Aprenda a usar o modo JSON

import os
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")
)

response = client.chat.completions.create(
  model="YOUR-MODEL_DEPLOYMENT_NAME", # Model = should match the deployment name you chose for your model deployment
  response_format={ "type": "json_object" },
  messages=[
    {"role": "system", "content": "You are a helpful assistant designed to output JSON."},
    {"role": "user", "content": "Who won the world series in 2020?"}
  ]
)
print(response.choices[0].message.content)

Produção

{
  "winner": "Los Angeles Dodgers",
  "event": "World Series",
  "year": 2020
}

Adicione os seguintes pacotes ao seu projeto:

dotnet add package OpenAI
dotnet add package Azure.Identity

using Azure.Identity;
using OpenAI;
using OpenAI.Chat;
using System.ClientModel;
using System.Text.Json;

ChatClient client = new(
    model: "YOUR-MODEL_DEPLOYMENT_NAME",
    credential: new ApiKeyCredential(
        Environment.GetEnvironmentVariable("AZURE_OPENAI_API_KEY")),
    options: new OpenAIClientOptions()
    {
        Endpoint = new Uri(
            "https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/")
    }
);

ChatCompletionOptions options = new()
{
    ResponseFormat = ChatResponseFormat.CreateJsonObjectFormat()
};

ChatCompletion completion = client.CompleteChat(
    [
        new SystemChatMessage(
            "You are a helpful assistant designed to output JSON."),
        new UserChatMessage("Who won the world series in 2020?")
    ],
    options);

Console.WriteLine(completion.Content[0].Text);

Produção

{
  "winner": "Los Angeles Dodgers",
  "event": "World Series",
  "year": 2020
}

Neste exemplo, o utilizador pede informação histórica num esquema JSON específico porque planeia usar a saída para scripting adicional.

$openai = @{
   api_key     = $Env:AZURE_OPENAI_API_KEY
   api_base    = 'https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/'
   name        = 'YOUR-DEPLOYMENT-NAME-HERE' # name you chose for your deployment
}

$headers = @{
  'api-key' = $openai.api_key
}

$messages  = @()
$messages += @{
  role     = 'system'
  content  = 'You are a helpful assistant designed to output JSON.'
}
$messages += @{
  role     = 'user'
  content  = 'Who threw the final pitch during the world series each year from 1979 to 1989?'
}
$messages += @{
  role     = 'user'
  content  = 'Respond using schema. response:{year, team, player, player_height}.'
}

$body      = @{
  response_format = @{type = 'json_object'}
  messages = $messages
} | ConvertTo-Json

$url = "$($openai.api_base)/chat/completions"

$response = Invoke-RestMethod -Uri $url -Headers $headers -Body $body -Method Post -ContentType 'application/json'
$response.choices[0].message.content

Produção

A capacidade de saída JSON facilita ao PowerShell converter a resposta para um objeto .NET. Passa os dados por um | pipeline para executar mais passos de script, como a ordenação.

if ($response.choices[0].finish_reason -eq 'stop') {
  $response.choices[0].message.content | ConvertFrom-Json | ForEach-Object response | Sort player_height -Descending
} else { write-warning 'the JSON response was incomplete'}

year team                  player           player_height
---- ----                  ------           -------------
1979 Pittsburgh Pirates    Kent Tekulve     6' 4"
1984 Detroit Tigers        Willie Hernandez 6' 3"
1988 Los Angeles Dodgers   Orel Hershiser   6' 3"
1982 St. Louis Cardinals   Bruce Sutter     6' 2"
1985 Kansas City Royals    Dan Quisenberry  6' 2"
1986 New York Mets         Jesse Orosco     6' 2"
1989 Oakland Athletics     Dennis Eckersley 6' 2"
1981 Los Angeles Dodgers   Steve Howe       6' 1"
1980 Philadelphia Phillies Tug McGraw       6' 0"
1987 Minnesota Twins       Jeff Reardon     6' 0"
1983 Baltimore Orioles     Tippy Martinez   5' 10"