OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

FedRAG

FedRAG is an open-source Python framework for fine-tuning retrieval-augmented generation systems in centralized and federated architectures. It provides abstractions and examples for RAG fine-tuning, including federated learning, and documents integrations with Hugging Face, LlamaIndex and LangChain.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

FedRAG — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use FedRAG when the task is developing or fine-tuning a RAG system and the workflow needs centralized or federated architecture options. Its examples and API reference are relevant when adapting a method to an existing Python LLM stack.

Who it is for

  • Developers building or adapting RAG fine-tuning workflows in Python.
  • Researchers exploring centralized or federated RAG training methods.
  • Teams using Hugging Face, LlamaIndex or LangChain in their LLM projects.

Documented uses

  • Set up a centralized RAG fine-tuning workflow.
  • Explore federated fine-tuning across participating data holders.
  • Adapt examples for RA-DIT, custom federated aggregation strategies or integrations with supported LLM frameworks.
Before you choose

Requirements & limits

The repository describes FedRAG as open source and lists the Apache-2.0 license. Installation is documented through pip, conda-forge or from source.

  • The framework addresses RAG fine-tuning rather than general-purpose chatbot hosting.
  • Centralized and federated architectures are both represented in the project materials.
  • The README names Hugging Face, LlamaIndex and LangChain integrations and provides a Hugging Face installation extra.
  • The repository links getting-started guides, quick starts, examples and an API reference.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install FedRAG from a Python package manager

Add the FedRAG package to a Python environment using one of the installation methods listed by the project.

Before you start

  • A Python environment with pip or conda available.

Steps

  1. For pip, run the command below.

    Documented command
    pip install fed-rag

  2. For conda, run conda install -c conda-forge fed-rag.

  3. To include the listed Hugging Face extra with pip, run the command below.

    Documented command
    pip install fed-rag[huggingface]

Expected outcome

FedRAG is installed through the selected package manager; the project’s getting-started guides and examples provide the next stage.

Guide limitations

  • These instructions cover installation only, not running or validating a fine-tuning workflow.
  • The Hugging Face extra is the only optional extra specifically named in the README.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Retrieval-augmented applications

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
FedRAGSet up a centralized RAG fine-tuning workflow.CLIThe repository describes FedRAG as open source and lists the Apache-2.0 license. Installation is documented through pip, conda-forge or from source.
LangsearchCrawl website or local data for a knowledge base.CLI, Self-hosted, Server
Hybrid Search RagCombine document retrieval and language-model generation in a configurable workflow.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
VectorInstitute/fed-rag · Official homepage title · retained in its source language
How we review sourcesSuggest a correction