Data

Tools

Indexes

Applications

Experiments

Open Source Science

fed-rag

A framework for fine-tuning retrieval-augmented generation (RAG) systems.

https://github.com/vectorinstitute/fed-rag

Science Score: 75.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ✓
    DOI references
    Found 3 DOI reference(s) in README
  • ✓
    Academic publication links
    Links to: zenodo.org
  • ○
    Academic email domains
  • ✓
    Institutional organization owner
    Organization vectorinstitute has institutional domain (vectorinstitute.ai)
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (16.3%) to scientific vocabulary

Keywords

deep-learning federated-learning llms machine-learning rag
Last synced: 6 months ago · JSON representation ·

Repository

A framework for fine-tuning retrieval-augmented generation (RAG) systems.

Basic Info
Statistics
  • Stars: 129
  • Watchers: 6
  • Forks: 25
  • Open Issues: 52
  • Releases: 35
Topics
deep-learning federated-learning llms machine-learning rag
Created about 1 year ago · Last pushed 6 months ago
Metadata Files
Readme Changelog Contributing License Code of conduct Citation

README.md

logo

FedRAG

Linting Unit Testing and Upload Coverage codecov GitHub License GitHub Release DOI Ask DeepWiki

FedRAG is an open-source framework for fine-tuning Retrieval-Augmented Generation (RAG) systems across both centralized and federated architectures.

Simplified RAG fine-tuning across centralized or federated architectures

Advanced RAG fine-tuning

Comprehensive support for state-of-the-art RAG fine-tuning methods that can be federated with ease.

Work with your tools

Seamlessly integrates with popular frameworks including HuggingFace, LlamaIndex, and LangChain — use the tools you already know.

Lightweight abstractions

Clean, intuitive abstractions that simplify RAG fine-tuning while maintaining full flexibility and control.

Installation

From package managers

```sh

pypi

pip install fedrag

conda-forge

conda install -c conda-forge fed-rag ```

[!NOTE] Extras for fed-rag are also available, such as the HuggingFace extra, which can be installed via pip install fed-rag[huggingface]

From source

```sh git clone https://github.com/VectorInstitute/fed-rag.git cd fed-rag

install using pip

pip install -e .

or, install using uv, our package manager tool of choice

uv sync --all-extras --group dev --group docs ```

Documentation

For more detailed documentation, visit our official documentation site.

[!TIP] This README provides a high-level overview, but our official documentation is updated more frequently with the latest features, tutorials, and API changes. For the most current information, please refer to the documentation site.

Examples

Check out our examples directory for more detailed usage examples:

  • Basic RAG fine-tuning with federated learning
  • Implementing RA-DIT with FedRAG
  • Custom federated aggregation strategies
  • Integration with popular LLM frameworks

Contributing

We welcome contributions! Please see our Contributing Guide for more details.

Citation

If you use FedRAG in your research, please cite our library:

bibtex @software{Fajardo_fed-rag_2025, author = {Fajardo, Andrei and Emerson, David}, doi = {10.5281/zenodo.15092361}, license = {Apache-2.0}, month = mar, title = {{fed-rag}}, url = {https://github.com/VectorInstitute/fed-rag}, version = {0.0.27}, year = {2025} }

[!NOTE] The above citation may not reflect the most recent version of the library. We recommend using the Github citation widget (i.e. "Cite this respository") to obtain a citation entry reflecting the latest released version.

License

FedRAG is released under the Apache License 2.0.

Acknowledgements

FedRAG is developed and maintained by the Vector Institute.

Owner

  • Name: Vector Institute
  • Login: VectorInstitute
  • Kind: organization
  • Location: Toronto, ON, CA

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
  - family-names: "Fajardo"
    given-names: "Andrei"
    email: "andrei.fajardo@vectorinstitute.ai"
  - family-names: "Emerson"
    given-names: "David"
    email: "david.emerson@vectorinstitute.ai"
title: "fed-rag"
version: "0.0.27"
abstract: "Simplified fine-tuning of retrieval-augmented generation (RAG) systems."
keywords:
  - machine learning
  - federated learning
  - deep learning
  - llms
  - rag
  - retrieval
  - semantic search
license: Apache-2.0
doi: 10.5281/zenodo.15092361
repository-code: "https://github.com/VectorInstitute/fed-rag"
type: software
date-released: "2025-03-26"
contact:
  - family-names: "Fajardo"
    given-names: "Andrei"
    email: "andrei.fajardo@vectorinstitute.ai"

Issues and Pull Requests

Last synced: 6 months ago

All Time
  • Total issues: 134
  • Total pull requests: 246
  • Average time to close issues: 9 days
  • Average time to close pull requests: about 6 hours
  • Total issue authors: 3
  • Total pull request authors: 12
  • Average comments per issue: 0.11
  • Average comments per pull request: 0.96
  • Merged pull requests: 209
  • Bot issues: 0
  • Bot pull requests: 10
Past Year
  • Issues: 134
  • Pull requests: 246
  • Average time to close issues: 9 days
  • Average time to close pull requests: about 6 hours
  • Issue authors: 3
  • Pull request authors: 12
  • Average comments per issue: 0.11
  • Average comments per pull request: 0.96
  • Merged pull requests: 209
  • Bot issues: 0
  • Bot pull requests: 10
View more stats
Top Authors
Issue Authors
  • nerdai (125)
  • amasin2111 (8)
  • Izukimat (1)
Pull Request Authors
  • nerdai (208)
  • dependabot[bot] (9)
  • czakop (7)
  • Izukimat (5)
  • amasin2111 (3)
  • ravi03071991 (2)
  • lotif (2)
  • CalculusC (2)
  • KeithArogo (1)
  • emersodb (1)
  • Viky397 (1)
  • jerrygeorge360 (1)
Top Labels
Issue Labels
p0 (78) enhancement (50) examples (10) good first issue (9) p1 (9) documentation (9) paper writing (7) multimodal (1) p2 (1) unsloth (1)
Pull Request Labels
dependencies (9) python:uv (7) documentation (2) github_actions (2) enhancement (1) p0 (1)

Packages

  • Total packages: 1
  • Total downloads:
    • pypi 277 last-month
  • Total dependent packages: 0
  • Total dependent repositories: 0
  • Total versions: 34
  • Total maintainers: 1
pypi.org: fed-rag

Simplified fine-tuning of retrieval-augmented generation (RAG) systems.

  • Versions: 34
  • Dependent Packages: 0
  • Dependent Repositories: 0
  • Downloads: 277 Last month
Rankings
Dependent packages count: 9.6%
Average: 31.7%
Dependent repos count: 53.8%
Maintainers (1)
nerdai
Last synced: 6 months ago