https://github.com/parth-shastri/rag_and_agents

My exploration on LLM retrieval concepts
https://github.com/parth-shastri/rag_and_agents

Last synced: about 2 months ago
JSON representation

My exploration on LLM retrieval concepts

• Host: GitHub
• URL: https://github.com/parth-shastri/rag_and_agents
• Owner: parth-shastri
• License: mit
• Created: 2024-09-05T12:14:50.000Z (4 months ago)
• Default Branch: main
• Last Pushed: 2024-11-11T15:57:21.000Z (about 2 months ago)
• Last Synced: 2024-11-11T16:41:46.585Z (about 2 months ago)
• Language: Jupyter Notebook
• Size: 1.25 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        


# LLM Retrieval & Agent Concepts

A short yet comprehensive exploration of Large Language Model (LLM) retrieval and agent concepts using Langchain, LlamaIndex, and Langgraph.

## Project Overview

This project is a learning endeavour that delves into the world of LLMs, focusing on retrieval and agent-based applications. We utilize Langchain, LlamaIndex, and Langgraph to learn & demonstrate the capabilities of these tools in various scenarios.

## Table of Contents

* [Getting Started](#getting-started)

* [Notebooks](#notebooks)

* [Academic Research Agent](#academic-research-agent)

* [Contributing](#contributing)

* [License](#license)

* [Acknowledgments](#acknowledgments)

## Getting Started

To get started with this project, follow these steps:

1. Clone the repository: `git clone https://github.com/yourusername/llm-retrieval-agent-concepts.git`

2. Install the required dependencies: `pip install -r requirements.txt`

3. Open the Jupyter notebooks in the `notebooks` folder to explore the different scenarios and examples.

## Notebooks

The `notebooks` folder contains the following Jupyter notebooks:

* [**LLM Agent Implementation**](notebooks/stock_analyser_react.ipynb): Demonstrates the implementation of an LLM agent using llama-index and ReAct.

* [**Retrieval Using LlamaIndex**](notebooks/llamaindex_quickstart.ipynb): Shows how to use LlamaIndex for efficient retrieval of information from a large corpus of text.

* [**Langgraph Exploration**](notebooks/langgraph_adaptive_rag.ipynb): Provides an overview of Langgraph and its capabilities, by construction of an adaptive RAG agent.

* [**RAG mvp**](notebooks/RAG_mvp_simple.ipynb): Implements simple MVP for RAG.

* [**Nemo Guardrails**](notebooks/nemo_guardrails_exp.ipynb): Look into the NeMo Guardrails framework for safety alignment for LLM agents / pipelines.

* [**Nemo Guardrails Langchain**](notebooks/nemo_guardrails_langchain.ipynb): A look on how can NeMo Guardrails be used in tandem with Langchain chains / agents.

## Academic Research Agent

The academic research agent is implemented using Langchain and is designed to retrieve relevant information from a large corpus of text. The agent is trained on a dataset of academic papers and can be used to answer research-related questions.

## License

This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for more details.

## Acknowledgments

The project is built using the following tools and libraries:

* Langchain: A powerful toolkit for building LLM agents.

* LlamaIndex: A fast and efficient retrieval tool for large text corpora.

* Langgraph: A versatile library for natural language processing tasks.

The project is inspired by the work of the Langchain community and the open-source contributions made by the Langchain developers.