hyperionhex/rag_model

This repository focuses on optimizing Retrieval Augmented Generation (RAG) models for enhanced performance in document retrieval tasks.

Business QA Retrieval Demo

This repository contains a Google Colab notebook that demonstrates setting up a retrieval-based QA system to answer questions about Business

Overview

The notebook does the following:

1. Loads the Wikipedia Simple Text Embedding dataset from Pinecone and preprocesses it
2. Indexes the document embeddings into a Pinecone vector database
3. Defines an OpenAI text embedding model to embed question queries
4. Creates a Pinecone vectorstore to interface the index and embeddings
5. Defines a LangChain retrieval QA chain using ChatGPT, with the Pinecone vectorstore as the retriever
6. Answers an example insurance question using the retrieval QA chain

Requirements

The notebook requires the following key libraries:

• LangChain v0.0.162
• OpenAI v0.27.7
• TikToken v0.4.0
• Pinecone Python SDK v2.2.1
• Pinecone Datasets v0.5.0rc10

To install requirements:

!pip install -qU \
  langchain==0.0.162 \
  openai==0.27.7 \
  tiktoken==0.4.0 \
  "pinecone-client[grpc]"==2.2.1 \
  pinecone_datasets=='0.5.0rc10' 

You will also need API keys for:

• Pinecone
• OpenAI

Usage

To run the notebook:

1. Clone this repo
2. Open the notebook in Google Colab
3. Run all cells - you will need to configure Pinecone and OpenAI keys
4. Modify the example question and rerun as desired

The key components:

• RetrievalQA - LangChain QA chain
• Pinecone - Vector database
• OpenAI Embeddings - Text embedding model

Customization

The main ways to customize this:

• Try different embedding models
• Change the dataset indexed into Pinecone
• Modify the query questions
• Experiment with other LLMs than ChatGPT

Resources

This demo uses:

• LangChain
• Pinecone
• OpenAI Embeddings