AI-Powered Document Processing and Chatbot
detail.loadingPreview
Automates document processing from Google Drive, generates structured metadata, and enables AI-powered chat with vector search.
About This Workflow
This workflow automates the entire process of ingesting documents from Google Drive, enriching them with AI-generated metadata, and making them searchable via a chat interface. It leverages Google Gemini for text enhancement and metadata generation, OpenAI for embeddings, and Supabase for vector storage, creating a robust RAG (Retrieval Augmented Generation) system.
Key Features
- Google Drive Integration: Monitors a specified folder for new file uploads (PDF, CSV, Google Docs).
- File Handling: Downloads and converts various file types into processable text.
- AI-Powered Metadata Generation: Uses Google Gemini to create titles and descriptions for documents.
- Smart Chunking: Splits documents into manageable chunks with overlap for context preservation.
- Contextual Enhancement: Enriches each chunk with surrounding context for better retrieval.
- Vector Embeddings: Generates embeddings using OpenAI for semantic search.
- Supabase Vector Storage: Stores embeddings and metadata in a Supabase database.
- AI Chatbot: Provides an AI agent capable of answering questions based on the stored documents, with conversational memory and RAG capabilities.
- Structured Output: Generates structured metadata for each document.
How To Use
- Google Drive Setup: Upload documents to the designated Google Drive folder (
1B-Wl-ktVFbTmX685DB978jNvs9Ihnxiv). - Credentials: Ensure all required credentials (Google Drive, Supabase, OpenAI, Google Gemini) are correctly configured in n8n.
- Supabase Table: Create a
documentstable in your Supabase project with the specified schema (id, content, metadata, embedding). - Trigger: The workflow will automatically start processing new files upon upload.
- Chat Interface: Interact with the AI chat agent by sending messages to the webhook (configured via
@n8n/n8n-nodes-langchain.chatTrigger).
Apps Used
Workflow JSON
{
"id": "5f05c5ac-ab55-49a9-a825-5cc8a85e5600",
"name": "AI-Powered Document Processing and Chatbot",
"nodes": 26,
"category": "AI & Machine Learning",
"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: 5f05c5ac-ab55...
About the Author
N8N_Community_Pick
Curator
Hand-picked high quality workflows from the global community.
Statistics
Related Workflows
Discover more workflows you might like
OpenAI Text-to-Speech Workflow
Generate audio from text using OpenAI's TTS API.
AI Assistant for Structured Metadata Generation
Automates the generation of structured metadata in English and Chinese using AI, leveraging communication platforms and various data sources.
Visa Requirement Checker
A workflow to check visa requirements based on user input, leveraging Langchain, Cohere embeddings, Weaviate vector store, and Anthropic LLM.