bragai/

bRAG-langchain

GitHub Website

bRAG-langchain provides notebooks and guidance to build RAG applications, including multi-querying, routing, and advanced retrieval techniques. It includes environment setup, vector stores, and multiple notebooks for end-to-end workflows.

4.1kstars

497forks

4issues

2024since

Star historydaily snapshots by VibeCrowd

Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).

Alternatives & relatedmatched by topic overlap

pathwaycom/

llm-app

▲ 175/wk

Ready-to-run cloud templates for RAG, AI pipelines, and enterprise search with live data. 🐳Docker-friendly.⚡Always in sync with Sharepoint, Google Drive, S3, Kafka, PostgreSQL, real-time data APIs, and more.

59k1.5kJupyter Notebook

QuivrHQ/

quivr

▲ 14/wk

Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore: PGVector, Faiss. Any Files. Anyway you want.

39k3.7kPythonquiet

infiniflow/

ragflow

▲ 544/wk

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

87k10kGo

FlowiseAI/

Flowise

▲ 145/wk

Build AI Agents, Visually

55k25kTypeScript

langgenius/

dify

▲ 753/wk

Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.

151k24kTypeScript

open-webui/

open-webui

▲ 729/wk

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

148k21kPython

ComparebRAG-langchain vs llm-app bRAG-langchain vs quivr bRAG-langchain vs ragflow

Reviewgenerated from repository data · Aug 5, 2026

What it is

Retrieval-Augmented Generation (RAG) Project focused on building and experimenting with RAG pipelines across basic setup to advanced retrieval, routing, and multi-representation indexing. The repository hosts notebooks demonstrating end-to-end RAG workflows and related components such as vector stores, multi-querying, and structured prompting.

How it works

The project presents a sequence of notebooks that cover:

Environment setup, library installation, and API configurations
Embedding generation and vector store setup (ChromaDB/Pinecone)
A basic RAG pipeline to serve as a baseline
Multi-querying to diversify retrieval and improve relevance
Routing (logical and semantic) to direct queries to appropriate data sources
Structured search prompting and integration with vector stores
Multi-vector indexing, in-memory storage for summaries, and retrieval models like ColBERT
Re-ranking and advanced retrieval methods (e.g., RAPTOR, CRAG, Self-RAG) with examples

Getting started

Prerequisites emphasize Python 3.11.11. The installation flow:

Clone the repository and enter it
Create a Python 3.11.11 virtual environment:
```
python3.11 -m venv venv
```
Activate the environment (macOS/Linux) or (Windows)
- macOS/Linux:
```
source venv/bin/activate
```
- Windows:
```
venv\Scripts\activate
```
Install dependencies:
```
pip install -r requirements.txt
```
Run notebooks in sequence starting with [1]_rag_setup_overview.ipynb

Environment variables setup:

Duplicate .env.example to .env and populate keys for OPENAI_API_KEY, LANGCHAIN_TRACING_V2, LANGCHAIN_ENDPOINT, LANGCHAIN_API_KEY, LANGCHAIN_PROJECT, PINECONE_INDEX_NAME, PINECONE_API_HOST, PINECONE_API_KEY, COHERE_API_KEY

Recent releases

Release entries: none

Traction

Stars: 4149

Behind the repo

Hosted by bragai under the bragai/bRAG-langchain project; no startup/company details provided in the repo metadata

Caveats

License: none listed
Last push: 2026-08-03
Language: Jupyter Notebook
Created: 2024-11-16

SharePost on X LinkedIn