> ## Documentation Index
> Fetch the complete documentation index at: https://docs.apimart.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Универсальный Chat API (без стриминга по умолчанию)

>  - Единый интерфейс chat API с поддержкой всех моделей генерации текста
- Выбор разных AI-моделей через параметр model
- Совместимость с форматом OpenAI Chat Completions API
- Нестриминговый вывод, возвращает полный ответ за один раз 

<RequestExample>
  ```bash cURL theme={null}
  curl --request POST \
    --url https://api.apimart.ai/api/v1/chat/completions \
    --header 'Authorization: Bearer <token>' \
    --header 'Content-Type: application/json' \
    --data '{
      "model": "gpt-5", # Can be replaced with any supported model ID
      "stream": false,
      "messages": [
        {
          "role": "system",
          "content": "You are a professional AI assistant."
        },
        {
          "role": "user",
          "content": "Tell me about the history of artificial intelligence."
        }
      ]
    }'
  ```

  ```python Python theme={null}
  import requests

  url = "https://api.apimart.ai/api/v1/chat/completions"

  payload = {
      "model": "gpt-5",  # Can be replaced with any supported model ID
      "stream": False,
      "messages": [
          {
              "role": "system",
              "content": "You are a professional AI assistant."
          },
          {
              "role": "user",
              "content": "Tell me about the history of artificial intelligence."
          }
      ]
  }

  headers = {
      "Authorization": "Bearer <token>",
      "Content-Type": "application/json"
  }

  response = requests.post(url, json=payload, headers=headers)

  print(response.json())
  ```

  ```javascript JavaScript theme={null}
  const url = "https://api.apimart.ai/api/v1/chat/completions";

  const payload = {
    model: "gpt-5",  // Can be replaced with any supported model ID
    stream: false,
    messages: [
      {
        role: "system",
        content: "You are a professional AI assistant."
      },
      {
        role: "user",
        content: "Tell me about the history of artificial intelligence."
      }
    ]
  };

  const headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
  };

  fetch(url, {
    method: "POST",
    headers: headers,
    body: JSON.stringify(payload)
  })
    .then(response => response.json())
    .then(data => console.log(data))
    .catch(error => console.error('Error:', error));
  ```

  ```go Go theme={null}
  package main

  import (
      "bytes"
      "encoding/json"
      "fmt"
      "io/ioutil"
      "net/http"
  )

  func main() {
      url := "https://api.apimart.ai/api/v1/chat/completions"

      payload := map[string]interface{}{
          "model": "gpt-5",  // Can be replaced with any supported model ID
          "stream": false,
          "messages": []map[string]string{
              {
                  "role":    "system",
                  "content": "You are a professional AI assistant.",
              },
              {
                  "role":    "user",
                  "content": "Tell me about the history of artificial intelligence.",
              },
          },
      }

      jsonData, _ := json.Marshal(payload)

      req, _ := http.NewRequest("POST", url, bytes.NewBuffer(jsonData))
      req.Header.Set("Authorization", "Bearer <token>")
      req.Header.Set("Content-Type", "application/json")

      client := &http.Client{}
      resp, err := client.Do(req)
      if err != nil {
          panic(err)
      }
      defer resp.Body.Close()

      body, _ := ioutil.ReadAll(resp.Body)
      fmt.Println(string(body))
  }
  ```

  ```java Java theme={null}
  import java.net.http.HttpClient;
  import java.net.http.HttpRequest;
  import java.net.http.HttpResponse;
  import java.net.URI;

  public class Main {
      public static void main(String[] args) throws Exception {
          String url = "https://api.apimart.ai/api/v1/chat/completions";

          // Can be replaced with any supported model ID
          String payload = """
          {
            "model": "gpt-5",
            "stream": false,
            "messages": [
              {
                "role": "system",
                "content": "You are a professional AI assistant."
              },
              {
                "role": "user",
                "content": "Tell me about the history of artificial intelligence."
              }
            ]
          }
          """;

          HttpClient client = HttpClient.newHttpClient();
          HttpRequest request = HttpRequest.newBuilder()
              .uri(URI.create(url))
              .header("Authorization", "Bearer <token>")
              .header("Content-Type", "application/json")
              .POST(HttpRequest.BodyPublishers.ofString(payload))
              .build();

          HttpResponse<String> response = client.send(request,
              HttpResponse.BodyHandlers.ofString());

          System.out.println(response.body());
      }
  }
  ```

  ```php PHP theme={null}
  <?php

  $url = "https://api.apimart.ai/api/v1/chat/completions";

  // Can be replaced with any supported model ID
  $payload = [
      "model" => "gpt-5",
      "stream" => false,
      "messages" => [
          [
              "role" => "system",
              "content" => "You are a professional AI assistant."
          ],
          [
              "role" => "user",
              "content" => "Tell me about the history of artificial intelligence."
          ]
      ]
  ];

  $ch = curl_init($url);
  curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
  curl_setopt($ch, CURLOPT_POST, true);
  curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($payload));
  curl_setopt($ch, CURLOPT_HTTPHEADER, [
      "Authorization: Bearer <token>",
      "Content-Type: application/json"
  ]);

  $response = curl_exec($ch);
  curl_close($ch);

  echo $response;
  ?>
  ```

  ```ruby Ruby theme={null}
  require 'net/http'
  require 'json'
  require 'uri'

  url = URI("https://api.apimart.ai/api/v1/chat/completions")

  # Can be replaced with any supported model ID
  payload = {
    model: "gpt-5",
    stream: false,
    messages: [
      {
        role: "system",
        content: "You are a professional AI assistant."
      },
      {
        role: "user",
        content: "Tell me about the history of artificial intelligence."
      }
    ]
  }

  http = Net::HTTP.new(url.host, url.port)
  http.use_ssl = true

  request = Net::HTTP::Post.new(url)
  request["Authorization"] = "Bearer <token>"
  request["Content-Type"] = "application/json"
  request.body = payload.to_json

  response = http.request(request)
  puts response.body
  ```

  ```swift Swift theme={null}
  import Foundation

  let url = URL(string: "https://api.apimart.ai/api/v1/chat/completions")!

  let payload: [String: Any] = [
      "model": "gpt-5",  // Can be replaced with any supported model ID
      "stream": false,
      "messages": [
          [
              "role": "system",
              "content": "You are a professional AI assistant."
          ],
          [
              "role": "user",
              "content": "Tell me about the history of artificial intelligence."
          ]
      ]
  ]

  var request = URLRequest(url: url)
  request.httpMethod = "POST"
  request.setValue("Bearer <token>", forHTTPHeaderField: "Authorization")
  request.setValue("application/json", forHTTPHeaderField: "Content-Type")
  request.httpBody = try? JSONSerialization.data(withJSONObject: payload)

  let task = URLSession.shared.dataTask(with: request) { data, response, error in
      if let error = error {
          print("Error: \(error)")
          return
      }

      if let data = data, let responseString = String(data: data, encoding: .utf8) {
          print(responseString)
      }
  }

  task.resume()
  ```

  ```csharp C# theme={null}
  using System;
  using System.Net.Http;
  using System.Text;
  using System.Threading.Tasks;

  class Program
  {
      static async Task Main(string[] args)
      {
          var url = "https://api.apimart.ai/api/v1/chat/completions";

          // Can be replaced with any supported model ID
          var payload = @"{
              ""model"": ""gpt-5"",
              ""stream"": false,
              ""messages"": [
                  {
                      ""role"": ""system"",
                      ""content"": ""You are a professional AI assistant.""
                  },
                  {
                      ""role"": ""user"",
                      ""content"": ""Tell me about the history of artificial intelligence.""
                  }
              ]
          }";

          using var client = new HttpClient();
          client.DefaultRequestHeaders.Add("Authorization", "Bearer <token>");

          var content = new StringContent(payload, Encoding.UTF8, "application/json");
          var response = await client.PostAsync(url, content);
          var result = await response.Content.ReadAsStringAsync();

          Console.WriteLine(result);
      }
  }
  ```

  ```c C theme={null}
  #include <stdio.h>
  #include <curl/curl.h>

  int main(void) {
      CURL *curl;
      CURLcode res;

      curl_global_init(CURL_GLOBAL_DEFAULT);
      curl = curl_easy_init();

      if(curl) {
          const char *url = "https://api.apimart.ai/api/v1/chat/completions";
          // Can be replaced with any supported model ID
          const char *payload = "{"
              "\"model\":\"gpt-5\","
              "\"stream\":false,"
              "\"messages\":[{\"role\":\"system\",\"content\":\"You are a professional AI assistant.\"},{\"role\":\"user\",\"content\":\"Tell me about the history of artificial intelligence.\"}]"
          "}";

          struct curl_slist *headers = NULL;
          headers = curl_slist_append(headers, "Authorization: Bearer <token>");
          headers = curl_slist_append(headers, "Content-Type: application/json");

          curl_easy_setopt(curl, CURLOPT_URL, url);
          curl_easy_setopt(curl, CURLOPT_POSTFIELDS, payload);
          curl_easy_setopt(curl, CURLOPT_HTTPHEADER, headers);

          res = curl_easy_perform(curl);

          if(res != CURLE_OK) {
              fprintf(stderr, "curl_easy_perform() failed: %s\n",
                      curl_easy_strerror(res));
          }

          curl_slist_free_all(headers);
          curl_easy_cleanup(curl);
      }

      curl_global_cleanup();
      return 0;
  }
  ```

  ```objectivec Objective-C theme={null}
  #import <Foundation/Foundation.h>

  int main(int argc, const char * argv[]) {
      @autoreleasepool {
          NSURL *url = [NSURL URLWithString:@"https://api.apimart.ai/api/v1/chat/completions"];

          NSDictionary *payload = @{
              @"model": @"gpt-5",  // Can be replaced with any supported model ID
              @"stream": @NO,
              @"messages": @[
                  @{
                      @"role": @"system",
                      @"content": @"You are a professional AI assistant."
                  },
                  @{
                      @"role": @"user",
                      @"content": @"Tell me about the history of artificial intelligence."
                  }
              ]
          };

          NSError *error;
          NSData *jsonData = [NSJSONSerialization dataWithJSONObject:payload
                                                            options:0
                                                              error:&error];

          NSMutableURLRequest *request = [NSMutableURLRequest requestWithURL:url];
          [request setHTTPMethod:@"POST"];
          [request setValue:@"Bearer <token>" forHTTPHeaderField:@"Authorization"];
          [request setValue:@"application/json" forHTTPHeaderField:@"Content-Type"];
          [request setHTTPBody:jsonData];

          NSURLSessionDataTask *task = [[NSURLSession sharedSession]
              dataTaskWithRequest:request
              completionHandler:^(NSData *data, NSURLResponse *response, NSError *error) {
                  if (error) {
                      NSLog(@"Error: %@", error);
                      return;
                  }
                  NSString *result = [[NSString alloc] initWithData:data
                                                          encoding:NSUTF8StringEncoding];
                  NSLog(@"%@", result);
              }];

          [task resume];
          [[NSRunLoop mainRunLoop] run];
      }
      return 0;
  }
  ```

  ```ocaml OCaml theme={null}
  (* Requires cohttp and yojson libraries *)
  open Lwt
  open Cohttp
  open Cohttp_lwt_unix

  let url = "https://api.apimart.ai/api/v1/chat/completions"

  (* Can be replaced with any supported model ID *)
  let payload = {|{
    "model": "gpt-5",
    "stream": false,
    "messages": [
      {
        "role": "system",
        "content": "You are a professional AI assistant."
      },
      {
        "role": "user",
        "content": "Tell me about the history of artificial intelligence."
      }
    ]
  }|}

  let () =
    let headers = Header.init ()
      |> fun h -> Header.add h "Authorization" "Bearer <token>"
      |> fun h -> Header.add h "Content-Type" "application/json"
    in
    let body = Cohttp_lwt.Body.of_string payload in

    let response = Client.post ~headers ~body (Uri.of_string url) >>= fun (resp, body) ->
      body |> Cohttp_lwt.Body.to_string >|= fun body_str ->
      print_endline body_str
    in
    Lwt_main.run response
  ```

  ```dart Dart theme={null}
  import 'dart:convert';
  import 'package:http/http.dart' as http;

  void main() async {
    final url = Uri.parse('https://api.apimart.ai/api/v1/chat/completions');

    // Can be replaced with any supported model ID
    final payload = {
      'model': 'gpt-5',
      'stream': false,
      'messages': [
        {
          'role': 'system',
          'content': 'You are a professional AI assistant.'
        },
        {
          'role': 'user',
          'content': 'Tell me about the history of artificial intelligence.'
        }
      ]
    };

    final response = await http.post(
      url,
      headers: {
        'Authorization': 'Bearer <token>',
        'Content-Type': 'application/json',
      },
      body: jsonEncode(payload),
    );

    print(response.body);
  }
  ```

  ```r R theme={null}
  library(httr)
  library(jsonlite)

  url <- "https://api.apimart.ai/api/v1/chat/completions"

  # Can be replaced with any supported model ID
  payload <- list(
    model = "gpt-5",
    stream = FALSE,
    messages = list(
      list(
        role = "system",
        content = "You are a professional AI assistant."
      ),
      list(
        role = "user",
        content = "Tell me about the history of artificial intelligence."
      )
    )
  )

  response <- POST(
    url,
    add_headers(
      Authorization = "Bearer <token>",
      `Content-Type` = "application/json"
    ),
    body = toJSON(payload, auto_unbox = TRUE),
    encode = "raw"
  )

  cat(content(response, "text"))
  ```
</RequestExample>

<ResponseExample>
  ```json 200 theme={null}
  {
    "code": 200,
    "data": {
      "id": "chatcmpl-9876543210",
      "object": "chat.completion",
      "created": 1677652288,
      "model": "gpt-5",
      "choices": [
        {
          "index": 0,
          "message": {
            "role": "assistant",
            "content": "The history of artificial intelligence (AI) dates back to the 1950s...\n\n1. **Early Period (1950s-1960s)**: The proposal of the Turing Test marked the beginning of AI research...\n\n2. **Expert Systems Era (1970s-1980s)**: Rule-based systems began to be applied in medical diagnosis, financial analysis, and other fields...\n\n3. **Rise of Machine Learning (1990s-2000s)**: Statistical learning methods gradually became mainstream...\n\n4. **Deep Learning Revolution (2010s-Present)**: Breakthroughs in neural network technology brought explosive growth to AI..."
          },
          "finish_reason": "stop"
        }
      ],
      "usage": {
        "prompt_tokens": 28,
        "completion_tokens": 320,
        "total_tokens": 348
      }
    }
  }
  ```

  ```json 400 theme={null}
  {
    "error": {
      "code": 400,
      "message": "Invalid request parameters",
      "type": "invalid_request_error"
    }
  }
  ```

  ```json 401 theme={null}
  {
    "error": {
      "code": 401,
      "message": "Authentication failed, please check your API key",
      "type": "authentication_error"
    }
  }
  ```

  ```json 402 theme={null}
  {
    "error": {
      "code": 402,
      "message": "Insufficient account balance, please recharge",
      "type": "payment_required"
    }
  }
  ```

  ```json 403 theme={null}
  {
    "error": {
      "code": 403,
      "message": "Access forbidden, you don't have permission to access this resource",
      "type": "permission_error"
    }
  }
  ```

  ```json 429 theme={null}
  {
    "error": {
      "code": 429,
      "message": "Too many requests, please try again later",
      "type": "rate_limit_error"
    }
  }
  ```

  ```json 500 theme={null}
  {
    "error": {
      "code": 500,
      "message": "Internal server error, please try again later",
      "type": "server_error"
    }
  }
  ```

  ```json 502 theme={null}
  {
    "error": {
      "code": 502,
      "message": "Bad gateway, service temporarily unavailable",
      "type": "bad_gateway"
    }
  }
  ```
</ResponseExample>

## Авторизация

<ParamField header="Authorization" type="string" required>
  Все конечные точки API требуют аутентификации Bearer Token

  Получите свой API-ключ:

  Откройте [страницу управления API-ключами](https://apimart.ai/keys), чтобы получить ваш API-ключ

  Добавьте его в заголовок запроса:

  ```
  Authorization: Bearer YOUR_API_KEY
  ```
</ParamField>

## Body

<ParamField body="model" type="string" required default="gpt-5">
  Название модели

  Поддерживаемые модели:

  * **OpenAI**: `gpt-5`, `gpt-5.1`, `gpt-5-chat-latest`, `gpt-5-mini`
  * **Anthropic**: `claude-opus-4-8`, `claude-opus-4-7`, `claude-opus-4-6`, `claude-sonnet-4-6`, `claude-opus-4-5-20251101`
  * **Google**: `gemini-3.5-flash`, `gemini-3.1-pro-preview`, `gemini-3-pro-preview`, `gemini-3-pro-preview-thinking`, `gemini-3-flash-preview`, `gemini-2.5-pro`, `gemini-2.5-flash`, `gemini-2.5-flash-lite`
  * **DeepSeek**: `deepseek-v4-pro`, `deepseek-v4-flash`, `deepseek-v3.2`, `deepseek-v3.2-exp`, `deepseek-r1-250528`, `deepseek-v3-0324`
  * Список моделей постоянно пополняется...
</ParamField>

<ParamField body="messages" type="array" required>
  Список сообщений беседы

  Массив сообщений. Каждое сообщение содержит поля `role` и `content`.

  **💡 Быстрое заполнение (область «Try it»):**

  1. Нажмите «+ Add an item», чтобы добавить сообщение
  2. Введите `user` (сообщение пользователя), `assistant` (ответ AI) или `system` (системная подсказка) в поле `role`
  3. В поле `content` введите то, что хотите сказать

  <Expandable title="Структура объекта сообщения">
    <ParamField body="role" type="string" required default="user">
      Тип роли

      * `user` — сообщение пользователя
      * `assistant` — ответ AI (для многошагового диалога)
      * `system` — системная подсказка
    </ParamField>

    <ParamField body="content" type="string" required>
      Содержимое сообщения

      Ваш вопрос или сообщение
    </ParamField>
  </Expandable>

  **Пример:**

  ```json theme={null}
  [{"role": "user", "content": "Hello, please introduce yourself"}]
  ```

  **Расширенное использование:**

  Добавление системной подсказки (для определения поведения AI):

  ```json theme={null}
  [
    {"role": "system", "content": "You are a professional Python tutor"},
    {"role": "user", "content": "How do I learn programming?"}
  ]
  ```

  Многошаговый диалог (с контекстом):

  ```json theme={null}
  [
    {"role": "user", "content": "Hello"},
    {"role": "assistant", "content": "Hi! How can I help you?"},
    {"role": "user", "content": "Tell me about AI"}
  ]
  ```

  **Описание ролей:**

  * `user`: сообщение пользователя (используется в большинстве случаев)
  * `system`: системная подсказка для задания поведения и роли AI
  * `assistant`: предыдущие ответы AI, используются для контекста разговора
</ParamField>

<ParamField body="temperature" type="number">
  Управляет случайностью вывода, диапазон 0–2

  * Меньшие значения (например, 0.2) делают вывод более детерминированным
  * Большие значения (например, 1.8) делают вывод более случайным

  По умолчанию: 1.0
</ParamField>

<ParamField body="max_tokens" type="integer">
  Максимальное количество токенов для генерации

  У разных моделей разные максимальные лимиты, обратитесь к документации конкретной модели
</ParamField>

<ParamField body="stream" type="boolean" default="false">
  Использовать ли потоковый вывод

  * `false`: полный ответ за один раз
  * `true`: потоковый возврат

  По умолчанию: false
</ParamField>

<ParamField body="top_p" type="number">
  Параметр ядровой выборки (nucleus sampling), диапазон 0–1

  Управляет разнообразием генерируемого текста, рекомендуется использовать либо этот параметр, либо temperature

  По умолчанию: 1.0
</ParamField>

<ParamField body="frequency_penalty" type="number">
  Штраф за частоту, диапазон от -2.0 до 2.0

  Положительные значения уменьшают вероятность повторения одних и тех же слов

  По умолчанию: 0
</ParamField>

<ParamField body="presence_penalty" type="number">
  Штраф за присутствие, диапазон от -2.0 до 2.0

  Положительные значения увеличивают вероятность обсуждения новых тем

  По умолчанию: 0
</ParamField>

<ParamField body="stop" type="string or array">
  Стоп-последовательности

  До 4 последовательностей, при встрече которых генерация останавливается
</ParamField>

<ParamField body="n" type="integer">
  Количество вариантов ответа для генерации

  По умолчанию: 1

  **⚠️ Внимание:** Необходимо ввести обычное число (например, `1`), без кавычек, иначе возникнет ошибка
</ParamField>

## Response

<ResponseField name="id" type="string">
  Уникальный идентификатор ответа
</ResponseField>

<ResponseField name="object" type="string">
  Тип объекта, фиксированное значение `chat.completion`
</ResponseField>

<ResponseField name="created" type="integer">
  Временная метка создания
</ResponseField>

<ResponseField name="model" type="string">
  Фактически использованное название модели
</ResponseField>

<ResponseField name="choices" type="array">
  Список сгенерированных ответов

  <Expandable title="Свойства">
    <ResponseField name="index" type="integer">
      Индекс варианта
    </ResponseField>

    <ResponseField name="message" type="object">
      Содержимое сообщения

      <Expandable title="Свойства">
        <ResponseField name="role" type="string">
          Тип роли (assistant)
        </ResponseField>

        <ResponseField name="content" type="string">
          Сгенерированный текстовый контент
        </ResponseField>
      </Expandable>
    </ResponseField>

    <ResponseField name="finish_reason" type="string">
      Причина завершения

      Возможные значения:

      * `stop` — естественное завершение
      * `length` — достигнут максимальный размер
      * `content_filter` — контент отфильтрован
      * `function_call` — вызов функции
    </ResponseField>
  </Expandable>
</ResponseField>

<ResponseField name="usage" type="object">
  Статистика использования токенов

  <Expandable title="Свойства">
    <ResponseField name="prompt_tokens" type="integer">
      Количество токенов во входных сообщениях
    </ResponseField>

    <ResponseField name="completion_tokens" type="integer">
      Количество токенов в сгенерированном контенте
    </ResponseField>

    <ResponseField name="total_tokens" type="integer">
      Общее количество токенов
    </ResponseField>
  </Expandable>
</ResponseField>

## Поддерживаемые модели

### OpenAI Series

* `gpt-5` - GPT-5 base model
* `gpt-5.1` - GPT-5.1 enhanced version
* `gpt-5-chat-latest` - GPT-5 latest chat version
* `gpt-5-mini` - GPT-5 lightweight version, cost-effective

### Anthropic Series

* `claude-opus-4-8` - Claude Opus 4.8 flagship model
* `claude-opus-4-7` - Claude Opus 4.7 flagship model
* `claude-opus-4-6` - Claude Opus 4.6 flagship model
* `claude-sonnet-4-6` - Claude Sonnet 4.6 balanced version
* `claude-opus-4-5-20251101` - Claude Opus 4.5 model

### Google Series

* `gemini-3.5-flash` - Gemini 3.5 fast version
* `gemini-3.1-pro-preview` - Gemini 3.1 Pro preview version
* `gemini-3-pro-preview` - Gemini 3 Pro preview version
* `gemini-3-pro-preview-thinking` - Gemini 3 Pro deep thinking preview version
* `gemini-3-flash-preview` - Gemini 3 Flash preview version
* `gemini-2.5-pro` - Gemini 2.5 professional version
* `gemini-2.5-flash` - Gemini 2.5 fast version
* `gemini-2.5-flash-lite` - Gemini 2.5 ultra-lightweight version

### DeepSeek Series

* `deepseek-v4-pro` - DeepSeek V4 professional version
* `deepseek-v4-flash` - DeepSeek V4 fast version
* `deepseek-v3.2` - DeepSeek V3.2 standard version
* `deepseek-v3.2-exp` - DeepSeek V3.2 experimental version
* `deepseek-r1-250528` - DeepSeek R1 reasoning model
* `deepseek-v3-0324` - DeepSeek V3 standard version

## Примеры использования

### Базовый диалог

```json theme={null}
{
  "model": "gpt-5",
  "stream": false,
  "messages": [
    {"role": "user", "content": "Hello"}
  ]
}
```

### Системная подсказка

```json theme={null}
{
  "model": "claude-sonnet-4-6",
  "stream": false,
  "messages": [
    {"role": "system", "content": "You are a professional Python programming tutor"},
    {"role": "user", "content": "How to use list comprehensions?"}
  ]
}
```

### Многошаговый диалог

```json theme={null}
{
  "model": "gemini-2.5-flash",
  "stream": false,
  "messages": [
    {"role": "user", "content": "What is machine learning?"},
    {"role": "assistant", "content": "Machine learning is a branch of artificial intelligence..."},
    {"role": "user", "content": "Can you give me an example?"}
  ]
}
```