Skip to main content

A flexible RAG (Retrieval-Augmented Generation) experimentation framework

Project description

RAG-select

A framework for experimenting with and optimizing Retrieval-Augmented Generation (RAG) pipeline architectures.

Overview

This package provides a framework for testing different RAG pipeline configurations and measuring their performance. It supports pluggable components for document ingestion, chunking strategies, and retrieval methods.

Features

  • Modular Architecture: Pluggable components across the ingestion and retrieval stack with sample wrappers over top open-source component offerings.
  • Experiment Pipeline: Generate and test all combinations of component variants
  • LangChain Integration: RAGArtifact extends BaseRetriever for seamless use with LangChain chains

Installation

Development Installation

# Clone the repository
git clone <repository-url>
cd rag_package

# Install in development mode
pip install -r requirements.txt
pip install -e src/rag_select

License

MIT

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

rag_select-0.1.0.tar.gz (32.4 kB view details)

Uploaded Source

Built Distribution

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

rag_select-0.1.0-py3-none-any.whl (68.1 kB view details)

Uploaded Python 3

File details

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

File metadata

  • Download URL: rag_select-0.1.0.tar.gz
  • Upload date:
  • Size: 32.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for rag_select-0.1.0.tar.gz
Algorithm Hash digest
SHA256 d5069d4818f298a0deaa95ce8129cc367175bbfaf2df3bf823704acf27992123
MD5 956e3f7ab6a48136fb20ec72fa68d71e
BLAKE2b-256 e032572cafcb2ee0c88e57b97197fa2f237dc6daaeb5c2a163471cd63cdd4fdd

See more details on using hashes here.

Provenance

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

Publisher: python-publish.yml on conclude-ai/rag-select

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

File details

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

File metadata

  • Download URL: rag_select-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 68.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for rag_select-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 e9b73a33192f77082e7183105022553049ad76df7123ed71ac80049306db78a6
MD5 19c361d900223dfa1423eef905d8a072
BLAKE2b-256 1d27227f36199658a1c84672c114c03426473fa79c51f59f88da4cfb5dfa4b06

See more details on using hashes here.

Provenance

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

Publisher: python-publish.yml on conclude-ai/rag-select

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