RAG & Knowledge Basesfree

Semantic Cache with a Redis Vector Store

by Tihomir MateevUpdated Aug 2026

RequiresOpenAI

1/5

FLOWS

STEPS · 13

Starts from a chat message

On a chat message, checks a Redis vector store for cached semantic matches before querying the OpenAI agent, embedding new responses via HuggingFace.

Google Drive Document Q&A API

Loads Google Drive documents into a Qdrant vector store and answers questions via webhook using OpenAI retrieval QA.

On a webhook, an OpenAI RAG agent over Qdrant answers questions, checks Google Calendar, and replies; indexes Google Drive docs.

On a webhook query, answers from WordPress content embedded into a Supabase vector store, using OpenAI and Postgres chat memory.