Creating a Model

Function

The API is used to create a model. The configuration includes the model name, description, endpoint, and relevant settings.

**Note: When using a third-party LLM, it is your responsibility to ensure that the model output is secure and compliant. **

There is a strong connection between the embedding model and the cache generation model. When an embedding model is created, the system automatically generates a cache generation model. If any configuration information is deleted by mistake, the model must be rebuilt using the same configuration parameters. For example, if the name of the embedding model is pangu_embedding, the name of the matching cache generation model is pangu_embedding_faq.

When creating a knowledge base, both the embedding model (pangu_embedding) and cache generation model (pangu_embedding_faq) are required. If the cache generation model (pangu_embedding_faq) does not exist or is not accessible, an error is returned. In this case, the administrator needs to check whether the pangu_embedding_faq model exists or whether the knowledge base user has access to it. If the model is missing, create it. If the knowledge base user does not have access to it, grant them the access permission.

URI

POST /v1/{project_id}/applications/{application_id}/uni-search/models

**Table 1** Path Parameters
Parameter	Mandatory	Type	Description
project_id	Yes	String	Definition: Project ID. For details about how to obtain the project ID, see Obtaining a Project ID. Constraints: N/A Value range: The value can contain 1 to 64 characters. Only digits, letters, hyphens (-), and underscores (_) are allowed. The value must start with a letter. Default value: N/A
application_id	Yes	String	Definition: Application ID. For details about how to obtain the application ID, see Obtaining an Application ID. Constraints: Character string Value range: The value can contain 1 to 64 characters. Only digits, letters, hyphens (-), and underscores (_) are allowed. The value must start with a letter. Default value: N/A

Request Parameters

**Table 2** Request header parameters
Parameter	Mandatory	Type	Description
X-Auth-Token	Yes	String	Definition: Token used for API authentication. For details about how to obtain the token, see Obtaining an IAM User Token. Constraints: N/A Value range: N/A Default value: N/A

**Table 3** Request body parameters
Parameter	Mandatory	Type	Description
name	Yes	String	Definition: Model name. Constraints: The length for the embedding model is 28 characters, and 32 characters for other models. Value range: The value contains 1 to 32 characters. It can only contain letters, digits, underscores (_), and hyphens (-), and must start with a letter or digit. Default value: N/A
alias	No	String	Definition: Model name required for the Ascend model scenario. Constraints: N/A Value range: The value cannot be empty. It can contain 1 to 32 characters. It can only contain letters, digits, periods (.), hyphens (-), colons (:), and slashes (/), and must start with a letter or digit. Default value: N/A
detail	Yes	String	Definition: Model details. Constraints: N/A Value range: This parameter cannot be left blank. The value can contain 1 to 512 characters and can contain any characters. Default value: N/A
endpoint	Yes	String	Definition: Model endpoint. Constraints: N/A Value range: The value cannot be empty. It can contain 1 to 512 characters, including any characters. Default value: N/A
type	Yes	String	Definition: Model type. Constraints: N/A Value range: 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 ai_engine Enhance web search service search_engine Search engine mllm: multimodal model Default value: N/A
extend_config	Yes	ModelExtendConfig object	Definition: User-defined model configuration, in JSON format. Constraints: N/A Value range: N/A Default value: N/A
project_id	No	String	Definition: Project ID. Constraints: N/A Value range: Optional. The value must be a string of 1 to 64 characters. It can only contain letters, digits, underscores (_), and hyphens (-). Default value: N/A

**Table 4** ModelExtendConfig
Parameter	Mandatory	Type	Description
iam_info	Yes	IamInfo object	Definition: IAM authentication agency information Constraints: N/A Value range: N/A Default value: N/A
custom_header	No	map<string, object>	Definition: Extended request header. Constraints: N/A Value range: N/A Default value: N/A
deployment_id	No	String	Definition: Model deployment ID. Constraints: N/A Value range: N/A Default value: N/A
vector_config	No	VectorConfig object	Definition: Vector model configuration. Constraints: N/A Value range: N/A Default value: N/A
nlp_config	No	NlpConfig object	Definition: Configuration of the NLP foundation model. Constraints: N/A Value range: N/A Default value: N/A
guard_enabled	No	Boolean	Definition: Whether to enable moderation. Constraints: N/A Value range: N/A Default value: N/A
query_key	No	String	Definition: Key value of the query request body. Constraints: N/A Value range: N/A Default value: N/A
custom_param	No	Map<String,String>	Definition: Request parameter. Constraints: N/A Value range: N/A Default value: N/A
custom_enabled	No	Boolean	Definition: Custom field. Constraints: N/A Value range: N/A Default value: N/A
custom_json_parse	No	Map<String,String>	Definition: Result parsing. Constraints: N/A Value range: N/A Default value: N/A
proxy_enabled	No	Boolean	Definition: Whether to enable the proxy. This parameter is enabled when the web search engine is configured. Constraints: N/A Value range: N/A Default value: N/A
time_detect_enabled	No	Boolean	Definition: Whether to enable periodic detection. This parameter is enabled when the web search engine is configured. Constraints: N/A Value range: N/A Default value: N/A
agree_disclaimer	No	String	Definition: If the disclaimer has been agreed, AGREE is sent. By default, this parameter is left empty. Constraints: N/A Value range: N/A Default value: N/A

**Table 5** IamInfo
Parameter	Mandatory	Type	Description
iam_enabled	No	Boolean	Definition: Indicates whether to enable authentication. Constraints: N/A Value range: N/A Default value: N/A
agency_enabled	No	Boolean	Definition: Indicates whether to use an agency account for authentication Constraints: N/A Value range: N/A Default value: N/A
project_id	No	String	Definition: Project ID of the IAM user. This parameter is mandatory when iam_enable is set to true. Constraints: N/A Value range: N/A Default value: N/A
domain_name	No	String	Definition: Name of the agency account. Constraints: N/A Value range: N/A Default value: N/A
agency_name	No	String	Definition: Agency name. Constraints: N/A Value range: N/A Default value: N/A

**Table 6** VectorConfig
Parameter	Mandatory	Type	Description
embedding_url	Yes	String	Definition: URL for calling the embedding or query2query model. Constraints: N/A Value range: N/A Default value: N/A
rerank_url	No	String	Definition: URL for calling the reranking model. Constraints: N/A Value range: N/A Default value: N/A

**Table 7** NlpConfig
Parameter	Mandatory	Type	Description
context_length	Yes	Integer	Definition: Context length, that is, the maximum number of tokens that can be considered by the NLP foundation model during a specific inference. Constraints: N/A Value range: N/A Default value: N/A

Response Parameters

Status code: 200

Added successfully.

Status code: 400

**Table 8** Response body parameters
Parameter	Type	Description
error_code	String	Definition: Error Code. Value range: N/A
error_msg	String	Definition: Error message. Value range: N/A

Status code: 500

**Table 9** Response body parameters
Parameter	Type	Description
error_code	String	Definition: Error Code. Value range: N/A
error_msg	String	Definition: Error message. Value range: N/A

Example Requests

Add a model.

/v1/b25446daeb1a41a7953c5deba2b2677a/applications/cefb2a59-2f9e-4268-b56b-eab15dc0b9d6/uni-search/models

{
  "name" : "25-test-enbedding",
  "type" : "embedding",
  "endpoint" : "https://xxxxxx",
  "detail" : "test",
  "extend_config" : {
    "iam_info" : {
      "iam_enabled" : false,
      "agency_enabled" : false
    },
    "vector_config" : {
      "embedding_url" : "/app/search/v1/vector"
    },
    "time_detect_enabled" : true,
    "custom_enabled" : true,
    "custom_header" : { }
  }
}