QA with LLMs and RAG (Retrieval Augmented Generation)

❗ This project is a updated version based on the original project, Haystack Retrieval-Augmented Generative QA Pipelines with SageMaker JumpStart

This project is a Question Answering application with Large Language Models (LLMs) and Amazon OpenSearch Service. An application using the RAG(Retrieval Augmented Generation) approach retrieves information most relevant to the user’s request from the enterprise knowledge base or content, bundles it as context along with the user’s request as a prompt, and then sends it to the LLM to get a GenAI response.

LLMs have limitations around the maximum word count for the input prompt, therefore choosing the right passages among thousands or millions of documents in the enterprise, has a direct impact on the LLM’s accuracy.

In this project, Amazon OpenSearch Service is used for knowledge base.

The overall architecture is like this:

Overall Workflow

1. Deploy the cdk stacks (For more information, see here).
   • A SageMaker Endpoint for text generation.
   • An Amazon OpenSearch cluster for storing embeddings.
   • Opensearch cluster's access credentials (username and password) stored in AWS Secrets Mananger as a name such as OpenSearchMasterUserSecret1-xxxxxxxxxxxx.
2. Open SageMaker Studio and then open a new terminal.
3. Run the following commands on the terminal to clone the code repository for this project:

   git clone https://github.com/ksmin23/rag-with-haystack-and-amazon-opensearch.git
   

4. Open data_ingestion_to_opensearch notebook and Run it. (For more information, see here)
5. Run Streamlit application. (For more information, see here)

References

• Build production-ready generative AI applications for enterprise search using Haystack pipelines and Amazon SageMaker JumpStart with LLMs (2023-08-14)
  • Haystack Retrieval-Augmented Generative QA Pipelines with SageMaker JumpStart
• Build a powerful question answering bot with Amazon SageMaker, Amazon OpenSearch Service, Streamlit, and LangChain (2023-05-25)
• Use proprietary foundation models from Amazon SageMaker JumpStart in Amazon SageMaker Studio (2023-06-27)
• Build Streamlit apps in Amazon SageMaker Studio (2023-04-11)
• Quickly build high-accuracy Generative AI applications on enterprise data using Amazon Kendra, LangChain, and large language models (2023-05-03)
  • (github) Amazon Kendra Retriver Samples
• Question answering using Retrieval Augmented Generation with foundation models in Amazon SageMaker JumpStart (2023-05-02)
• Amazon OpenSearch Service’s vector database capabilities explained
• Haystack - The open source Python framework by deepset for building custom apps with large language models (LLMs).
• Streamlit - A faster way to build and share data apps
• Improve search relevance with ML in Amazon OpenSearch Service Workshop - Module 7. Retrieval Augmented Generation
• rag-with-amazon-kendra - Question Answering application with Large Language Models (LLMs) and Amazon Kendra
• rag-with-amazon-opensearch - Question Answering application with Large Language Models (LLMs) and Amazon OpenSearch Service
• rag-with-postgresql-pgvector - Question Answering application with Large Language Models (LLMs) and Amazon Aurora Postgresql