Example of a RAG application workflow with Webhook integration
Workflow Description
A retrieval-augmented generation workflow that accepts queries via webhook, processes documents through intelligent text splitting, retrieves relevant content from Qdrant vector database using embeddings, and generates accurate responses with Gemini LLM. Results can be published to X or returned directly to clients.
How it works
- 1.Receive incoming request through webhook and store initial data
- 2.Load documents and split them into manageable text segments using recursive character splitting
- 3.Search vector store in Qdrant and retrieve the most relevant documents
- 4.Generate contextual responses using Gemini language model
- 5.Deliver results via X integration or direct webhook response
Use cases
- Intelligent question-answering system powered by company documentation
- Internal search engine that finds relevant information and explains it naturally
- API-driven document analysis and data processing pipeline
- Automated publishing of insights and answers to social media based on queries
Requirements
- Qdrant vector database server configured with pre-loaded text embeddings
- Google Cloud Gemini API credentials and valid authentication
- X platform API credentials for automated posting capability
- Base documents indexed and stored in the vector database
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 (34)
Bitrix24 Handler
Webhook
Credentials
Set
Validate Token
If
Route Event
Switch
Process Message
Function
Process Join
Function
Process Install
Function
Register Bot
HTTP Request
Send Message
HTTP Request
Send Join Message
HTTP Request
Process Delete
No Op
Success Response
Webhook
Error Response
Webhook
Merge parameters for Subworkflow
Merge
Get a list of available storages
HTTP Request
Get a list of List of Files and Folders
HTTP Request
Get a list of Folders files
HTTP Request
Download file
HTTP Request
Default Data Loader
Document Default Data Loader
Recursive Character Text Splitter
Text Splitter Recursive Character Text Splitter
Split Out folder files and folders
Split Out
Filter for files
Filter
Move files to Vector stored folder
HTTP Request
Execute Workflow Trigger
Execute Workflow Trigger
Sticky Note
Sticky Note
Qdrant Vector Store
Vector Store Qdrant
Embeddings Ollama
Embeddings Ollama
Vector Store Retriever
Retriever Vector Store
Question and Answer Chain
Chain Retrieval Qa
Prepare output parameters
Set
Embeddings Ollama1
Embeddings Ollama
Google Gemini Chat Model
Gemini Model
Qdrant Vector Store1
Vector Store Qdrant
Execute subworkflow
Execute Workflow