← All N8N workflows
AI & researchChain LLMChat TriggerCodeIfOpenAI Chat Model

Dynamically switch between LLMs Template

Configured with Chain LLM, Chat Trigger, OpenAI Chat Model, Sentiment Analysis. Review the connections and setup before adapting this template.

Workflow preview
TriggerWhen chat messagereceivedChat TriggerCodeSwitch ModelCodeTransformSet LLM indexEdit FieldsTransformIncrease LLM indexEdit FieldsRoutingNo Operation, donothingNo OpRoutingCheck for expectederrorIfTransformLoop finished withoutresultsEdit FieldsTransformUnexpected errorEdit FieldsTransformReturn resultEdit FieldsAI & modelsOpenAI 4o-miniOpenAI Chat ModelAI & modelsOpenAI 4oOpenAI Chat ModelAI & modelsOpenAI o1OpenAI Chat ModelAI & modelsOpenAI Chat ModelOpenAI Chat ModelAI & modelsValidate responseSentiment AnalysisAI & modelsGenerate responseChain LLM

Node categories in this workflow

  • Trigger
  • Code
  • Transform
  • Routing
  • AI & models

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
When chat message receivedTriggerChat TriggerSee node parameters
Switch ModelCodeCodeSee node parameters
Set LLM indexTransformEdit FieldsSee node parameters
Increase LLM indexTransformEdit FieldsSee node parameters
No Operation, do nothingRoutingNo OpSee node parameters
Check for expected errorRoutingIfSee node parameters
Loop finished without resultsTransformEdit FieldsSee node parameters
Unexpected errorTransformEdit FieldsSee node parameters
Return resultTransformEdit FieldsSee node parameters
OpenAI 4o-miniAI & modelsOpenAI Chat ModelSee node parameters
OpenAI 4oAI & modelsOpenAI Chat ModelSee node parameters
OpenAI o1AI & modelsOpenAI Chat ModelSee node parameters
OpenAI Chat ModelAI & modelsOpenAI Chat ModelSee node parameters
Validate responseAI & modelsSentiment AnalysisSee node parameters
Generate responseAI & modelsChain LLMSee 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

  • openAiApi

Workflow notes

Customer complaint - example

Customer complaint - example

I really love waiting two weeks just to get a keyboard that doesn’t even work. Great job. Any chance I could actually use the thing I paid for sometime this month?

Sticky Note1

Defines the LLM node by index which should be used.

Sticky Note2

Dynamically connects the LLM by the index provided in the previous node.

Sticky Note3

Check if LangChain Code Node ran into error. Currently only supports error output from main Node

Sticky Note4

Generates a polite answer based on the customers complaint.

Sticky Note5

Analyses the generated answer by certain criteria

Sticky Note6

Increases the index to choose the next available LLM on the next run

Dynamically switch between LLMs Template

Dynamically switch between LLMs Template

Purpose and structure

This folder contains the Dynamically switch between LLMs Template workflow. Its executable nodes use chainLlm, chatTrigger, code, if, lmChatOpenAi, noOp, sentimentAnalysis, set. 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

When chat message received

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/Noop/1838_Noop_Stickynote_Automation_Triggered.json MIT; preserve source notices.

More in AI & research