Public Form Auto Triage
detail.loadingPreview
Automate the triage and enrichment of data submitted through a public form using RAG and Supabase.
🚀Ready to Deploy This Workflow?
About This Workflow
This workflow automates the processing of data received from a public form. It leverages a webhook to trigger the process, splits incoming text into manageable chunks, generates embeddings using Cohere, and stores these embeddings in a Supabase vector store. It then uses a RAG (Retrieval Augmented Generation) agent, powered by Anthropic's chat model and a vector tool for context retrieval from Supabase, to process the data. Finally, the outcome is logged to a Google Sheet, and alerts are sent to Slack in case of errors.
Key Features
- Webhook Trigger: Accepts data submissions via a POST request to a designated endpoint.
- Text Splitting: Divides incoming text into smaller, processable chunks with defined overlap.
- Embeddings Generation: Creates vector representations of text using Cohere's models.
- Supabase Vector Store Integration: Inserts and queries embeddings within a Supabase vector database.
- RAG Agent: Employs Retrieval Augmented Generation for intelligent data processing and response generation.
- Anthropic Chat Model: Utilizes Anthropic's models for advanced conversational AI capabilities.
- Google Sheets Logging: Appends processed results to a Google Sheet for record-keeping.
- Slack Alerting: Sends notifications to a Slack channel in case of workflow errors.
How To Use
- Webhook Trigger: Configure the
Webhook Triggernode with the desired path (public-form-auto-triage). Send POST requests with your form data to this endpoint. - Text Splitter: Adjust
chunkSizeandchunkOverlapparameters in theText Splitternode based on the expected length of your input data. - Embeddings: Ensure your
COHERE_APIcredentials are set up. Themodelis set toembed-english-v3.0for English text. - Supabase Insert: Configure your
SUPABASE_APIcredentials. TheindexNameshould match your Supabase vector table. - Supabase Query: This node is used for retrieving data from Supabase. It's connected to the
Embeddingsnode. - Vector Tool: The
Vector Toolnode defines the vector store for the RAG agent. - Window Memory: The
Window Memorynode manages the conversation history for the agent. - Chat Model: Configure your
ANTHROPIC_APIcredentials. This node provides the language model for the RAG agent. - RAG Agent: The
RAG Agentnode orchestrates the RAG process. ThepromptTypeis 'define' and thetextparameter uses{{ $json }}to inject the incoming data. ThesystemMessageprovides context to the agent. - Append Sheet: Configure your
SHEETS_APIcredentials. Specify thedocumentIdandsheetNamefor logging. The 'Status' column will be populated with the output from the 'RAG Agent'. - Slack Alert: Configure your
SLACK_APIcredentials to receive error notifications in the specified channel (#alerts).
Apps Used
Workflow JSON
{
"id": "bbe90c75-e05e-4f5f-bca4-207c1e246049",
"name": "Public Form Auto Triage",
"nodes": 0,
"category": "AI",
"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: bbe90c75-e05e...
About the Author
Crypto_Watcher
Web3 Developer
Automated trading bots and blockchain monitoring workflows.
Statistics
Related Workflows
Discover more workflows you might like
Build an AI Documentation Expert Chatbot with Gemini RAG
This n8n workflow automates the creation of an AI-powered expert chatbot capable of answering questions based on your documentation. It intelligently ingests, cleans, and processes your knowledge base, preparing it for a Retrieval Augmented Generation (RAG) pipeline with Google Gemini.
Generate Multilingual Image Captions and Overlay
This workflow generates captions for images using Google Gemini and overlays them onto the image, with support for multilingual output.
LangChain Workflow Retriever Example
Demonstrates using LangChain's Retriever QA Chain to query data retrieved from another workflow.