enable_structured_output

Turn on structured output for a model configuration. Supports OpenAI‑compatible
providers (OpenAI, Groq, Together, x.ai, DeepSeek), Anthropic, and Gemini.

Provides a unified interface to large language models across multiple
providers. Supports text generation, structured output with optional JSON
Schema validation, and embeddings. Includes tidyverse-friendly helpers,
chat session, consistent error handling, and parallel batch tools.

Ali Sanaei

LLMR

Interface for Large Language Model APIs in R

enable_structured_output function

<dl><dt>config</dt>
<dd>An llm_config object.</dd>
<dt>schema</dt>
<dd>A named list representing a JSON Schema.
If <code>NULL</code>, OpenAI-compatible providers enforce a JSON object; Gemini switches
to JSON mime type; Anthropic only injects a tool when a schema is supplied.</dd>
<dt>name</dt>
<dd>Character. Schema/tool name for providers requiring one. Default "llmr_schema".</dd>
<dt>method</dt>
<dd>One of c("auto","json_mode","tool_call"). "auto" chooses the best
per provider. You rarely need to change this.</dd>
<dt>strict</dt>
<dd>Logical. Request strict validation when supported (OpenAI-compatible).</dd></dl>

Arguments

Enable Structured Output (Provider-Agnostic) — enable_structured_output

<dl>

<dt>config</dt>
<dd>An llm_config object.</dd>


<dt>schema</dt>
<dd>A named list representing a JSON Schema.
If <code>NULL</code>, OpenAI-compatible providers enforce a JSON object; Gemini switches
to JSON mime type; Anthropic only injects a tool when a schema is supplied.</dd>


<dt>name</dt>
<dd>Character. Schema/tool name for providers requiring one. Default "llmr_schema".</dd>


<dt>method</dt>
<dd>One of c("auto","json_mode","tool_call"). "auto" chooses the best
per provider. You rarely need to change this.</dd>


<dt>strict</dt>
<dd>Logical. Request strict validation when supported (OpenAI-compatible).</dd>

</dl>

enable_structured_output: Enable Structured Output (Provider-Agnostic)

Description

Usage

Value

Arguments