Creating a model

Function

The API is used to configure the added NLP model, including the model name, model description, model endpoint, and model deployment_id.

URI

POST /v1/koosearch/models

Request Parameters

**Table 1** Request header parameters
Parameter	Mandatory	Type	Description
X-Auth-Token	Yes	String	Parameter description: Token used for API authentication. For how to obtain the token, see section 3.2 "Authentication." Constraints: N/A.

**Table 2** Request body parameters
Parameter	Mandatory	Type	Description
name	Yes	String	Model name
detail	Yes	String	Model description
endpoint	Yes	String	Model endpoint
type	Yes	String	Model type: Pangu_chat Pangu chat model pangu_llm Pangu model deployed on bare metal embedding Embedding model query2query query2query model rerank Reranking model search_plan Search planning model llm LLM
extend_config	Yes	ModelExtendConfig object	Customized model configuration in JSON format
alias	No	String	Model name required for the Ascend model scenario

**Table 3** ModelExtendConfig
Parameter	Mandatory	Type	Description
iam_info	Yes	IamInfo object	IAM authentication agency information
custom_header	No	map<string, object>	Extended request header
deployment_id	No	String	deployment_id of a model
vector_config	No	VectorConfig object	Vector model configuration.
nlp_config	No	NlpConfig object	Configuration of the NLP foundation model.

**Table 4** IamInfo
Parameter	Mandatory	Type	Description
iam_enabled	No	Boolean	Indicates whether to enable authentication
agency_enabled	No	Boolean	Indicates whether to use an agency account for authentication
project_id	No	String	Project ID of the IAM user. This parameter is mandatory when iam_enable is set to true.
domain_name	No	String	Name of the agency account
agency_name	No	String	Agency name.

**Table 5** VectorConfig
Parameter	Mandatory	Type	Description
embedding_url	Yes	String	URL for calling the embedding or query2query model.
rerank_url	Yes	String	URL for calling the reranking model.

**Table 6** NlpConfig
Parameter	Mandatory	Type	Description
context_length	Yes	Integer	Context length, that is, the maximum number of tokens that can be considered by the NLP foundation model during a specific inference.

Response Parameters

Status code: 400

**Table 7** Response body parameters
Parameter	Type	Description
error_code	String	Error Code
error_msg	String	Error description

Status code: 500

**Table 8** Response body parameters
Parameter	Type	Description
error_code	String	Error Code
error_msg	String	Error description

Example Requests

POST https://{endpoint}/v1/koosearch/models

{
  "name" : "pangu_v30_32k",
  "type" : "pangu_llm",
  "endpoint" : "http://10.0.0.169:31010",
  "detail" : "panguv30_4k",
  "extend_config" : {
    "deployment_id" : "panguv30_4k",
    "iam_info" : {
      "project_id" : "123",
      "iam_enabled" : false,
      "agency_enabled" : false
    },
    "nlp_config" : {
      "context_length" : 32
    }
  }
}