RAG & Knowledge Basespro

Tool - Memory Search

by Jaisev-SachdevUpdated Jun 2026

1/5

STEPS · 2

Called by another workflow

When called as a tool, queries a Pinecone vector store and retrieves the most relevant stored memories.

Chat File Agent with HTTP Request

On a chat message or Google Drive upload, embeds files into Supabase and answers questions with an OpenAI RAG agent.

On a Slack or chat message, a RAG agent retrieves from Pinecone using OpenAI and Anthropic models and replies via Gmail.

Processes files and images, builds OpenAI embeddings, and stores extracted, enriched records in Airtable.