Listing Models

Function

Lists models.

URI

GET /v1/koosearch/models/search

**Table 1** Query Parameters
Parameter	Mandatory	Type	Description
model_name	No	String	Model name.
model_type	No	String	Model type. Enumerated values: embedding, rerank, nlp, search-plan, and query2query
model_status	No	String	Model status.
page_num	No	Integer	Request page number.
page_size	No	Integer	Response result page size specified by the request, for example, 5 records/page or 10 records/page.

Request Parameters

**Table 2** 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.

Response Parameters

Status code: 200

**Table 3** Response body parameters
Parameter	Type	Description
models	Array of ModelInfo objects	Model list.
total	Integer	Total Items Returned
page_num	Integer	Page number.
page_size	Integer	Number of records returned on each page.

**Table 4** ModelInfo
Parameter	Type	Description
name	String	Model name.
detail	String	Model details
type	String	Model type.
endpoint	String	Model endpoint
status	String	Model status
create_time	String	Model creation time.
update_time	String	Time when a model is updated.
extend_config	ModelExtendConfig object	Model extension configuration
alias	String	Name used in the Ascend model request.

**Table 5** ModelExtendConfig
Parameter	Type	Description
iam_info	IamInfo object	IAM authentication agency information
custom_header	map<string, object>	Extended request header
deployment_id	String	deployment_id of a model
vector_config	VectorConfig object	Vector model configuration.
nlp_config	NlpConfig object	Configuration of the NLP foundation model.

**Table 6** IamInfo
Parameter	Type	Description
iam_enabled	Boolean	Indicates whether to enable authentication
agency_enabled	Boolean	Indicates whether to use an agency account for authentication
project_id	String	Project ID of the IAM user. This parameter is mandatory when iam_enable is set to true.
domain_name	String	Name of the agency account
agency_name	String	Agency name.

**Table 7** VectorConfig
Parameter	Type	Description
embedding_url	String	URL for calling the embedding or query2query model.
rerank_url	String	URL for calling the reranking model.

**Table 8** NlpConfig
Parameter	Type	Description
context_length	Integer	Context length, that is, the maximum number of tokens that can be considered by the NLP foundation model during a specific inference.

Status code: 400

**Table 9** Response body parameters
Parameter	Type	Description
error_code	String	Error Code
error_msg	String	Error description

Status code: 500

**Table 10** Response body parameters
Parameter	Type	Description
error_code	String	Error Code
error_msg	String	Error description

Example Requests

None

Example Responses

Status code: 200

Model list.

{
  "page_num" : 1,
  "page_size" : 1,
  "total" : 1,
  "models" : [ {
    "name" : "pangu_38b",
    "detail" : "pangu_38b",
    "type" : "nlp",
    "status" : "ready",
    "create_time" : "1716946517167",
    "update_time" : "1716946517167",
    "endpoint" : "http://10.0.0.169:31010",
    "extend_config" : {
      "deployment_id" : "123",
      "iam_info" : {
        "iam_enabled" : false,
        "agency_enabled" : false,
        "project_id" : "456"
      }
    }
  } ]
}