O botão Gerar no Playground permite gerar prompts, funções e esquemas apenas com uma descrição da sua tarefa. Este guia explica em detalhes como isso funciona.
Visão geral
Criar prompts e esquemas do zero pode levar tempo, então gerá-los pode ajudar você a começar rapidamente. O botão Gerar usa duas abordagens principais:
- Prompts: usamos metaprompts que incorporam práticas recomendadas para gerar ou melhorar prompts.
- Esquemas: usamos metaesquemas que produzem JSON e sintaxe de funções válidos.
Embora atualmente usemos metaprompts e metaesquemas, podemos integrar técnicas mais avançadas no futuro, como DSPy e “descida do gradiente”.
Prompts
Um metaprompt instrui o modelo a criar um bom prompt com base na descrição da sua tarefa ou a melhorar um prompt existente. Os metaprompts do Playground se baseiam nas nossas práticas recomendadas de engenharia de prompt e na nossa experiência prática com usuários.
Usamos metaprompts específicos para diferentes tipos de saída, como áudio, para garantir que os prompts gerados sigam o formato esperado.
Metaprompts
Saída 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.")
);Saída de áudio
Metaprompt de áudio
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.")
);Edição de prompts
Para editar prompts, usamos um metaprompt ligeiramente modificado. Embora seja simples aplicar edições diretas, pode ser difícil identificar as mudanças necessárias em revisões mais abertas. Para lidar com isso, incluímos uma seção de raciocínio no início da resposta. Essa seção ajuda a orientar o modelo na identificação das mudanças necessárias, avaliando a clareza do prompt existente, a ordem da cadeia de pensamento, a estrutura geral e a especificidade, entre outros fatores. A seção de raciocínio sugere melhorias e depois é removida da resposta final durante o processamento.
Saída de texto
Metaprompt de texto para edições
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.")
);Saída de áudio
Metaprompt de áudio para edições
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
Os esquemas de Saídas estruturadas e os esquemas de funções são, por si só, objetos JSON, então usamos Saídas estruturadas para gerá-los. Isso exige definir um esquema para a saída desejada, que, neste caso, também é um esquema. Para isso, usamos um esquema que descreve a si mesmo: um metaesquema.
Como o campo parameters em um esquema de função também é um esquema, usamos o mesmo metaesquema para gerar funções.
Definição de um metaesquema com restrições
O recurso Saídas estruturadas oferece dois modos: strict=true e strict=false. Ambos usam o mesmo modelo treinado para seguir o esquema fornecido, mas apenas o “modo estrito” garante conformidade perfeita por meio de amostragem com restrições.
Nosso objetivo é gerar esquemas para o modo estrito usando o próprio modo estrito. No entanto, os metaesquemas oficiais fornecidos pela especificação JSON Schema dependem de recursos ainda não compatíveis com o modo estrito. Isso traz desafios que afetam tanto os esquemas de entrada quanto os de saída.
- Esquema de entrada: não podemos usar recursos não compatíveis no esquema de entrada para descrever o esquema de saída.
- Esquema de saída: o esquema gerado não deve incluir recursos não compatíveis.
Como precisamos gerar novas chaves no esquema de saída, o metaesquema de entrada deve usar additionalProperties. Isso significa que, atualmente, não podemos usar o modo estrito para gerar esquemas. Ainda assim, queremos que o esquema gerado siga as restrições do modo estrito.
Para contornar essa limitação, definimos um pseudometaesquema : um metaesquema que usa recursos não compatíveis com o modo estrito para descrever apenas os recursos compatíveis com esse modo. Essencialmente, essa abordagem deixa de usar o modo estrito na definição do metaesquema, mas ainda garante que os esquemas gerados sigam as restrições desse modo.
Deep dive
Como projetamos o pseudometaesquema
Construir um metaesquema com restrições é uma tarefa desafiadora, então recorremos aos nossos modelos para ajudar.
Começamos fornecendo a o1-preview e gpt-4o, em modo JSON, uma descrição do nosso objetivo com base na documentação de Saídas estruturadas.
Após algumas iterações, desenvolvemos nosso primeiro metaesquema funcional.
Em seguida, usamos gpt-4o com Saídas estruturadas e fornecemos esse esquema inicial , junto com a descrição da tarefa e a documentação, para gerar versões melhores. A cada iteração, usamos um esquema melhor para gerar o próximo, até finalmente revisá-lo com cuidado, manualmente.
Por fim, após limpar a saída, validamos os esquemas com um conjunto de avaliações para esquemas e funções.
Limpeza da saída
O modo estrito garante conformidade perfeita com o esquema. No entanto, como não podemos usá-lo durante a geração, precisamos validar e transformar a saída após gerá-la.
Após gerar um esquema, seguimos estas etapas:
- Definir
additionalPropertiescomofalsepara todos os objetos. - Marcar todas as propriedades como obrigatórias.
- Para esquemas de saída estruturada, encapsulá-los em um objeto
json_schema. - Para funções, encapsulá-las em um objeto
function.
O objeto function da Realtime API difere ligeiramente do objeto da API chat completions, mas usa o mesmo esquema.
Metaesquemas
Cada metaesquema tem um prompt correspondente que inclui exemplos few-shot. Ao combinar esses prompts com a confiabilidade de Saídas estruturadas, conseguimos gerar esquemas mesmo sem o modo estrito.
Esquema de saída estruturada
Metaesquema de saída estruturada
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 função
Metaesquema de saída estruturada
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
)
);