Unify LLM icon

Unify LLM

LangChain-style orchestration and multi-provider intelligence via Unify LLM

Actions10

Orchestration → Routed Generate

AI-generated

Summary

Routes a prompt through a Bayesian-Pareto-Prim ensemble router to select the best model, then generates a text response via the matched connected AI model.

Inputs

  • prompt (required) — Prompt or query text
  • systemPrompt — Optional system instruction
  • temperature — Sampling temperature
  • maxTokens — Maximum number of output tokens
  • candidateModels — Comma-separated models used by the combined router ensemble

Output shape

object

Returned per item in the workflow execution. Includes routing metadata and generated text.

Examples

Example 1: Standard routed generation with default models

Uses default candidate models (gpt-4o-mini, claude-3-5-sonnet-20241022, gemini-1.5-pro, llama3.1) and default temperature (0.7) and max tokens (512). Connect at least one AI model to the Chat Model input; the node automatically routes and invokes it.

Links

Discussion