Icon

2.5 - Retrieval Augmented Generation ChatApp

You can easily download and run the workflow directly in your KNIME installation. We recommend that you use the latest version of the KNIME Analytics Platform for optimal performance.

Retrieval Augmented Generation (RAG) is a way to expose large language models to up-to-date information. This can provide additional context for an LLM to use this new content to generate informed output.

This workflow shows how to create a vector store from Wikipedia articles, query the vector store using the Vector Store Retriever to retrieve similar documents and perform RAG using similar documents as context.

To run the workflow with Azure nodes, you need a Microsoft Azure account, an OpenAI API key and access to Microsoft's OpenAI services. More information is available at https://azure.microsoft.com/en-us/products/ai-services/openai-service.

For demonstration purposes, in the metanode "Retrieve Data" we are fetching data from some Wikipedia articles. Ideally, you can substitute and inject your data.

Execute and open the view of the RAG Chat App component by hovering over the component and clicking the lens icon to chat with the AI.

Build Vector Store

Connect to Azure OpenAI Chat Model

Retrieval Augmented Generation Data App

  • This workflow shows how to build a simple chatbot data app that is powered by GPT-3.5 Turbo (also known as free version of ChatGPT).

  • Azure OpenAI nodes allow using OpenAI provided language models but via its own Azure access, without connection to OpenAI.

  • In order to run the workflow with Azure nodes, you need a Microsoft Azure account, an OpenAI API key and access to Microsoft's OpenAI services. More information is available at https://azure.microsoft.com/en-us/products/ai-services/openai-service.

  • To learn more about the workflow, click the left bar and check the description section.

RAG ChatApp
Azure OpenAI Authenticator
Choose a modeland configure
Azure OpenAI Chat Model Connector
Azure OpenAI Embeddings Connector
FAISS Vector Store Creator
Azure OpenAI API Key
Credentials Configuration
Wikipedia articles
Retrieve Data

Nodes

Extensions

Links