Completions

English

Completions

Article summary

Did you find this summary helpful?

Thank you for your feedback

Available in Classic and VPC

This is a guide to the Completions API available through the normal mode (LK model) of the Playground.

Request

The following describes the request format for the endpoint. The request format is as follows:

Method	URI
POST	/v1/completions/{model}

Note

When using a task that has been tuning trained, it should be called in the form /v1/tasks/{taskId}/completions. You can check the taskID required for calling in the response body of Create training API.

Request headers

The following describes the headers.

Headers	Required	Description
X-NCP-CLOVASTUDIO-API-KEY	Y	API key issued when creating the test app or service app
X-NCP-APIGW-API-KEY	Y	API Gateway key issued when creating the test app or service app
X-NCP-CLOVASTUDIO-REQUEST-ID	N	Request ID for each request
Content-Type	Y	application/json

Request path parameters

The following describes the parameters.

Field	Type	Required	Description
model	string	Y	Model name to use (e.g., LK-D2)

The following describes the parameters for a task that has been tuning trained.

Field	Type	Required	Description
taskId	string	Y	Training ID

Note

You can check the taskID required for calling in the response body of Create training API.

Request body

The following describes the body.

Field	Type	Required	Description
text	string	Y	User input (prompt); new sentence is generated based on this text
topK	int	N	Top K value; List tokens in order of increasing probability and use only those tokens that are in the range of the top K 0 ≤ topk ≤ 128 (default: 0)
topP	float	N	Top P value; Select tokens with top P in the range of cumulative probability values as candidates 0.00 ＜ topP ≤ 1.00 (default: 0.80)
repeatPenalty	float	N	Penalty value for tokens with repeated expressions 0.0 ＜ repeatPenalty ≤ 10.0 (default: 5.0)
stopBefore	array	N	Character to abort token generation [] (default)
start	string	N	Text to be attached behind the user input value
restart	string	N	Text to be attached behind the output value
maxTokens	int	N	Maximum number of tokens to be used when generating the result value 0 ＜ maxTokens ≤ 2048 (default: 100)
includeTokens	boolean	N	Whether input_tokens and output_tokens will be included in the response false: do not include true: include (default)
temperature	float	N	The randomness of the results; the higher the value, the more likely it is that random results will be generated 0.00 ＜ temperature ≤ 1.00 (default: 0.50)
includeAiFilters	boolean	N	Degree of the generated results in categories such as profanity, degradation/discrimination/hate, sexual harassment/obscenity, etc. false (default) true

Note

When entering some fields, check the following.

The sum of the number of tokens entered in text and the number of tokens entered in maxTokens cannot exceed 2048 tokens.
The number of tokens entered in the text can be checked in CLOVA Studio web by calling the Token Calculator API in the Explorer > Tools tab menu.
topP, temperature: Display to two decimal places.

Request syntax

The following is a sample syntax.

curl --location --request POST 'https://clovastudio.apigw.ntruss.com/testapp/v1/completions/LK-D2' \
--header 'X-NCP-CLOVASTUDIO-API-KEY: <X-NCP-CLOVASTUDIO-API-KEY>' \
--header 'X-NCP-APIGW-API-KEY: <X-NCP-APIGW-API-KEY>' \
--header 'X-NCP-CLOVASTUDIO-REQUEST-ID: <X-NCP-CLOVASTUDIO-REQUEST-ID>' \
--header 'Content-Type: application/json' \
--data '{
 "start": "\nEnglish: ",
  "stopBefore": ["\nKorean: "],
  "text": "Korean: 사과\nEnglish: Apple\nKorean: 바나나",
  "includeAiFilters": true
}'

Response

The following describes the response format.

Response headers

The following describes the headers.

Headers	Required	Description
Content-Type	-	application/json

Response body

The following describes the body.

Field	Type	Required	Description
text	string	-	Created token. It includes both the prompt and result value
stopReason	string	-	Reason for stopping results generation length: reached the maximum length set end_token: reached the maximum number of tokens available stop_before: reached the set stop sequence
inputLength	integer	-	Number of tokens input
inputTokens	string array	-	Entered token information
outputLength	integer	-	Number of response tokens
outputTokens	string array	-	Generated token information
probs	float	-	Probability of each created token being selected
aiFilter	array	-	AI Filter result
aiFilter.groupName	string	-	AI Filter category group name curse unsafeContents
aiFilter.name	string	-	AI Filter category detailed name discrimination: degradation, discrimination, hate (curse) insult: profanity (curse) sexualHarassment: sexual harassment, obscenity (unsafeContents)
aiFilter.score	string	-	AI Filter score 0: Conversation messages are more likely to contain sensitive/hazardous language 1: Conversation messages are likely to contain sensitive/hazardous language 2: Conversation messages are unlikely to contain sensitive/hazardous language -1: AI Filter error occurred
aiFilter.result	string	-	Whether AI Filter is operating properly OK: normal operation ERROR: error occurred

Note

AI Filter can analyze up to 500 characters. However, if the text being analyzed contains many unusual formats, emojis, or special characters, it may not be analyzed correctly.

Response syntax

The following is a sample syntax.

Succeeded

The following is a sample syntax upon a successful call.

{
 
    "status": {
        "code": "20000",
        "message": "OK"
    },
    "result": {
        "text": "Write emotional marketing copy\n\nProduct: lotion\nText: Moisturizes as soon as it touches your skin\n###\nProduct: planner\nText: a gift I give to myself",
        "stopReason": "end_token",
        "startLength": 33,
        "inputText": "Write emotional marketing copy\n\nProduct: lotion\nText: Moisturizes as soon as it touches your skin\n###\nProduct: planner",
        "inputLength": 33,
        "inputTokens": ["Wr", "ite", " emo", "tion", "al", " market","ing", " copy", "\n",
        "\n", "Product", ":", " lotion", "\n", "Text", ":"," Moisturizes", " as", " soon", " as", " it", " touches", " your skin"
        "\n", "##", "#", "\n", "Product", ":", " planner", "\n", "Text", ":"
        ],
        "outputText": "\nText: a gift I give to myself",
        "outputLength": 7,
        "outputTokens": ["a", "gift", "I", "give", "to", "myself",""
        ],
        "probs": [],
        "ok": true,
        "aiFilter": [
            {
                "groupName": "curse",
                "name": "insult",
                "score": "2"
            },
            {
                "groupName": "curse",
                "name": "discrimination",
                "score": "1"
            },
            {
                "groupName": "unsafeContents",
                "name": "sexualHarassment",
                "score": "2"
            }
        ]
    }
}

Failure

The following is a sample syntax upon a failed call.

Was this article helpful?

What's Next

View training

Table of contents

Request
Response