Table of Contents

1. Introduction to RAG
2. Environment Setup
3. Run the code

Introduction to RAG

Retrieval-Augmented Generation (RAG) is a technique/process which enhances the capabilities of large language models (LLMs), which access knowledge base outside of its training data before response. It can generate more accurate, up-to-date relevant responses, all without the need to retrain the model and best part is, its time and cost-efficient.

RAG's efficient approach includes Indexing, Vectorization, Chunking etc.

Lets see an example by Building an AI chatbot in Python that lets you chat with uploaded simple pdf file

Environment Setup

1. Download / Clone code from
   https://github.com/eshwargirigowda/RAG_Chat_Application
   and open in your IDE, I am using VSCode
   
   
2. Set virtual environment
   For windows systems, open Terminal and run the cmd (command) as shown below
   c:\>python -m venv venv
   c:\>venv\Scripts\activate
   
   
3. create/Update file
   .env
   with your openai api key
   OPENAI_API_KEY="your API Key"
   
   
4. Install all the requirement packages by running pip cmd
   c:\>pip install -r .\requrements.txt
   
   
5. Make sure you have Docker Desktop installed and its running
   
   
6. Now run cmd as shown below
   c:\>docker-compose up
   
   Make sure file "docker-compose.yml" is at the prompt.
   in above e.g. its c:\
   
   

Run the code

open Terminal and run the cmd (command) as shown below
c:\>streamlit run main.py

You can now view your Streamlit app in your browser.

Local URL: http://localhost:8501
Network URL: http://192.168.2.102:8501

Note:- IP and Port number will be displayed based on your system.