Create an AlibabaCloud AI Search inference endpoint
- PUT /_inference/{task_type}/{alibabacloud_inference_id}
Create an inference endpoint to perform an inference task with the alibabacloud-ai-search service.
- Cluster privileges:
manage_inference
Path Parameters
-
task_typeAlibabaCloudTaskTyperequired -
The type of the inference task that the model will perform.
-
Values:
completionreranksparse_embeddingtext_embedding -
alibabacloud_inference_idstring Idrequired -
The unique identifier of the inference endpoint.
Query Parameters
-
timeoutstring Duration · default: 30s Specifies the amount of time to wait for the inference endpoint to be created.
Request
-
chunking_settingsInferenceChunkingSettings -
The chunking configuration object. Applies only to the
sparse_embeddingortext_embeddingtask types. Not applicable to thererankorcompletiontask types. - Reference
-
max_chunk_sizenumber · default: 250 -
The maximum size of a chunk in words. This value cannot be lower than
20(forsentencestrategy) or10(forwordstrategy). This value should not exceed the window size for the associated model. -
overlapnumber · default: 100 -
The number of overlapping words for chunks. It is applicable only to a
wordchunking strategy. This value cannot be higher than half themax_chunk_sizevalue. -
sentence_overlapnumber · default: 1 -
The number of overlapping sentences for chunks. It is applicable only for a
sentencechunking strategy. It can be either1or0. -
separator_groupstring -
Only applicable to the
recursivestrategy and required when using it.Sets a predefined list of separators in the saved chunking settings based on the selected text type. Values can be
markdownorplaintext.Using this parameter is an alternative to manually specifying a custom
separatorslist. -
separatorsstring -
Only applicable to the
recursivestrategy and required when using it.A list of strings used as possible split points when chunking text.
Each string can be a plain string or a regular expression (regex) pattern. The system tries each separator in order to split the text, starting from the first item in the list.
After splitting, it attempts to recombine smaller pieces into larger chunks that stay within the
max_chunk_sizelimit, to reduce the total number of chunks generated. -
serviceAlibabaCloudServiceTyperequired -
The type of service supported for the specified task type. In this case,
alibabacloud-ai-search. -
Values:
alibabacloud-ai-search -
service_settingsAlibabaCloudServiceSettingsrequired -
Settings used to install the inference model. These settings are specific to the
alibabacloud-ai-searchservice. -
api_keystringrequired -
A valid API key for the AlibabaCloud AI Search API.
-
hoststringrequired -
The name of the host address used for the inference task. You can find the host address in the API keys section of the documentation.
- External docs
-
rate_limitRateLimitSetting -
This setting helps to minimize the number of rate limit errors returned from AlibabaCloud AI Search. By default, the
alibabacloud-ai-searchservice sets the number of requests allowed per minute to1000. -
requests_per_minutenumber -
The number of requests allowed per minute. By default, the number of requests allowed per minute is set by each service as follows:
alibabacloud-ai-searchservice:1000amazonbedrockservice:240anthropicservice:50azureaistudioservice:240azureopenaiservice and task typetext_embedding:1440azureopenaiservice and task typescompletionorchat_completion:120cohereservice:10000contextualaiservice:1000elasticservice and task typechat_completion:240fireworksaiservice:6000googleaistudioservice:360googlevertexaiservice:30000hugging_faceservice:3000jinaaiservice:2000llamaservice:3000mistralservice:240openaiservice and task typetext_embedding:3000openaiservice and task typecompletion:500openshift_aiservice:3000voyageaiservice:2000watsonxaiservice:120
-
service_idstringrequired -
The name of the model service to use for the inference task. The following service IDs are available for the
completiontask:ops-qwen-turboqwen-turboqwen-plusqwen-max ÷ qwen-max-longcontext
The following service ID is available for the
reranktask:ops-bge-reranker-larger
The following service ID is available for the
sparse_embeddingtask:ops-text-sparse-embedding-001
The following service IDs are available for the
text_embeddingtask:ops-text-embedding-001ops-text-embedding-zh-001ops-text-embedding-en-001ops-text-embedding-002 -
workspacestringrequired -
The name of the workspace used for the inference task.
-
task_settingsAlibabaCloudTaskSettings -
Settings to configure the inference task. These settings are specific to the task type you specified.
-
input_typestring -
For a
sparse_embeddingortext_embeddingtask, specify the type of input passed to the model. Valid values are:ingestfor storing document embeddings in a vector database.searchfor storing embeddings of search queries run against a vector database to find relevant documents.
-
return_tokenboolean -
For a
sparse_embeddingtask, it affects whether the token name will be returned in the response. It defaults tofalse, which means only the token ID will be returned in the response.
Response
-
chunking_settingsInferenceChunkingSettings -
The chunking configuration object. Applies only to the
embedding,sparse_embeddingandtext_embeddingtask types. Not applicable to thererank,completion, orchat_completiontask types. -
max_chunk_sizenumber · default: 250 -
The maximum size of a chunk in words. This value cannot be lower than
20(forsentencestrategy) or10(forwordstrategy). This value should not exceed the window size for the associated model. -
overlapnumber · default: 100 -
The number of overlapping words for chunks. It is applicable only to a
wordchunking strategy. This value cannot be higher than half themax_chunk_sizevalue. -
sentence_overlapnumber · default: 1 -
The number of overlapping sentences for chunks. It is applicable only for a
sentencechunking strategy. It can be either1or0. -
separator_groupstring -
Only applicable to the
recursivestrategy and required when using it.Sets a predefined list of separators in the saved chunking settings based on the selected text type. Values can be
markdownorplaintext.Using this parameter is an alternative to manually specifying a custom
separatorslist. -
separatorsstring -
Only applicable to the
recursivestrategy and required when using it.A list of strings used as possible split points when chunking text.
Each string can be a plain string or a regular expression (regex) pattern. The system tries each separator in order to split the text, starting from the first item in the list.
After splitting, it attempts to recombine smaller pieces into larger chunks that stay within the
max_chunk_sizelimit, to reduce the total number of chunks generated. -
servicestringrequired -
The service type
-
service_settingsServiceSettingsrequired -
Settings specific to the service
-
task_settingsTaskSettings -
Task settings specific to the service and task type
-
inference_idstringrequired -
The inference Id
-
task_typeTaskTypeAlibabaCloudAIrequired -
The task type
-
Values:
text_embeddingrerankcompletionsparse_embedding