Automated workflow
Workflow Description
An intelligent workflow combining an AI agent and vector search engine to process and analyze documents automatically. It splits texts into indexed chunks, then uses OpenAI models to answer queries based on document content.
How it works
- 1.Load document and convert its content into processable format
- 2.Split text into overlapping chunks using recursive character splitter
- 3.Convert chunks to vectors and store them in Milvus database
- 4.Route queries to AI agent for semantic search and response generation
- 5.Deliver results through chat interface to end user
Use cases
- Instant answers to questions about company policies, documentation, and procedures
- Automated analysis of reports and contracts to extract key information
Requirements
- Valid OpenAI API key with sufficient usage quota
- Active Milvus server and configured vector database instance
Service Value
Ideal as a smart automation service combining integrations and AI to produce ready-to-use results.
Apps Used
Details
How to Use
- 1.Click "Download Template"
- 2.Open your n8n dashboard
- 3.Go to Workflows > Import from File
- 4.Select downloaded file and configure credentials
Nodes Used (21)
When clicking "Execute Workflow"
Manual Trigger
Fetch Essay List
HTTP Request
Extract essay names
HTML Page
Split out into items
Split Out
Fetch essay texts
HTTP Request
Limit to first 3
Limit
Extract Text Only
HTML Page
Sticky Note3
Sticky Note
Sticky Note5
Sticky Note
Recursive Character Text Splitter1
Text Splitter Recursive Character Text Splitter
Milvus Vector Store
Vector Store Milvus
AI Agent
Agent
When chat message received
Chat Trigger
Sticky Note
Sticky Note
Default Data Loader
Document Default Data Loader
Milvus Vector Store as tool
Vector Store Milvus
Sticky Note1
Sticky Note
Embeddings OpenAI
OpenAI
OpenAI Chat Model
OpenAI
Embeddings OpenAI1
OpenAI
Sticky Note2
Sticky Note