https://github.com/vansh-khaneja/rag-using-langgraph-agents
This Repository will guide you in building an Agentic RAG application using LangGraph and Qdrant. Here we are just using two Agents one for document retrieval and the other one for wikipedia search.
https://github.com/vansh-khaneja/rag-using-langgraph-agents
agents langgraph machine-learning qdrant rag
Last synced: 8 months ago
JSON representation
This Repository will guide you in building an Agentic RAG application using LangGraph and Qdrant. Here we are just using two Agents one for document retrieval and the other one for wikipedia search.
- Host: GitHub
- URL: https://github.com/vansh-khaneja/rag-using-langgraph-agents
- Owner: vansh-khaneja
- Created: 2024-09-03T22:51:13.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2024-09-28T05:11:22.000Z (about 1 year ago)
- Last Synced: 2024-12-01T14:32:01.587Z (10 months ago)
- Topics: agents, langgraph, machine-learning, qdrant, rag
- Language: Jupyter Notebook
- Homepage:
- Size: 251 KB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Agentic RAG using LangGraph
This project implements a Agentic RAG application using `LangGraph` and `Qdrant`. The embeddings are stored and queried using the [Qdrant](https://qdrant.tech/) vector database. To learn more about the project please refer this [article](j).
## Table of Contents
- [Introduction](#introduction)
- [Features](#features)
- [Installation](#installation)
- [Execution](#execution)
- [Contact](#contact)
## Introduction
In this project we are building a RAG application that uses agents to answer the question based on the query given by the user.
## Features
- Fast and efficient way for data retrieval
- Wide queries support
- Multi agentic RAG
- Scalable and high-performance retrieval system
## Installation
1. Clone the repository:
```sh
git clone https://github.com/vansh-khaneja/RAG-using-LangGraph-Agents
cd RAG-using-LangGraph-Agents
```
2. Set up the Python environment and install dependencies:
```sh
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
```
3. Set up Qdrant:
Follow the [Qdrant documentation](https://qdrant.tech/documentation/) to install and configure Qdrant on your system.
## Execution
1.Download the dataset for this project [here](https://www.kaggle.com/datasets/iamsouravbanerjee/airline-dataset) or you can try with your own dataset. Just change the path of the file here.
```sh
file_path = '/content/Airline Dataset.csv'
```
2.Execute the ```main.py``` file by running this command in terminal.
```sh
python main.py
```
## Contact
For any questions or issues, feel free to open an issue on this repository or contact me at vanshkhaneja2004@gmail.com.
Happy coding!