← All N8N workflows
AI & researchAgentHTTP RequestIfLM Chat Azure Open AiEdit Fields

Chatbot AI

Configured with Agent, HTTP Request, LM Chat Azure Open Ai, Webhook. Review the connections and setup before adapting this template.

Workflow preview
Web / APILoading AnimationHTTP RequestWeb / APIReplyMessage - NotsupportedHTTP RequestAI & modelsAI AgentAgentAI & modelsAzure OpenAI Chat ModelLM Chat Azure Open AiWeb / APIReplyMessage - LineHTTP RequestTriggerLine ChatbotWebhookRoutingCheck Message TypeIsText?IfTransformFormat ReplyEdit Fields

Node categories in this workflow

  • Web / API
  • AI & models
  • Trigger
  • Routing
  • Transform

Icons describe general node roles, inferred from node types. Inspect the parameters for the configured action.

Drag to pan; use + and − to zoom. Reconstructed from the exported node positions; nothing runs here. Dashed lines represent non-main connections. Full node names and notes appear below.

How it works

The exported workflow contains the following configured nodes. Their connections are shown above; inspect the JSON for the complete logic, expressions, and external actions.

Workflow node names, types, and operations
NodeCategoryTypeOperation
Loading AnimationWeb / APIHTTP RequestPOST
ReplyMessage - Not supportedWeb / APIHTTP RequestPOST
AI AgentAI & modelsAgentSee node parameters
Azure OpenAI Chat ModelAI & modelsLM Chat Azure Open AiSee node parameters
ReplyMessage - LineWeb / APIHTTP RequestPOST
Line ChatbotTriggerWebhookSee node parameters
Check Message Type IsText?RoutingIfSee node parameters
Format ReplyTransformEdit FieldsSee node parameters

Setup

  1. Download the JSON and import it into an isolated n8n instance. Leave the workflow inactive.
  2. Connect your own credentials through n8n’s credential store. Replace REPLACE_WITH_* values with your resource identifiers.
  3. Inspect API destinations, Code nodes, database queries, file paths, and outbound actions.
  4. Run with synthetic data and harmless destinations. Enable triggers only after checking the actual outputs.

Requirements

An n8n instance with the listed node types and compatible versions. Service-connected workflows may require accounts, credentials, or paid APIs.

Credential types declared in the source

  • azureOpenAiApi
  • httpHeaderAuth

Workflow notes

Sticky Note

For non-text, we do not process and just provide user that it's not supported right now

Sticky Note1

Webhook from Line

You need to set-up this webhook at Line Manager or Line Developer Console

You'll need to copy Webhook URL from this node to put in Line Console

Also, don't forget to remove 'test' part when going for production

https://developers.line.biz/en/docs/messaging-api/receiving-messages/

Sticky Note2

Line Loading Animation

This node is to only give ... loading animation back in Line.

It seems stupid but it actually tells user that the workflow is running and you are not left waiting without hope

To authorize, use header authorization

https://developers.line.biz/en/docs/messaging-api/use-loading-indicator/

Sticky Note3

Reply Message

You can send anything with reply-token without using your broadcast quota.

To use header auth:

  • select generic > header auth
  • add new
  • name = Authorization
  • value = Bearer
  • you can rename this credential on top

https://developers.line.biz/en/docs/messaging-api/sending-messages/

Sticky Note4

The output from AI-Agent is not properly formatted for JSON to send via reply. So you need to edit it a bit

Sticky Note5

Chat Model (LLM)

To use chat LLM, you need to have AI Agent or LLM Chain. Then you can connect the model to the node.

  • edit system prompt on the mother node.
  • edit model parameters eg. temperature at the AI node (closer to 1 = more creative)

Azure OpenAI Ref : https://davoy.tech/how-to-use-azure-openai-2/

Or you can choose different models

Chatbot AI

Chatbot AI

Purpose and structure

This folder contains the Chatbot AI workflow. Its executable nodes use agent, httpRequest, if, lmChatAzureOpenAi, set, webhook. The table and connection map below are derived from the JSON, not an inferred guarantee of behavior.

Setup

Import inactive. Configure your own credentials and replace REPLACE_WITH_* values. Review external destinations and Code nodes before running.

Entry points

Line Chatbot

Verification

Sanitized source candidate; not runtime-tested. This overview is generated from node metadata. Read the folder README for the connection map, credential types, and license.

Attribution

https://github.com/Zie619/n8n-workflows/blob/94007c1445d9258a7da116646b79473e7c7c3282/workflows/Http/1868_HTTP_Stickynote_Automate_Webhook.json MIT; preserve source notices.

More in AI & research