Truefoundry Chat Model icon

Truefoundry Chat Model

Truefoundry Chat Model with automatic user attribution

Truefoundry Chat Model

AI-generated

Summary

Generate a Truefoundry-configured chat language model with automatic user attribution.

Inputs

  • model (required) — The model to use for generating completions. Models are loaded from your AI gateway. Select from list or enter ID directly.
  • options — Generation configuration. Controls temperature, max tokens, penalties, top p, and timeout.
  • attributionSettings — Fallback attribution values for when n8n context is unavailable (webhooks, scheduled triggers).

Output shape

{ response: ChatOpenAI }

Emits a ChatOpenAI instance from @langchain/openai, pre-configured with the selected Truefoundry model, generation options, and attribution metadata injected via X-TFY-METADATA header.

Examples

Example 1: Basic chat completion

Set model to desired Truefoundry model ID, optionally adjust temperature and maxTokens, leave attributionSettings at defaults if running within n8n context.

Links

Discussion