Getting started with YandexGPT API

To run sample requests using the API, install cURL.

To work with the YandexGPT API, you need to get authenticated using your account:

1. Get an IAM token: see the guide for a Yandex account or federated account.

2. Get the ID of the folder for which your account has the ai.languageModels.user role or higher.

3. When accessing YandexGPT API via the API, provide the received parameters in each request:

   • Specify the IAM token in the Authorization header.
   • Specify the folder ID in the x-folder-id header.

   Authorization: Bearer <IAM_token>
   x-folder-id: <folder_ID>
   

For information about other API authentication methods, see Authentication with the Yandex Foundation Models API.

1. Create a file with the request body, e.g., prompt.json:

   {
     "modelUri": "gpt://<folder_ID>/yandexgpt-lite",
     "completionOptions": {
       "stream": false,
       "temperature": 0.6,
       "maxTokens": "2000"
     },
     "messages": [
       {
         "role": "system",
         "text": "Find and correct errors in the text."
       },
       {
         "role": "user",
         "text": "Laminate flooring is sutiable for instalation in the kitchen or in a child's room. It withsatnds moisturre and mechanical dammage thanks to a proctive layer of melamine films 0.2 mm thick and a wax-treated interlocking systme."
       }
     ]
   }
   

   Where:

   • modelUri: ID of the model to generate the response. The parameter contains the ID of a Yandex Cloud folder or the ID of a model fine-tuned in DataSphere.

   • completionOptions: Request configuration options:

     • stream: Enables streaming of partially generated text. It may take either the true or false value.
     • temperature: With a higher temperature, you get more creative and randomized response from the model. This parameter accepts values between 0 and 1, inclusive. The default value is 0.3.
     • maxTokens: Sets a limit on the model's output in tokens. The maximum number of tokens per generation depends on the model. For more information, see Quotas and limits in Yandex Foundation Models.

   • messages: List of messages that set the context for the model:

     • role: Message sender's role:

       • user: Used to send user messages to the model.
       • system: Used to set request context and define the model's behavior.
       • assistant: Used for responses generated by the model. In chat mode, the model's responses tagged with the assistant role are included in the message to save the conversation context. Do not send user messages with this role.

     • text: Text content of the message.

2. Use the completion method to send a request to the neural network in the following command:

   export FOLDER_ID=<folder_ID>
   export IAM_TOKEN=<IAM_token>
   curl \
     --request POST \
     --header "Content-Type: application/json" \
     --header "Authorization: Bearer ${IAM_TOKEN}" \
     --header "x-folder-id: ${FOLDER_ID}" \
     --data "@prompt.json" \
     "https://llm.api.cloud.yandex.net/foundationModels/v1/completion"
   

   Where:

   • FOLDER_ID: ID of the folder for which your account has the ai.languageModels.user role or higher.
   • IAM_TOKEN: IAM token you got before you started.

   In response, the service will return the generated text:

   {
     "result": {
       "alternatives": [
         {
           "message": {
             "role": "assistant",
             "text": "Laminate flooring is suitable for installation in the kitchen or in a child's room. It withstands moisture and mechanical damage thanks to a protective layer of melamine films 0.2 mm thick and a wax-treated interlocking system."
           },
           "status": "ALTERNATIVE_STATUS_TRUNCATED_FINAL"
         }
       ],
       "usage": {
         "inputTextTokens": "67",
         "completionTokens": "50",
         "totalTokens": "117"
       },
       "modelVersion": "06.12.2023"
     }
   }