Sliding window

Available in Classic and VPC

Delete sentences that exceed the maximum number of tokens when using Chat completions API. The oldest conversation turns are deleted to free up tokens so that conversations can be created without interruption.

Note

For a detailed description of how the sliding window works and how to work with it, see Utilize API of the CLOVA Studio user guide.

Request

This section describes the request format. The method and URI are as follows:

Method	URI
POST	/v1/api-tools/sliding/chat-messages/{modelName}

Request headers

The following describes the request headers.

Field	Required	Description
`Authorization`	Required	API key for authentication <e.g.,> `Bearer nv-************`
`X-NCP-CLOVASTUDIO-REQUEST-ID`	Optional	Request ID
`Content-Type`	Required	Request data format `application/json`

Request path parameters

You can use the following path parameters with your request:

Field	Type	Required	Description
`modelName`	String	Required	Model name <e.g.> HCX-003

Request body

You can include the following data in the body of your request:

Field	Type	Required	Description
`maxTokens`	Integer	Required	Maximum number of generated tokens 0 ＜ `maxTokens` ≤ 4096 (default: 100)
`messages`	Array	Required	Conversation message list Need to be adjusted for maximum number of tokens
`messages.role`	Enum	Required	Role of conversation messages `system` \| `user` \| `assistant` `system`: directives that define roles `user`: user utterances/questions `assistant`: answers to user utterances/questions
`messages.content`	String	Required	Content of conversation messages

Note

When entering some fields, check the following.

messages: The sum of the number of tokens entered and the number of tokens entered in maxTokens can't exceed 4096 tokens. The number of tokens entered in messages can be checked by calling the Token calculation API.

Request example

The request example is as follows:

curl --location --request POST 'https://clovastudio.stream.ntruss.com/v1/api-tools/sliding/chat-messages/{modelName}' \
--header 'Authorization: Bearer {API Key}' \
--header 'X-NCP-CLOVASTUDIO-REQUEST-ID: {Request ID}' \
--header 'Content-Type: application/json' \
--data '{
      "maxTokens" : 200,
      "messages" : [ {
        "role" : "user",
        "content" : "hello"
      } ]
}'

Response

This section describes the response format.

Response body

The following describes the body.

Field	Type	Required	Description
`result`	Object	-	Response result Result of adjusting for the maximum number of tokens
`result.messages`	Array	-	Conversation message list
`result.messages.role`	Enum	-	Role of conversation messages `system` \| `user` \| `assistant` `system`: directives that define roles `user`: user utterances/questions `assistant`: answers to user utterances/questions
`result.messages.content`	String	-	Content of conversation messages

Response example

The response example is as follows:

Succeeded

The following is a sample response upon a successful call.

{
    "status": {
        "code": "20000",
        "message": "OK"
    },
    "result": {
        "messages": [
            {
                "role": "user",
                "content": "hello"
            }
        ]
    }
}

Failure

The following is a sample response upon a failed call.