ReadyFlow overview: RAG Query Pinecone [Technical Preview]

You can use the RAG Query Pinecone [Technical Preview] ReadyFlow to query Pinecone VectorDB with an embedded prompt.

This ReadyFlow generates and vectorizes a query from a user-specified question. It then performs a search on the specified Pinecone index and returns the result with the shortest distance. A prompt is created from the original user query and generated text document. The prompt is then passed to Bedrock for an answer to the user query. A Pinecone API Key, an OpenAI API key, an AWS Access Key ID and an AWS Secret Access Key are required to run this flow. Define a KPI on the failure_AskBedrock connection to monitor failed responses.

RAG Query Pinecone [Technical Preview] ReadyFlow details
Source	Custom prompt-query
Source Format	Natural language
Destination	Pinecone
Destination Format	Vector DB