El botón Generar de Playground te permite generar prompts, funciones y esquemas con solo describir tu tarea. Esta guía explica en detalle cómo funciona.
Descripción general
Crear prompts y esquemas desde cero puede llevar tiempo, por lo que generarlos puede ayudarte a empezar rápidamente. El botón Generar utiliza dos enfoques principales:
- Prompts: usamos metaprompts que incorporan prácticas recomendadas para generar o mejorar prompts.
- Esquemas: usamos metaesquemas que producen JSON y sintaxis de funciones válidos.
Aunque actualmente usamos metaprompts y metaesquemas, en el futuro podríamos integrar técnicas más avanzadas, como DSPy y el “descenso de gradiente”.
Prompts
Un metaprompt le indica al modelo que cree un buen prompt a partir de la descripción de tu tarea o que mejore uno existente. Los metaprompts de Playground se basan en nuestras prácticas recomendadas de ingeniería de prompts y en nuestra experiencia práctica con los usuarios.
Usamos metaprompts específicos para distintos tipos de salida, como audio, para garantizar que los prompts generados cumplan con el formato esperado.
Metaprompts
Salida de texto
Metaprompt de texto
JavaScript
import OpenAI from "openai";
const client = new OpenAI();
const metaPrompt = `Given a task description or existing prompt, produce a detailed system prompt to guide a language model in completing the task effectively.
# Guidelines
- Understand the Task: Grasp the main objective, goals, requirements, constraints, and expected output.
- Minimal Changes: If an existing prompt is provided, improve it only if it's simple. For complex prompts, enhance clarity and add missing elements without altering the original structure.
- Reasoning Before Conclusions**: Encourage reasoning steps before any conclusions are reached. ATTENTION! If the user provides examples where the reasoning happens afterward, REVERSE the order! NEVER START EXAMPLES WITH CONCLUSIONS!
- Reasoning Order: Call out reasoning portions of the prompt and conclusion parts (specific fields by name). For each, determine the ORDER in which this is done, and whether it needs to be reversed.
- Conclusion, classifications, or results should ALWAYS appear last.
- Examples: Include high-quality examples if helpful, using placeholders [in brackets] for complex elements.
- What kinds of examples may need to be included, how many, and whether they are complex enough to benefit from placeholders.
- Clarity and Conciseness: Use clear, specific language. Avoid unnecessary instructions or bland statements.
- Formatting: Use markdown features for readability. DO NOT USE \`\`\` CODE BLOCKS UNLESS SPECIFICALLY REQUESTED.
- Preserve User Content: If the input task or prompt includes extensive guidelines or examples, preserve them entirely, or as closely as possible. If they are vague, consider breaking down into sub-steps. Keep any details, guidelines, examples, variables, or placeholders provided by the user.
- Constants: DO include constants in the prompt, as they are not susceptible to prompt injection. Such as guides, rubrics, and examples.
- Output Format: Explicitly the most appropriate output format, in detail. This should include length and syntax (e.g. short sentence, paragraph, JSON, etc.)
- For tasks outputting well-defined or structured data (classification, JSON, etc.) bias toward outputting a JSON.
- JSON should never be wrapped in code blocks (\`\`\`) unless explicitly requested.
The final prompt you output should adhere to the following structure below. Do not include any additional commentary, only output the completed system prompt. SPECIFICALLY, do not include any additional messages at the start or end of the prompt. (e.g. no "---")
[Concise instruction describing the task - this should be the first line in the prompt, no section header]
[Additional details as needed.]
[Optional sections with headings or bullet points for detailed steps.]
# Steps [optional]
[optional: a detailed breakdown of the steps necessary to accomplish the task]
# Output Format
[Specifically call out how the output should be formatted, be it response length, structure e.g. JSON, markdown, etc]
# Examples [optional]
[Optional: 1-3 well-defined examples with placeholders if necessary. Clearly mark where examples start and end, and what the input and output are. User placeholders as necessary.]
[If the examples are shorter than what a realistic example is expected to be, make a reference with () explaining how real examples should be longer / shorter / different. AND USE PLACEHOLDERS! ]
# Notes [optional]
[optional: edge cases, details, and an area to call or repeat out specific important considerations]`;
async function generatePrompt(taskOrPrompt) {
const completion = await client.chat.completions.create({
model: "gpt-6-astra",
messages: [
{ role: "system", content: metaPrompt },
{
role: "user",
content: "Task, Goal, or Current Prompt:\n" + taskOrPrompt,
},
],
});
return completion.choices[0].message.content;
}
console.log(
await generatePrompt("Write a concise product launch announcement.")
);Salida de audio
Metaprompt de audio
JavaScript
import OpenAI from "openai";
const client = new OpenAI();
const metaPrompt = `Given a task description or existing prompt, produce a detailed system prompt to guide a realtime audio output language model in completing the task effectively.
# Guidelines
- Understand the Task: Grasp the main objective, goals, requirements, constraints, and expected output.
- Tone: Make sure to specifically call out the tone. By default it should be emotive and friendly, and speak quickly to avoid keeping the user just waiting.
- Audio Output Constraints: Because the model is outputting audio, the responses should be short and conversational.
- Minimal Changes: If an existing prompt is provided, improve it only if it's simple. For complex prompts, enhance clarity and add missing elements without altering the original structure.
- Examples: Include high-quality examples if helpful, using placeholders [in brackets] for complex elements.
- What kinds of examples may need to be included, how many, and whether they are complex enough to benefit from placeholders.
- It is very important that any examples included reflect the short, conversational output responses of the model.
Keep the sentences very short by default. Instead of 3 sentences in a row by the assistant, it should be split up with a back and forth with the user instead.
- By default each sentence should be a few words only (5-20ish words). However, if the user specifically asks for "short" responses, then the examples should truly have 1-10 word responses max.
- Make sure the examples are multi-turn (at least 4 back-forth-back-forth per example), not just one questions an response. They should reflect an organic conversation.
- Clarity and Conciseness: Use clear, specific language. Avoid unnecessary instructions or bland statements.
- Preserve User Content: If the input task or prompt includes extensive guidelines or examples, preserve them entirely, or as closely as possible. If they are vague, consider breaking down into sub-steps. Keep any details, guidelines, examples, variables, or placeholders provided by the user.
- Constants: DO include constants in the prompt, as they are not susceptible to prompt injection. Such as guides, rubrics, and examples.
The final prompt you output should adhere to the following structure below. Do not include any additional commentary, only output the completed system prompt. SPECIFICALLY, do not include any additional messages at the start or end of the prompt. (e.g. no "---")
[Concise instruction describing the task - this should be the first line in the prompt, no section header]
[Additional details as needed.]
[Optional sections with headings or bullet points for detailed steps.]
# Examples [optional]
[Optional: 1-3 well-defined examples with placeholders if necessary. Clearly mark where examples start and end, and what the input and output are. User placeholders as necessary.]
[If the examples are shorter than what a realistic example is expected to be, make a reference with () explaining how real examples should be longer / shorter / different. AND USE PLACEHOLDERS! ]
# Notes [optional]
[optional: edge cases, details, and an area to call or repeat out specific important considerations]`;
async function generatePrompt(taskOrPrompt) {
const completion = await client.chat.completions.create({
model: "gpt-6-astra",
messages: [
{ role: "system", content: metaPrompt },
{
role: "user",
content: "Task, Goal, or Current Prompt:\n" + taskOrPrompt,
},
],
});
return completion.choices[0].message.content;
}
console.log(
await generatePrompt("Create a friendly voice assistant for a bike shop.")
);Edición de prompts
Para editar prompts, usamos un metaprompt ligeramente modificado. Aunque las modificaciones directas son fáciles de aplicar, identificar los cambios necesarios para revisiones más abiertas puede ser difícil. Para resolverlo, incluimos una sección de razonamiento al principio de la respuesta. Esta sección ayuda al modelo a determinar qué cambios se necesitan al evaluar la claridad del prompt existente, el orden de la cadena de pensamiento, la estructura general y el nivel de detalle, entre otros factores. La sección de razonamiento propone mejoras y luego se elimina de la respuesta final durante el procesamiento.
Salida de texto
Metaprompt de texto para ediciones
JavaScript
import OpenAI from "openai";
const client = new OpenAI();
const metaPrompt = `Given a current prompt and a change description, produce a detailed system prompt to guide a language model in completing the task effectively.
Your final output will be the full corrected prompt verbatim. However, before that, at the very beginning of your response, use <reasoning> tags to analyze the prompt and determine the following, explicitly:
<reasoning>
- Simple Change: (yes/no) Is the change description explicit and simple? (If so, skip the rest of these questions.)
- Reasoning: (yes/no) Does the current prompt use reasoning, analysis, or chain of thought?
- Identify: (max 10 words) if so, which section(s) utilize reasoning?
- Conclusion: (yes/no) is the chain of thought used to determine a conclusion?
- Ordering: (before/after) is the chain of though located before or after
- Structure: (yes/no) does the input prompt have a well defined structure
- Examples: (yes/no) does the input prompt have few-shot examples
- Representative: (1-5) if present, how representative are the examples?
- Complexity: (1-5) how complex is the input prompt?
- Task: (1-5) how complex is the implied task?
- Necessity: ()
- Specificity: (1-5) how detailed and specific is the prompt? (not to be confused with length)
- Prioritization: (list) what 1-3 categories are the MOST important to address.
- Conclusion: (max 30 words) given the previous assessment, give a very concise, imperative description of what should be changed and how. this does not have to adhere strictly to only the categories listed
</reasoning>
# Guidelines
- Understand the Task: Grasp the main objective, goals, requirements, constraints, and expected output.
- Minimal Changes: If an existing prompt is provided, improve it only if it's simple. For complex prompts, enhance clarity and add missing elements without altering the original structure.
- Reasoning Before Conclusions**: Encourage reasoning steps before any conclusions are reached. ATTENTION! If the user provides examples where the reasoning happens afterward, REVERSE the order! NEVER START EXAMPLES WITH CONCLUSIONS!
- Reasoning Order: Call out reasoning portions of the prompt and conclusion parts (specific fields by name). For each, determine the ORDER in which this is done, and whether it needs to be reversed.
- Conclusion, classifications, or results should ALWAYS appear last.
- Examples: Include high-quality examples if helpful, using placeholders [in brackets] for complex elements.
- What kinds of examples may need to be included, how many, and whether they are complex enough to benefit from placeholders.
- Clarity and Conciseness: Use clear, specific language. Avoid unnecessary instructions or bland statements.
- Formatting: Use markdown features for readability. DO NOT USE \`\`\` CODE BLOCKS UNLESS SPECIFICALLY REQUESTED.
- Preserve User Content: If the input task or prompt includes extensive guidelines or examples, preserve them entirely, or as closely as possible. If they are vague, consider breaking down into sub-steps. Keep any details, guidelines, examples, variables, or placeholders provided by the user.
- Constants: DO include constants in the prompt, as they are not susceptible to prompt injection. Such as guides, rubrics, and examples.
- Output Format: Explicitly the most appropriate output format, in detail. This should include length and syntax (e.g. short sentence, paragraph, JSON, etc.)
- For tasks outputting well-defined or structured data (classification, JSON, etc.) bias toward outputting a JSON.
- JSON should never be wrapped in code blocks (\`\`\`) unless explicitly requested.
The final prompt you output should adhere to the following structure below. Do not include any additional commentary, only output the completed system prompt. SPECIFICALLY, do not include any additional messages at the start or end of the prompt. (e.g. no "---")
[Concise instruction describing the task - this should be the first line in the prompt, no section header]
[Additional details as needed.]
[Optional sections with headings or bullet points for detailed steps.]
# Steps [optional]
[optional: a detailed breakdown of the steps necessary to accomplish the task]
# Output Format
[Specifically call out how the output should be formatted, be it response length, structure e.g. JSON, markdown, etc]
# Examples [optional]
[Optional: 1-3 well-defined examples with placeholders if necessary. Clearly mark where examples start and end, and what the input and output are. User placeholders as necessary.]
[If the examples are shorter than what a realistic example is expected to be, make a reference with () explaining how real examples should be longer / shorter / different. AND USE PLACEHOLDERS! ]
# Notes [optional]
[optional: edge cases, details, and an area to call or repeat out specific important considerations]
[NOTE: you must start with a <reasoning> section. the immediate next token you produce should be <reasoning>]`;
async function generatePrompt(taskOrPrompt) {
const completion = await client.chat.completions.create({
model: "gpt-6-astra",
messages: [
{ role: "system", content: metaPrompt },
{
role: "user",
content: "Task, Goal, or Current Prompt:\n" + taskOrPrompt,
},
],
});
return completion.choices[0].message.content;
}
console.log(
await generatePrompt("Make this support prompt more concise and empathetic.")
);Salida de audio
Metaprompt de audio para ediciones
JavaScript
import OpenAI from "openai";
const client = new OpenAI();
const metaPrompt = `Given a current prompt and a change description, produce a detailed system prompt to guide a realtime audio output language model in completing the task effectively.
Your final output will be the full corrected prompt verbatim. However, before that, at the very beginning of your response, use <reasoning> tags to analyze the prompt and determine the following, explicitly:
<reasoning>
- Simple Change: (yes/no) Is the change description explicit and simple? (If so, skip the rest of these questions.)
- Reasoning: (yes/no) Does the current prompt use reasoning, analysis, or chain of thought?
- Identify: (max 10 words) if so, which section(s) utilize reasoning?
- Conclusion: (yes/no) is the chain of thought used to determine a conclusion?
- Ordering: (before/after) is the chain of though located before or after
- Structure: (yes/no) does the input prompt have a well defined structure
- Examples: (yes/no) does the input prompt have few-shot examples
- Representative: (1-5) if present, how representative are the examples?
- Complexity: (1-5) how complex is the input prompt?
- Task: (1-5) how complex is the implied task?
- Necessity: ()
- Specificity: (1-5) how detailed and specific is the prompt? (not to be confused with length)
- Prioritization: (list) what 1-3 categories are the MOST important to address.
- Conclusion: (max 30 words) given the previous assessment, give a very concise, imperative description of what should be changed and how. this does not have to adhere strictly to only the categories listed
</reasoning>
# Guidelines
- Understand the Task: Grasp the main objective, goals, requirements, constraints, and expected output.
- Tone: Make sure to specifically call out the tone. By default it should be emotive and friendly, and speak quickly to avoid keeping the user just waiting.
- Audio Output Constraints: Because the model is outputting audio, the responses should be short and conversational.
- Minimal Changes: If an existing prompt is provided, improve it only if it's simple. For complex prompts, enhance clarity and add missing elements without altering the original structure.
- Examples: Include high-quality examples if helpful, using placeholders [in brackets] for complex elements.
- What kinds of examples may need to be included, how many, and whether they are complex enough to benefit from placeholders.
- It is very important that any examples included reflect the short, conversational output responses of the model.
Keep the sentences very short by default. Instead of 3 sentences in a row by the assistant, it should be split up with a back and forth with the user instead.
- By default each sentence should be a few words only (5-20ish words). However, if the user specifically asks for "short" responses, then the examples should truly have 1-10 word responses max.
- Make sure the examples are multi-turn (at least 4 back-forth-back-forth per example), not just one questions an response. They should reflect an organic conversation.
- Clarity and Conciseness: Use clear, specific language. Avoid unnecessary instructions or bland statements.
- Preserve User Content: If the input task or prompt includes extensive guidelines or examples, preserve them entirely, or as closely as possible. If they are vague, consider breaking down into sub-steps. Keep any details, guidelines, examples, variables, or placeholders provided by the user.
- Constants: DO include constants in the prompt, as they are not susceptible to prompt injection. Such as guides, rubrics, and examples.
The final prompt you output should adhere to the following structure below. Do not include any additional commentary, only output the completed system prompt. SPECIFICALLY, do not include any additional messages at the start or end of the prompt. (e.g. no "---")
[Concise instruction describing the task - this should be the first line in the prompt, no section header]
[Additional details as needed.]
[Optional sections with headings or bullet points for detailed steps.]
# Examples [optional]
[Optional: 1-3 well-defined examples with placeholders if necessary. Clearly mark where examples start and end, and what the input and output are. User placeholders as necessary.]
[If the examples are shorter than what a realistic example is expected to be, make a reference with () explaining how real examples should be longer / shorter / different. AND USE PLACEHOLDERS! ]
# Notes [optional]
[optional: edge cases, details, and an area to call or repeat out specific important considerations]
[NOTE: you must start with a <reasoning> section. the immediate next token you produce should be <reasoning>]`;
async function generatePrompt(taskOrPrompt) {
const completion = await client.chat.completions.create({
model: "gpt-6-astra",
messages: [
{ role: "system", content: metaPrompt },
{
role: "user",
content: "Task, Goal, or Current Prompt:\n" + taskOrPrompt,
},
],
});
return completion.choices[0].message.content;
}
console.log(
await generatePrompt(
"Make this voice assistant prompt warmer and more direct."
)
);Esquemas
Los esquemas de resultados estructurados y los esquemas de funciones son, a su vez, objetos JSON, por lo que usamos resultados estructurados para generarlos. Esto requiere definir un esquema para el resultado deseado, que en este caso también es un esquema. Para ello, usamos un esquema que se describe a sí mismo: un metaesquema.
Como el campo parameters de un esquema de función es, a su vez, un esquema, usamos el mismo metaesquema para generar funciones.
Definir un metaesquema con restricciones
Resultados estructurados admite dos modos: strict=true y strict=false. Ambos usan el mismo modelo entrenado para seguir el esquema proporcionado, pero solo el “modo estricto” garantiza el cumplimiento exacto mediante un muestreo con restricciones.
Nuestro objetivo es generar esquemas para el modo estricto usando el propio modo estricto. Sin embargo, los metaesquemas oficiales de la especificación JSON Schema dependen de características que actualmente no se admiten en el modo estricto. Esto plantea dificultades que afectan tanto a los esquemas de entrada como a los de salida.
- Esquema de entrada: no podemos usar características no admitidas en el esquema de entrada para describir el esquema de salida.
- Esquema de salida: el esquema generado no debe incluir características no admitidas.
Como necesitamos generar nuevas claves en el esquema de salida, el metaesquema de entrada debe usar additionalProperties. Esto significa que actualmente no podemos usar el modo estricto para generar esquemas. Sin embargo, queremos que el esquema generado cumpla con las restricciones del modo estricto.
Para superar esta limitación, definimos un pseudometaesquema : un metaesquema que usa características no admitidas en el modo estricto para describir únicamente las que sí se admiten en ese modo. En esencia, este enfoque permite definir el metaesquema fuera del modo estricto y, al mismo tiempo, garantizar que los esquemas generados cumplan con sus restricciones.
Deep dive
Cómo diseñamos el pseudometaesquema
Construir un metaesquema con restricciones es una tarea difícil, así que recurrimos a nuestros modelos para que nos ayudaran.
Comenzamos por proporcionar a o1-preview y gpt-4o, en modo JSON, una descripción de nuestro objetivo basada en la documentación de resultados estructurados.
Después de algunas iteraciones, desarrollamos nuestro primer metaesquema funcional.
Luego usamos gpt-4o con resultados estructurados y proporcionamos ese esquema inicial junto con la descripción de nuestra tarea y la documentación para generar mejores candidatos. En cada iteración, usamos un esquema mejorado para generar el siguiente, hasta que finalmente lo revisamos minuciosamente de forma manual.
Por último, después de limpiar la salida, validamos los esquemas con un conjunto de evaluaciones para esquemas y funciones.
Limpieza de la salida
El modo estricto garantiza el cumplimiento exacto del esquema. Sin embargo, como no podemos usarlo durante la generación, necesitamos validar y transformar la salida después de generarla.
Después de generar un esquema, realizamos los siguientes pasos:
- Establecer
additionalPropertiesenfalsepara todos los objetos. - Marcar todas las propiedades como obligatorias.
- Para los esquemas de resultados estructurados, incluirlos dentro de un objeto
json_schema. - Para las funciones, incluirlas dentro de un objeto
function.
El objeto function de Realtime API difiere ligeramente del de la API para completar chats, pero usa el mismo esquema.
Metaesquemas
Cada metaesquema tiene un prompt correspondiente que incluye unos pocos ejemplos. Al combinar estos prompts con la confiabilidad de los resultados estructurados, incluso sin el modo estricto, pudimos generar esquemas.
Esquema de resultado estructurado
Metaesquema de resultado estructurado
JavaScript
import OpenAI from "openai";
const client = new OpenAI();
const metaSchema = {
name: "metaschema",
schema: {
type: "object",
properties: {
name: {
type: "string",
description: "The name of the schema",
},
type: {
type: "string",
enum: ["object", "array", "string", "number", "boolean", "null"],
},
properties: {
type: "object",
additionalProperties: {
$ref: "#/$defs/schema_definition",
},
},
items: {
anyOf: [
{
$ref: "#/$defs/schema_definition",
},
{
type: "array",
items: {
$ref: "#/$defs/schema_definition",
},
},
],
},
required: {
type: "array",
items: {
type: "string",
},
},
additionalProperties: {
type: "boolean",
},
},
required: ["type"],
additionalProperties: false,
if: {
properties: {
type: {
const: "object",
},
},
},
then: {
required: ["properties"],
},
$defs: {
schema_definition: {
type: "object",
properties: {
type: {
type: "string",
enum: ["object", "array", "string", "number", "boolean", "null"],
},
properties: {
type: "object",
additionalProperties: {
$ref: "#/$defs/schema_definition",
},
},
items: {
anyOf: [
{
$ref: "#/$defs/schema_definition",
},
{
type: "array",
items: {
$ref: "#/$defs/schema_definition",
},
},
],
},
required: {
type: "array",
items: {
type: "string",
},
},
additionalProperties: {
type: "boolean",
},
},
required: ["type"],
additionalProperties: false,
if: {
properties: {
type: {
const: "object",
},
},
},
then: {
required: ["properties"],
},
},
},
},
};
const metaPrompt = `# Instructions
Return a valid schema for the described JSON.
You must also make sure:
- all fields in an object are set as required
- I REPEAT, ALL FIELDS MUST BE MARKED AS REQUIRED
- all objects must have additionalProperties set to false
- because of this, some cases like "attributes" or "metadata" properties that would normally allow additional properties should instead have a fixed set of properties
- all objects must have properties defined
- field order matters. any form of "thinking" or "explanation" should come before the conclusion
- $defs must be defined under the schema param
Notable keywords NOT supported include:
- For objects: unevaluatedProperties, propertyNames, minProperties, maxProperties
- For arrays: unevaluatedItems, contains, minContains, maxContains, uniqueItems
Other notes:
- definitions and recursion are supported
- only if necessary to include references e.g. "$defs", it must be inside the "schema" object
# Examples
Input: Generate a math reasoning schema with steps and a final answer.
Output: {
"name": "math_reasoning",
"type": "object",
"properties": {
"steps": {
"type": "array",
"description": "A sequence of steps involved in solving the math problem.",
"items": {
"type": "object",
"properties": {
"explanation": {
"type": "string",
"description": "Description of the reasoning or method used in this step."
},
"output": {
"type": "string",
"description": "Result or outcome of this specific step."
}
},
"required": [
"explanation",
"output"
],
"additionalProperties": false
}
},
"final_answer": {
"type": "string",
"description": "The final solution or answer to the math problem."
}
},
"required": [
"steps",
"final_answer"
],
"additionalProperties": false
}
Input: Give me a linked list
Output: {
"name": "linked_list",
"type": "object",
"properties": {
"linked_list": {
"$ref": "#/$defs/linked_list_node",
"description": "The head node of the linked list."
}
},
"$defs": {
"linked_list_node": {
"type": "object",
"description": "Defines a node in a singly linked list.",
"properties": {
"value": {
"type": "number",
"description": "The value stored in this node."
},
"next": {
"anyOf": [
{
"$ref": "#/$defs/linked_list_node"
},
{
"type": "null"
}
],
"description": "Reference to the next node; null if it is the last node."
}
},
"required": [
"value",
"next"
],
"additionalProperties": false
}
},
"required": [
"linked_list"
],
"additionalProperties": false
}
Input: Dynamically generated UI
Output: {
"name": "ui",
"type": "object",
"properties": {
"type": {
"type": "string",
"description": "The type of the UI component",
"enum": [
"div",
"button",
"header",
"section",
"field",
"form"
]
},
"label": {
"type": "string",
"description": "The label of the UI component, used for buttons or form fields"
},
"children": {
"type": "array",
"description": "Nested UI components",
"items": {
"$ref": "#"
}
},
"attributes": {
"type": "array",
"description": "Arbitrary attributes for the UI component, suitable for any element",
"items": {
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "The name of the attribute, for example onClick or className"
},
"value": {
"type": "string",
"description": "The value of the attribute"
}
},
"required": [
"name",
"value"
],
"additionalProperties": false
}
}
},
"required": [
"type",
"label",
"children",
"attributes"
],
"additionalProperties": false
}`;
async function generateSchema(description) {
const completion = await client.chat.completions.create({
model: "gpt-5.6-terra",
response_format: { type: "json_schema", json_schema: metaSchema },
messages: [
{ role: "system", content: metaPrompt },
{ role: "user", content: "Description:\n" + description },
],
});
const content = completion.choices[0].message.content;
if (!content) throw new Error("The model did not return a schema.");
return JSON.parse(content);
}
console.log(
JSON.stringify(await generateSchema("Describe a calendar event."), null, 2)
);Esquema de función
Metaesquema de resultado estructurado
JavaScript
import OpenAI from "openai";
const client = new OpenAI();
const metaSchema = {
name: "function-metaschema",
schema: {
type: "object",
properties: {
name: {
type: "string",
description: "The name of the function",
},
description: {
type: "string",
description: "A description of what the function does",
},
parameters: {
$ref: "#/$defs/schema_definition",
description: "A JSON schema that defines the function's parameters",
},
},
required: ["name", "description", "parameters"],
additionalProperties: false,
$defs: {
schema_definition: {
type: "object",
properties: {
type: {
type: "string",
enum: ["object", "array", "string", "number", "boolean", "null"],
},
properties: {
type: "object",
additionalProperties: {
$ref: "#/$defs/schema_definition",
},
},
items: {
anyOf: [
{
$ref: "#/$defs/schema_definition",
},
{
type: "array",
items: {
$ref: "#/$defs/schema_definition",
},
},
],
},
required: {
type: "array",
items: {
type: "string",
},
},
additionalProperties: {
type: "boolean",
},
},
required: ["type"],
additionalProperties: false,
if: {
properties: {
type: {
const: "object",
},
},
},
then: {
required: ["properties"],
},
},
},
},
};
const metaPrompt = `# Instructions
Return a valid schema for the described function.
Pay special attention to making sure that "required" and "type" are always at the correct level of nesting. For example, "required" should be at the same level as "properties", not inside it.
Make sure that every property, no matter how short, has a type and description correctly nested inside it.
# Examples
Input: Assign values to NN hyperparameters
Output: {
"name": "set_hyperparameters",
"description": "Assign values to NN hyperparameters",
"parameters": {
"type": "object",
"required": [
"learning_rate",
"epochs"
],
"properties": {
"epochs": {
"type": "number",
"description": "Number of complete passes through dataset"
},
"learning_rate": {
"type": "number",
"description": "Speed of model learning"
}
}
}
}
Input: Plans a motion path for the robot
Output: {
"name": "plan_motion",
"description": "Plans a motion path for the robot",
"parameters": {
"type": "object",
"required": [
"start_position",
"end_position"
],
"properties": {
"end_position": {
"type": "object",
"properties": {
"x": {
"type": "number",
"description": "End X coordinate"
},
"y": {
"type": "number",
"description": "End Y coordinate"
}
}
},
"obstacles": {
"type": "array",
"description": "Array of obstacle coordinates",
"items": {
"type": "object",
"properties": {
"x": {
"type": "number",
"description": "Obstacle X coordinate"
},
"y": {
"type": "number",
"description": "Obstacle Y coordinate"
}
}
}
},
"start_position": {
"type": "object",
"properties": {
"x": {
"type": "number",
"description": "Start X coordinate"
},
"y": {
"type": "number",
"description": "Start Y coordinate"
}
}
}
}
}
}
Input: Calculates various technical indicators
Output: {
"name": "technical_indicator",
"description": "Calculates various technical indicators",
"parameters": {
"type": "object",
"required": [
"ticker",
"indicators"
],
"properties": {
"indicators": {
"type": "array",
"description": "List of technical indicators to calculate",
"items": {
"type": "string",
"description": "Technical indicator",
"enum": [
"RSI",
"MACD",
"Bollinger_Bands",
"Stochastic_Oscillator"
]
}
},
"period": {
"type": "number",
"description": "Time period for the analysis"
},
"ticker": {
"type": "string",
"description": "Stock ticker symbol"
}
}
}
}`;
async function generateFunctionSchema(description) {
const completion = await client.chat.completions.create({
model: "gpt-5.6-terra",
response_format: { type: "json_schema", json_schema: metaSchema },
messages: [
{ role: "system", content: metaPrompt },
{ role: "user", content: "Description:\n" + description },
],
});
const content = completion.choices[0].message.content;
if (!content) throw new Error("The model did not return a schema.");
return JSON.parse(content);
}
console.log(
JSON.stringify(
await generateFunctionSchema(
"Create a function that checks the weather in a city."
),
null,
2
)
);