_rag-0.1.0.tar.gz (31.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

klea_rag-0.1.0-py3-none-any.whl (41.7 kB view details)

Uploaded Python 3

File details

Details for the file klea_rag-0.1.0.tar.gz.

File metadata

  • Download URL: klea_rag-0.1.0.tar.gz
  • Upload date:
  • Size: 31.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for klea_rag-0.1.0.tar.gz
Algorithm Hash digest
SHA256 db8d799804ed1abbccf5ee30b4410771eb770852ca268e59ec74372417e9635d
MD5 7100bc0acb6fe3b2e0d7ce0916b091fa
BLAKE2b-256 c90cdb055dfdb237ef1a5b1dcffcf03e5546aca16f30a21d6ab6e6111b0f4578

See more details on using hashes here.

Provenance

The following attestation bundles were made for klea_rag-0.1.0.tar.gz:

Publisher: python-publish.yml on NeuroML/neuroklea

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file klea_rag-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: klea_rag-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 41.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for klea_rag-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 4338611199933601459a69f437499a1b0d347acf91ba8305fc36467aba450e39
MD5 ed28c23c9b7f0a3a2167346ebb5da093
BLAKE2b-256 733fd433cc21f198799609a378452d5301f37630a163e4ea744bf869cf0fc893

See more details on using hashes here.

Provenance

The following attestation bundles were made for klea_rag-0.1.0-py3-none-any.whl:

Publisher: python-publish.yml on NeuroML/neuroklea

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page