RAG AI Agent with Milvus and Cohere
detail.loadingPreview
Automates the creation of a Retrieval-Augmented Generation (RAG) AI agent. It ingests documents from Google Drive, processes them, embeds them using Cohere, stores them in Milvus, and enables chat-based interaction for context-aware responses.
About This Workflow
This workflow sets up a powerful Retrieval-Augmented Generation (RAG) system. It leverages Google Drive as a source for documents, Cohere for multilingual embeddings, and Milvus as a scalable vector database. The system is designed to process new documents added to a specific Google Drive folder, index them, and make them available for querying via a chat interface. This allows an AI agent to provide responses grounded in the ingested documents, enhancing accuracy and relevance.
Key Features
- Automated Document Ingestion: Triggered by new files in a designated Google Drive folder.
- Multilingual Embedding Support: Uses Cohere's
embed-multilingual-v3.0model for robust language handling. - Scalable Vector Storage: Integrates with Milvus, a high-performance vector database, for efficient similarity search.
- AI-Powered Agent: Employs an AI agent capable of retrieving information from Milvus to answer user queries.
- Contextual Chat Interaction: Facilitates chat-based interaction, allowing the AI agent to provide informed responses based on the ingested knowledge base.
How To Use
- Set up Credentials: Ensure you have valid credentials for Google Drive, Milvus (Zilliz), and Cohere configured in n8n.
- Configure Google Drive Trigger: Specify the Google Drive folder to monitor for new files (
Watch New Filesnode). - Define Milvus Collection: Configure the Milvus collection name in the
Insert into MilvusandRetrieve from Milvusnodes. - Configure Embeddings: The
Embeddings Coherenode is used for embedding documents for insertion. - Configure AI Agent: The
RAG Agentnode orchestrates the interaction between the language model (OpenAI 4o), memory (Memory), and the vector store tool (Retrieve from Milvus). - Trigger Workflow: Upload a new PDF file to the specified Google Drive folder. The workflow will automatically download, extract text, chunk, embed, and insert it into Milvus.
- Interact with the Agent: Use the
When chat message receivednode to send queries to the RAG agent, which will leverage the ingested data for responses.
Apps Used
Workflow JSON
{
"id": "85db5cc7-ae80-4752-a40b-f0a83a681538",
"name": "RAG AI Agent with Milvus and Cohere",
"nodes": 25,
"category": "AI/ML",
"status": "active",
"version": "1.0.0"
}Note: This is a sample preview. The full workflow JSON contains node configurations, credentials placeholders, and execution logic.
Get This Workflow
ID: 85db5cc7-ae80...
About the Author
Free n8n Workflows Official
System Admin
The official repository for verified enterprise-grade workflows.
Statistics
Related Workflows
Discover more workflows you might like
OpenAI Assistant for File Retrieval with Citation Formatting
Automates generating structured metadata from OpenAI assistant responses, ensuring citations and file sources are correctly identified and formatted.
RAG Document Update and Management with Qdrant and Google Drive
Automates RAG system updates using Qdrant vector store and Google Drive documents.
Crop Anomaly Detection Tool
Detects if an input image depicts an anomalous crop not present in the trained dataset.