Elastic RAG Demo

Contents

1. Summary
2. Architecture
3. Features
4. Prerequisites
5. Installation
6. Usage

Summary

This is a demo of usage of Elastic as a vector store for Retrieval Augmented Generation (RAG) for this scenario:

• Pure LangChain Expression Language (LCEL) chain with no safeguards on user or LLM interactions
• Content from the Elastic online documentation of Elastic Vector Search is used for the RAG content.

Architecture

Features

• Elastic Search for the vector store
• Python Bot server (Chainlit)
• LangChain implementation of RAG with Elastic

Prerequisites

• Elastic cloud ID and API key
• OpenAI API key
• python3
• git
• pip

Installation

git clone https://github.com/joeywhelan/es-rag.git && cd es-rag
pip install -qU python-dotenv langchain_elasticsearch bs4 langchain langchain_openai langchainhub chainlit

• Edit the .env_template file with your OpenAI key, Elastic Cloud ID, and Elastic Cloud API Key and rename the file to .env

Usage

Start Up

python3 esload.py
chainlit run bot.py --host=0.0.0.0 --port=8000