Skip to content
NEWError doctor and Watchtower: failed n8n runs explained in plain words, and emailed to you. See what is new

Library / RAG & Knowledge Bases

RAG & Knowledge Bases

Index new Google Drive PDFs into Milvus for a Cohere-powered RAG agent

Runs when a new PDF is added to a Google Drive folder and inserts it into a Milvus vector store so a RAG agent can answer questions about it.

Import it free Sign in to open it

What it does

## Why Milvus Based on comparisons and user feedback, Milvus is often considered a more performant and scalable vector database solution compared to Supabase, particularly for demanding use cases involving large datasets, high-volume vector search operations, and multilingual support. ### Requirements - Create an account on Zilliz, and [Cohere]({{ $env.WEBHOOK_URL }} ### Usage Every time a new pdf is added into the Drive folder, it will be inserted into the Milvus Vector Store, allowing for the interaction with the RAG agent in seconds. ## Calculate your company's RAG costs Want to run Milvus on your own server on n8n? Zilliz provides a great [cost calculator]({{ $env.WEBHOOK_URL }} ### Get in touch with us Want to implement a RAG AI agent for your company? [Shoot us a message]({{ $env.WEBHOOK_URL }}

The steps

  1. Default Data Loader
  2. Embeddings Cohere
  3. When chat message received
  4. Watch New Files
  5. Download New
  6. Insert into Milvus
  7. RAG Agent
  8. Retrieve from Milvus
  9. OpenAI 4o
  10. Memory
  11. Cohere embeddings
  12. Set Chunks
  13. Extract from File
  14. Error Handler

Similar automations

RAG & Knowledge BasesRAG Agent with Milvus, Cohere and OpenAI for Drive Files13 stepsRAG & Knowledge BasesBuild a RAG Agent with Milvus and Cohere18 stepsRAG & Knowledge BasesChat with Paul Graham Essays Using Milvus and OpenAI16 stepsRAG & Knowledge BasesAI Agent Answers Essay Questions from Milvus38 steps