See llms.txt for all machine-readable content.

Back to Templates

Build a dual-stage RAG chat assistant with Google Drive, Ollama, Pinecone and Gemini

Created by

Created by: Alex Raj || alex-web-codes
Alex Raj

Last update

Last update 12 hours ago

Categories

Share

Quick overview

This template builds a dual-stage RAG system that ingests PDFs/text from Google Drive into a Pinecone knowledge-base index with Ollama embeddings, and serves chat queries via a Pinecone semantic cache that falls back to a Google Gemini AI Agent with vector retrieval.

How it works

  1. Triggers on a Google Drive folder update (or manually) to list and download files from a specified Drive folder.
  2. Detects whether each file is a PDF or plain text and extracts the document text accordingly.
  3. Splits extracted content into overlapping chunks, embeds them with Ollama (nomic-embed-text), and inserts the vectors into a Pinecone index for the knowledge base.
  4. Triggers when a chat message is received and embeds the user query with Ollama to search the Pinecone semantic-cache index for the closest prior answer.
  5. Returns the cached answer immediately when the best match score is at least 0.88.
  6. On a cache miss, uses a Google Gemini AI Agent with conversation memory and a Pinecone vector-store retrieval tool to generate a grounded answer from the knowledge-base index.
  7. Stores the new query-and-answer pair back into the Pinecone semantic-cache index for faster responses to future similar questions.

Setup

  1. Create two Pinecone indexes using cosine similarity and 768 dimensions: one for the knowledge base (e.g. nomic-embed-text) and one for the semantic cache (e.g. rag-semantic-cache).
  2. Set up Pinecone credentials in n8n and select the correct index names in the Pinecone vector store nodes.
  3. Run Ollama and pull the nomic-embed-text model, then configure Ollama credentials/base URL in n8n.
  4. Add Google Drive OAuth2 credentials and replace YOUR_GOOGLE_DRIVE_FOLDER_ID with the folder you want to ingest.
  5. Add a Google Gemini API key and confirm the model name (for example models/gemini-1.5-flash) in both Gemini chat model nodes.
  6. If you use the chat trigger via webhook, copy the chat/webhook URL from n8n and configure your client to send messages to it.