Unify LLM icon

Unify LLM

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

Actions10

Orchestration → Chain Structured

AI-generated

Summary

Stepwise reason then enforce JSON schema on model response.

Inputs

  • prompt (required) — Prompt or query text
  • schemaJson — JSON Schema object for structured output
  • systemPrompt — Optional system instruction
  • temperature — Sampling temperature
  • maxTokens — Maximum number of output tokens

Output shape

Returns a single item with json containing resource, operation, model: null, data: , schema: , reasoning: , usage: null, metadata: >

Prompt triggers two model invocations: first asks the model to reason step-by-step about the prompt; second re-prompts with the original prompt plus the reasoning appended and the JSON schema enforced. The model's JSON output is parsed and returned as data, with the raw reasoning text returned as reasoning.

Examples

Example 1: Workflow author chains a prompt through a model with structured JSON output and automatic reasoning.

Set prompt to the desired query, provide schemaJson (e.g., {type: object, properties: {}}), leave systemPrompt, temperature, maxTokens at defaults or adjust as needed. The node will output the model's structured data and its self-generated reasoning.

Links

Discussion