Create a DeepSeek inference endpoint
- PUT /_inference/{task_type}/{deepseek_inference_id}
Create an inference endpoint to perform an inference task with the deepseek service.
- Cluster privileges:
manage_inference
Path Parameters
-
task_typeTaskTypeDeepSeekrequired -
The type of the inference task that the model will perform.
-
Values:
completionchat_completion -
deepseek_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.
- Reference
-
max_chunk_sizenumber · default: 250 -
The maximum size of a chunk in words. This value cannot be higher than
300or lower than20(forsentencestrategy) or10(forwordstrategy). -
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. -
strategystring · default: sentence -
The chunking strategy:
sentenceorword. -
serviceDeepSeekServiceTyperequired -
The type of service supported for the specified task type. In this case,
deepseek. -
Values:
deepseek -
service_settingsDeepSeekServiceSettingsrequired -
Settings used to install the inference model. These settings are specific to the
deepseekservice. -
api_keystringrequired -
A valid API key for your DeepSeek account. You can find or create your DeepSeek API keys on the DeepSeek API key page.
IMPORTANT: You need to provide the API key only once, during the inference model creation. The get inference endpoint API does not retrieve your API key.
- External docs
-
model_idstringrequired -
For a
completionorchat_completiontask, the name of the model to use for the inference task.For the available
completionandchat_completionmodels, refer to the DeepSeek Models & Pricing docs. -
urlstring -
The URL endpoint to use for the requests. Defaults to
https://api.deepseek.com/chat/completions.
Response
-
chunking_settingsInferenceChunkingSettings -
Chunking configuration object
-
max_chunk_sizenumber · default: 250 -
The maximum size of a chunk in words. This value cannot be higher than
300or lower than20(forsentencestrategy) or10(forwordstrategy). -
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. -
strategystring · default: sentence -
The chunking strategy:
sentenceorword. -
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