Gestructureerde uitvoer

2025-10-11

Gestructureerde uitvoer maakt een model volgens een JSON-schemadefinitie die u opgeeft als onderdeel van uw deductie-API-aanroep. Dit is in tegenstelling tot de oudere JSON-modusfunctie , die gegarandeerde geldige JSON zou genereren, maar niet in staat was om strikte naleving van het opgegeven schema te garanderen. Gestructureerde uitvoer wordt aanbevolen voor het aanroepen van functies, het extraheren van gestructureerde gegevens en het bouwen van complexe werkstromen met meerdere stappen.

Opmerking

Gestructureerde uitvoer wordt momenteel niet ondersteund met:

Neem je eigen data mee scenario's.
Assistenten of Azure AI Agents-service.
gpt-4o-audio-preview en gpt-4o-mini-audio-preview versie: 2024-12-17.

Ondersteunde modellen

gpt-5-pro Versie 2025-10-06
gpt-5-codex Versie 2025-09-11
gpt-5 Versie 2025-08-07
gpt-5-mini Versie 2025-08-07
gpt-5-nano Versie 2025-08-07
codex-mini Versie 2025-05-16
o3-pro Versie 2025-06-10
o3-mini Versie 2025-01-31
o1 Versie: 2024-12-17
gpt-4o-mini Versie: 2024-07-18
gpt-4o Versie: 2024-08-06
gpt-4o Versie: 2024-11-20
gpt-4.1 Versie 2025-04-14
gpt-4.1-nano Versie 2025-04-14
gpt-4.1-mini Versie: 2025-04-14
o4-mini Versie: 2025-04-16
o3 Versie: 2025-04-16

API-ondersteuning

Ondersteuning voor gestructureerde uitvoer is voor het eerst toegevoegd in api-versie 2024-08-01-preview. Deze is beschikbaar in de nieuwste preview-API's en de nieuwste GA-API: v1.

Aan de slag

Python (Microsoft Entra-id)
Python (verificatie op basis van sleutels)

U kunt objectschema's Pydantic definiëren in Python. Afhankelijk van de versie van de OpenAI en Pydantic bibliotheken die u gebruikt, moet u mogelijk een upgrade uitvoeren naar een nieuwere versie. Deze voorbeelden zijn getest tegen openai 1.42.0 en pydantic 2.8.2.

pip install openai pydantic --upgrade

Als u nieuw bent in het gebruik van Microsoft Entra ID voor authenticatie, zie Hoe u Azure OpenAI configureert in Azure AI Foundry Models met Microsoft Entra ID-authenticatie.

import os
from pydantic import BaseModel
from openai import OpenAI
from azure.identity import DefaultAzureCredential, get_bearer_token_provider

token_provider = get_bearer_token_provider(
    DefaultAzureCredential(), "https://cognitiveservices.azure.com/.default"
)

client = OpenAI(  
  base_url = "https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/",  
  api_key=token_provider,
)

class CalendarEvent(BaseModel):
    name: str
    date: str
    participants: list[str]

completion = client.beta.chat.completions.parse(
    model="MODEL_DEPLOYMENT_NAME", # replace with the model deployment name of your gpt-4o 2024-08-06 deployment
    messages=[
        {"role": "system", "content": "Extract the event information."},
        {"role": "user", "content": "Alice and Bob are going to a science fair on Friday."},
    ],
    response_format=CalendarEvent,
)

event = completion.choices[0].message.parsed

print(event)
print(completion.model_dump_json(indent=2))

Uitvoer

name='Science Fair' date='Friday' participants=['Alice', 'Bob']
{
  "id": "chatcmpl-A1EUP2fAmL4SeB1lVMinwM7I2vcqG",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "logprobs": null,
      "message": {
        "content": "{\n  \"name\": \"Science Fair\",\n  \"date\": \"Friday\",\n  \"participants\": [\"Alice\", \"Bob\"]\n}",
        "refusal": null,
        "role": "assistant",
        "function_call": null,
        "tool_calls": [],
        "parsed": {
          "name": "Science Fair",
          "date": "Friday",
          "participants": [
            "Alice",
            "Bob"
          ]
        }
      }
    }
  ],
  "created": 1724857389,
  "model": "gpt-4o-2024-08-06",
  "object": "chat.completion",
  "service_tier": null,
  "system_fingerprint": "fp_1c2eaec9fe",
  "usage": {
    "completion_tokens": 27,
    "prompt_tokens": 32,
    "total_tokens": 59
  }
}

pip install openai pydantic --upgrade

import os
from pydantic import BaseModel
from openai import OpenAI

client = OpenAI(
  base_url = "https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/",  
  api_key=os.getenv("AZURE_OPENAI_API_KEY")  
)

class CalendarEvent(BaseModel):
    name: str
    date: str
    participants: list[str]

completion = client.beta.chat.completions.parse(
    model="MODEL_DEPLOYMENT_NAME", # replace with the model deployment name of your gpt-4o 2024-08-06 deployment
    messages=[
        {"role": "system", "content": "Extract the event information."},
        {"role": "user", "content": "Alice and Bob are going to a science fair on Friday."},
    ],
    response_format=CalendarEvent,
)

event = completion.choices[0].message.parsed

print(event)
print(completion.model_dump_json(indent=2))

Uitvoer

name='Science Fair' date='Friday' participants=['Alice', 'Bob']
{
  "id": "chatcmpl-A1EUP2fAmL4SeB1lVMinwM7I2vcqG",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "logprobs": null,
      "message": {
        "content": "{\n  \"name\": \"Science Fair\",\n  \"date\": \"Friday\",\n  \"participants\": [\"Alice\", \"Bob\"]\n}",
        "refusal": null,
        "role": "assistant",
        "function_call": null,
        "tool_calls": [],
        "parsed": {
          "name": "Science Fair",
          "date": "Friday",
          "participants": [
            "Alice",
            "Bob"
          ]
        }
      }
    }
  ],
  "created": 1724857389,
  "model": "gpt-4o-2024-08-06",
  "object": "chat.completion",
  "service_tier": null,
  "system_fingerprint": "fp_1c2eaec9fe",
  "usage": {
    "completion_tokens": 27,
    "prompt_tokens": 32,
    "total_tokens": 59
  }
}

Functie aanroepen met gestructureerde uitvoer

Gestructureerde uitvoer voor functieaanroepen kan worden ingeschakeld met één parameter door het opgeven strict: truevan .

Opmerking

Gestructureerde uitvoer wordt niet ondersteund met parallelle functie-aanroepen. Wanneer u gestructureerde uitvoer gebruikt, stel parallel_tool_calls in op false.

Python (Microsoft Entra-id)
Python (verificatie op basis van sleutels)

from enum import Enum
from typing import Union
from pydantic import BaseModel
from openai import OpenAI
from azure.identity import DefaultAzureCredential, get_bearer_token_provider

token_provider = get_bearer_token_provider(
    DefaultAzureCredential(), "https://cognitiveservices.azure.com/.default"
)

client = OpenAI(  
  base_url = "https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/",  
  api_key=token_provider,
)

class GetDeliveryDate(BaseModel):
    order_id: str

tools = [openai.pydantic_function_tool(GetDeliveryDate)]

messages = []
messages.append({"role": "system", "content": "You are a helpful customer support assistant. Use the supplied tools to assist the user."})
messages.append({"role": "user", "content": "Hi, can you tell me the delivery date for my order #12345?"}) 

response = client.chat.completions.create(
    model="MODEL_DEPLOYMENT_NAME", # replace with the model deployment name of your gpt-4o 2024-08-06 deployment
    messages=messages,
    tools=tools
)

print(response.choices[0].message.tool_calls[0].function)
print(response.model_dump_json(indent=2))

from enum import Enum
from typing import Union
from pydantic import BaseModel
import openai
from openai import OpenAI

client = OpenAI(
  base_url = "https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/",  
  api_key=os.getenv("AZURE_OPENAI_API_KEY")  
)


class GetDeliveryDate(BaseModel):
    order_id: str

tools = [openai.pydantic_function_tool(GetDeliveryDate)]

messages = []
messages.append({"role": "system", "content": "You are a helpful customer support assistant. Use the supplied tools to assist the user."})
messages.append({"role": "user", "content": "Hi, can you tell me the delivery date for my order #12345?"}) 

response = client.chat.completions.create(
    model="MODEL_DEPLOYMENT_NAME", # replace with the model deployment name of your gpt-4o 2024-08-06 deployment
    messages=messages,
    tools=tools
)

print(response.choices[0].message.tool_calls[0].function)
print(response.model_dump_json(indent=2))

Aan de slag

Voeg de volgende pakketten toe aan uw project om te werken met Azure OpenAI:

Azure.AI.OpenAI: biedt een Azure OpenAI-client met specifieke Azure-functionaliteit die voortbouwt op de standaardafhankelijkheid van de OpenAI-bibliotheek .
Azure.Identity: biedt verificatieondersteuning voor Microsoft Entra ID-token in de Azure SDK-bibliotheken.
Newtonsoft.Json.Schema: biedt nuttige hulpprogramma's voor het werken met JSON-schema's.

dotnet add package Azure.AI.OpenAI --prerelease
dotnet add package Azure.Identity
dotnet add package Newtonsoft.Json.Schema

Microsoft Entra-id
Verificatie op basis van sleutels

Als u nieuw bent in het gebruik van Microsoft Entra ID voor authenticatie, zie Hoe u Azure OpenAI configureert in Azure AI Foundry Models met Microsoft Entra ID-authenticatie.

using Azure.AI.OpenAI;
using Azure.Identity;
using Newtonsoft.Json.Schema.Generation;
using OpenAI.Chat;
using System.ClientModel;

// Create the clients
string endpoint = GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT");

AzureOpenAIClient openAIClient = new(
    new Uri(endpoint),
    new DefaultAzureCredential());

var client = openAIClient.GetChatClient("gpt-4o");

// Create a chat with initial prompts
var chat = new List<ChatMessage>()
    {
         new SystemChatMessage("Extract the event information and projected weather."),
         new UserChatMessage("Alice and Bob are going to a science fair in Seattle on June 1st, 2025.")
    };

// Get the schema of the class for the structured response
JSchemaGenerator generator = new JSchemaGenerator();
var jsonSchema = generator.Generate(typeof(CalendarEvent)).ToString();

// Get a completion with structured output
var chatUpdates = client.CompleteChatStreamingAsync(
        chat,
        new ChatCompletionOptions()
        {
            ResponseFormat = ChatResponseFormat.CreateJsonSchemaFormat(
                        "calenderEvent",
                        BinaryData.FromString(jsonSchema))
        });

// Write the structured response
await foreach (var chatUpdate in chatUpdates)
{
    foreach (var contentPart in chatUpdate.ContentUpdate)
    {
        Console.Write(contentPart.Text);
    }
}

// The class for the structured response
public class CalendarEvent()
{
    public string Name { get; set; }
    public string Date { get; set; }
    public List<string> Participants { get; set; }
}

using Azure.AI.OpenAI;
using Newtonsoft.Json.Schema.Generation;
using OpenAI.Chat;
using System.ClientModel;

// Create the clients
string endpoint = GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT");
string key = GetEnvironmentVariable("AZURE_OPENAI_API_KEY");

AzureOpenAIClient openAIClient = new(
    new Uri(endpoint),
    new ApiKeyCredential(key));

var client = openAIClient.GetChatClient("gpt-4o");

// Create a chat with initial prompts
var chat = new List<ChatMessage>()
    {
         new SystemChatMessage("Extract the event information and projected weather."),
         new UserChatMessage("Alice and Bob are going to a science fair in Seattle on June 1st, 2025.")
    };

// Get the schema of the class for the structured response
JSchemaGenerator generator = new JSchemaGenerator();
var jsonSchema = generator.Generate(typeof(CalendarEvent)).ToString();

// Get a completion with structured output
var chatUpdates = client.CompleteChatStreamingAsync(
        chat,
        new ChatCompletionOptions()
        {
            ResponseFormat = ChatResponseFormat.CreateJsonSchemaFormat(
                        "calenderEvent",
                        BinaryData.FromString(jsonSchema))
        });

// Write the structured response
await foreach (var chatUpdate in chatUpdates)
{
    foreach (var contentPart in chatUpdate.ContentUpdate)
    {
        Console.Write(contentPart.Text);
    }
}

// The class for the structured response
public class CalendarEvent()
{
    public string Name { get; set; }
    public string Date { get; set; }
    public List<string> Participants { get; set; }
}

Functie aanroepen met gestructureerde uitvoer

Gestructureerde uitvoer voor functieaanroepen kan worden ingeschakeld met één parameter door het opgeven strict: truevan .

Microsoft Entra-id
Verificatie op basis van sleutels

using Azure.AI.OpenAI;
using Newtonsoft.Json.Schema.Generation;
using OpenAI.Chat;
using System.ClientModel;

// Create the clients
string endpoint = GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT");

AzureOpenAIClient openAIClient = new(
    new Uri(endpoint),
    new DefaultAzureCredential());

var chatClient = openAIClient.GetChatClient("gpt-4o");

// Local function to be used by the assistant tooling
string GetTemperature(string location, string date)
{
    // Placeholder for Weather API
    if(location == "Seattle" && date == "2025-06-01")
    {
        return "75";
    }

    return "50";
}

// Create a tool to get the temperature
ChatTool GetTemperatureTool = ChatTool.CreateFunctionTool(
    functionName: nameof(GetTemperature),
    functionSchemaIsStrict: true,
    functionDescription: "Get the projected temperature by date and location.",
    functionParameters: BinaryData.FromBytes("""
        {
            "type": "object",
            "properties": {
                "location": {
                    "type": "string",
                    "description": "The location of the weather."
                },
                "date": {
                    "type": "string",
                    "description": "The date of the projected weather."
                }
            },
            "required": ["location", "date"],
            "additionalProperties": false  
        }
        """u8.ToArray())
);

// Create a chat with prompts
var chat = new List<ChatMessage>()
    {
         new SystemChatMessage("Extract the event information and projected weather."),
         new UserChatMessage("Alice and Bob are going to a science fair in Seattle on June 1st, 2025.")
    };

// Create a JSON schema for the CalendarEvent structured response
JSchemaGenerator generator = new JSchemaGenerator();
var jsonSchema = generator.Generate(typeof(CalendarEvent)).ToString();

// Get a chat completion from the AI model
var completion = chatClient.CompleteChat(
        chat,
        new ChatCompletionOptions()
        {
            ResponseFormat = ChatResponseFormat.CreateJsonSchemaFormat(
                "calenderEvent",
                BinaryData.FromString(jsonSchema)),
            Tools = { GetTemperatureTool }
        });

Console.WriteLine(completion.Value.ToolCalls[0].FunctionName);

// Structured response class
public class CalendarEvent()
{
    public string Name { get; set; }
    public string Date { get; set; }
    public string Temperature { get; set; }
    public List<string> Participants { get; set; }
}

using Azure.AI.OpenAI;
using Newtonsoft.Json.Schema.Generation;
using OpenAI.Chat;
using System.ClientModel;

// Create the clients
string endpoint = GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT");
string key = GetEnvironmentVariable("AZURE_OPENAI_API_KEY");

AzureOpenAIClient openAIClient = new(
    new Uri(endpoint),
    new ApiKeyCredential(key));

var chatClient = openAIClient.GetChatClient("gpt-4o");

// Local function to be used by the assistant tooling
string GetTemperature(string location, string date)
{
    // Placeholder for Weather API
    if(location == "Seattle" && date == "2025-06-01")
    {
        return "75";
    }

    return "50";
}

// Create a tool to get the temperature
ChatTool GetTemperatureTool = ChatTool.CreateFunctionTool(
    functionName: nameof(GetTemperature),
    functionSchemaIsStrict: true,
    functionDescription: "Get the projected temperature by date and location.",
    functionParameters: BinaryData.FromBytes("""
        {
            "type": "object",
            "properties": {
                "location": {
                    "type": "string",
                    "description": "The location of the weather."
                },
                "date": {
                    "type": "string",
                    "description": "The date of the projected weather."
                }
            },
            "required": ["location", "date"],
            "additionalProperties": false  
        }
        """u8.ToArray())
);

// Create a chat with prompts
var chat = new List<ChatMessage>()
    {
         new SystemChatMessage("Extract the event information and projected weather."),
         new UserChatMessage("Alice and Bob are going to a science fair in Seattle on June 1st, 2025.")
    };

// Create a JSON schema for the CalendarEvent structured response
JSchemaGenerator generator = new JSchemaGenerator();
var jsonSchema = generator.Generate(typeof(CalendarEvent)).ToString();

// Get a chat completion from the AI model
var completion = chatClient.CompleteChat(
        chat,
        new ChatCompletionOptions()
        {
            ResponseFormat = ChatResponseFormat.CreateJsonSchemaFormat(
                "calenderEvent",
                BinaryData.FromString(jsonSchema)),
            Tools = { GetTemperatureTool }
        });

Console.WriteLine(completion.Value.ToolCalls[0].FunctionName);

// Structured response class
public class CalendarEvent()
{
    public string Name { get; set; }
    public string Date { get; set; }
    public string Temperature { get; set; }
    public List<string> Participants { get; set; }
}

Aan de slag

response_format is ingesteld op json_schema met strict: true ingesteld.

curl -X POST  https://YOUR_RESOURCE_NAME.openai.azure.com/openai/v1/chat/completions \
  -H "api-key: $AZURE_OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
    -d '{
        "model": "YOUR_MODEL_DEPLOYMENT_NAME",
        "messages": [
                {"role": "system", "content": "Extract the event information."},
                {"role": "user", "content": "Alice and Bob are going to a science fair on Friday."}
            ],
            "response_format": {
                "type": "json_schema",
                "json_schema": {
                    "name": "CalendarEventResponse",
                    "strict": true,
                    "schema": {
                        "type": "object",
                        "properties": {
                            "name": {
                              "type": "string"
                            },
                            "date": {
                                "type": "string"
                            },
                            "participants": {
                                "type": "array",
                                "items": {
                                    "type": "string"
                                }
                            }
                        },
                        "required": [
                            "name",
                            "date",
                            "participants"
                        ],
                        "additionalProperties": false
                    }
                }
          }
  }'

Uitvoer:

{
  "id": "chatcmpl-A1HKsHAe2hH9MEooYslRn9UmEwsag",
  "object": "chat.completion",
  "created": 1724868330,
  "model": "gpt-4o-2024-08-06",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "{\n  \"name\": \"Science Fair\",\n  \"date\": \"Friday\",\n  \"participants\": [\"Alice\", \"Bob\"]\n}"
      },
      "logprobs": null,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 33,
    "completion_tokens": 27,
    "total_tokens": 60
  },
  "system_fingerprint": "fp_1c2eaec9fe"
}

Functie aanroepen met gestructureerde uitvoer

curl -X POST  https://YOUR_RESOURCE_NAME.openai.azure.com/openai/v1/chat/completions \
  -H "api-key: $AZURE_OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "YOUR_MODEL_DEPLOYMENT_NAME",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant. The current date is August 6, 2024. You help users query for the data they are looking for by calling the query function."
    },
    {
      "role": "user",
      "content": "look up all my orders in may of last year that were fulfilled but not delivered on time"
    }
  ],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "query",
        "description": "Execute a query.",
        "strict": true,
        "parameters": {
          "type": "object",
          "properties": {
            "table_name": {
              "type": "string",
              "enum": ["orders"]
            },
            "columns": {
              "type": "array",
              "items": {
                "type": "string",
                "enum": [
                  "id",
                  "status",
                  "expected_delivery_date",
                  "delivered_at",
                  "shipped_at",
                  "ordered_at",
                  "canceled_at"
                ]
              }
            },
            "conditions": {
              "type": "array",
              "items": {
                "type": "object",
                "properties": {
                  "column": {
                    "type": "string"
                  },
                  "operator": {
                    "type": "string",
                    "enum": ["=", ">", "<", ">=", "<=", "!="]
                  },
                  "value": {
                    "anyOf": [
                      {
                        "type": "string"
                      },
                      {
                        "type": "number"
                      },
                      {
                        "type": "object",
                        "properties": {
                          "column_name": {
                            "type": "string"
                          }
                        },
                        "required": ["column_name"],
                        "additionalProperties": false
                      }
                    ]
                  }
                },
                "required": ["column", "operator", "value"],
                "additionalProperties": false
              }
            },
            "order_by": {
              "type": "string",
              "enum": ["asc", "desc"]
            }
          },
          "required": ["table_name", "columns", "conditions", "order_by"],
          "additionalProperties": false
        }
      }
    }
  ]
}'

Ondersteunde schema's en beperkingen

Gestructureerde Uitvoer van Azure OpenAI ondersteunt dezelfde subset van het JSON-schema als OpenAI.

Ondersteunde typen

Snaar / Touwtje
Aantal
Booleaan
Geheel getal
Voorwerp
Array
Enum
één van

Opmerking

Hoofdobjecten kunnen niet het anyOf type zijn.

Alle velden moeten vereist zijn

Alle velden of functieparameters moeten worden opgenomen zoals vereist. In het onderstaande voorbeeld location, en unit worden beide opgegeven onder "required": ["location", "unit"].

{
    "name": "get_weather",
    "description": "Fetches the weather in the given location",
    "strict": true,
    "parameters": {
        "type": "object",
        "properties": {
            "location": {
                "type": "string",
                "description": "The location to get the weather for"
            },
            "unit": {
                "type": "string",
                "description": "The unit to return the temperature in",
                "enum": ["F", "C"]
            }
        },
        "additionalProperties": false,
        "required": ["location", "unit"]
    }

Indien nodig is het mogelijk om een optionele parameter te emuleren met behulp van een samenvoegtype met null. In dit voorbeeld wordt dit bereikt met de regel "type": ["string", "null"],.

{
    "name": "get_weather",
    "description": "Fetches the weather in the given location",
    "strict": true,
    "parameters": {
        "type": "object",
        "properties": {
            "location": {
                "type": "string",
                "description": "The location to get the weather for"
            },
            "unit": {
                "type": ["string", "null"],
                "description": "The unit to return the temperature in",
                "enum": ["F", "C"]
            }
        },
        "additionalProperties": false,
        "required": [
            "location", "unit"
        ]
    }
}

Nestdiepte

Een schema kan maximaal 100 objecteigenschappen bevatten, met maximaal vijf niveaus van nesteling.

additionalProperties: false moet in objecten altijd worden ingesteld.

Deze eigenschap bepaalt of een object extra sleutel-waardeparen kan hebben die niet zijn gedefinieerd in het JSON-schema. Als u gestructureerde uitvoer wilt gebruiken, moet u deze waarde instellen op false.

Sleutelvolgorde

Gestructureerde uitvoer wordt op dezelfde volgorde gerangschikt als het opgegeven schema. Als u de uitvoervolgorde wilt wijzigen, wijzigt u de volgorde van het schema dat u verzendt als onderdeel van uw deductieaanvraag.

Niet-ondersteunde typespecifieke trefwoorden

Typologie	Niet-ondersteund trefwoord
Snaar / Touwtje	minimale lengte maximale lengte patroon formaat
Aantal	minimum maximum multipleOf
Objecten	patroonEigenschappen niet-geëvalueerde eigenschappen propertyNames minimaleEigenschappen maxEigenschappen
Reeksen	niet-geëvalueerde items Bevat min bevat maximum hoeveelheden minimaal aantal items maximaal aantal items unieke items

Geneste schema's die anyOf gebruiken, moeten voldoen aan de algemene subset van het JSON-schema

Voorbeeld van een ondersteund anyOf schema:

{
    "type": "object",
    "properties": {
        "item": {
            "anyOf": [
                {
                    "type": "object",
                    "description": "The user object to insert into the database",
                    "properties": {
                        "name": {
                            "type": "string",
                            "description": "The name of the user"
                        },
                        "age": {
                            "type": "number",
                            "description": "The age of the user"
                        }
                    },
                    "additionalProperties": false,
                    "required": [
                        "name",
                        "age"
                    ]
                },
                {
                    "type": "object",
                    "description": "The address object to insert into the database",
                    "properties": {
                        "number": {
                            "type": "string",
                            "description": "The number of the address. Eg. for 123 main st, this would be 123"
                        },
                        "street": {
                            "type": "string",
                            "description": "The street name. Eg. for 123 main st, this would be main st"
                        },
                        "city": {
                            "type": "string",
                            "description": "The city of the address"
                        }
                    },
                    "additionalProperties": false,
                    "required": [
                        "number",
                        "street",
                        "city"
                    ]
                }
            ]
        }
    },
    "additionalProperties": false,
    "required": [
        "item"
    ]
}

Definities worden ondersteund

Ondersteund voorbeeld:

{
    "type": "object",
    "properties": {
        "steps": {
            "type": "array",
            "items": {
                "$ref": "#/$defs/step"
            }
        },
        "final_answer": {
            "type": "string"
        }
    },
    "$defs": {
        "step": {
            "type": "object",
            "properties": {
                "explanation": {
                    "type": "string"
                },
                "output": {
                    "type": "string"
                }
            },
            "required": [
                "explanation",
                "output"
            ],
            "additionalProperties": false
        }
    },
    "required": [
        "steps",
        "final_answer"
    ],
    "additionalProperties": false
}

Recursieve schema's worden ondersteund

Voorbeeld van het gebruik van # voor hoofdrecursie:

{
        "name": "ui",
        "description": "Dynamically generated UI",
        "strict": true,
        "schema": {
            "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"
                            }
                        },
                      "additionalProperties": false,
                      "required": ["name", "value"]
                    }
                }
            },
            "required": ["type", "label", "children", "attributes"],
            "additionalProperties": false
        }
    }

Voorbeeld van expliciete recursie:

{
    "type": "object",
    "properties": {
        "linked_list": {
            "$ref": "#/$defs/linked_list_node"
        }
    },
    "$defs": {
        "linked_list_node": {
            "type": "object",
            "properties": {
                "value": {
                    "type": "number"
                },
                "next": {
                    "anyOf": [
                        {
                            "$ref": "#/$defs/linked_list_node"
                        },
                        {
                            "type": "null"
                        }
                    ]
                }
            },
            "additionalProperties": false,
            "required": [
                "next",
                "value"
            ]
        }
    },
    "additionalProperties": false,
    "required": [
        "linked_list"
    ]
}

Feedback

Is deze pagina nuttig?

Delen via

Gestructureerde uitvoer

Ondersteunde modellen

API-ondersteuning

Aan de slag

Uitvoer

Functie aanroepen met gestructureerde uitvoer

Aan de slag

Functie aanroepen met gestructureerde uitvoer

Aan de slag

Functie aanroepen met gestructureerde uitvoer

Ondersteunde schema's en beperkingen

Ondersteunde typen

Alle velden moeten vereist zijn

Nestdiepte

additionalProperties: false moet in objecten altijd worden ingesteld.

Sleutelvolgorde

Niet-ondersteunde typespecifieke trefwoorden

Geneste schema's die anyOf gebruiken, moeten voldoen aan de algemene subset van het JSON-schema

Definities worden ondersteund

Recursieve schema's worden ondersteund

Feedback

Aanvullende resources