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.

External resources

• OpenAI API Keys
• Microsoft Azure OpenAI Service
• What is retrieval-augmented generation?