Create an Nvidia inference endpoint
- PUT /_inference/{task_type}/{nvidia_inference_id}
Create an inference endpoint to perform an inference task with the nvidia service.
Required privileges
- Cluster privileges manage_inference
Request body
-
chunking_settingsobject -
The chunking configuration object. Applies only to the
text_embeddingtask type. Not applicable to thererank,completion, orchat_completiontask 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. -
strategystring · default: sentence -
The chunking strategy:
sentence,word,noneorrecursive.- If
strategyis set torecursive, you must also specify:
max_chunk_size- either
separatorsorseparator_group
Learn more about different chunking strategies in the linked documentation.
- If
- Reference
-
serviceenumrequired -
The type of service supported for the specified task type. In this case,
nvidia. -
Values:
nvidia -
service_settingsobjectrequired -
Settings used to install the inference model. These settings are specific to the
nvidiaservice. -
api_keystringrequired -
A valid API key for your Nvidia endpoint. Can be found in
API Keyssection of Nvidia account settings. -
urlstring -
The URL of the Nvidia model endpoint. If not provided, the default endpoint URL is used depending on the task type:
- For
text_embeddingtask -https://integrate.api.nvidia.com/v1/embeddings. - For
completionandchat_completiontasks -https://integrate.api.nvidia.com/v1/chat/completions. - For
reranktask -https://ai.api.nvidia.com/v1/retrieval/nvidia/reranking.
- For
-
model_idstringrequired -
The name of the model to use for the inference task. Refer to the model's documentation for the name if needed. Service has been tested and confirmed to be working with the following models:
- For
text_embeddingtask -nvidia/llama-3.2-nv-embedqa-1b-v2. - For
completionandchat_completiontasks -microsoft/phi-3-mini-128k-instruct. - For
reranktask -nv-rerank-qa-mistral-4b:1. Service doesn't supporttext_embeddingtaskbaai/bge-m3andnvidia/nvclipmodels due to them not recognizing theinput_typeparameter.
- For
-
max_input_tokensnumber -
For a
text_embeddingtask, the maximum number of tokens per input. Inputs exceeding this value are truncated prior to sending to the Nvidia API. -
similarityenum -
For a
text_embeddingtask, the similarity measure. One of cosine, dot_product, l2_norm. -
Values:
cosinedot_productl2_norm -
rate_limitobject -
This setting helps to minimize the number of rate limit errors returned from the Nvidia API. By default, the
nvidiaservice sets the number of requests allowed per minute to 3000. -
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
-
task_settingsobject -
Settings to configure the inference task. Applies only to the
text_embeddingtask type. Not applicable to thererank,completion, orchat_completiontask types. These settings are specific to the task type you specified. -
input_typeenum -
For a
text_embeddingtask, type of input sent to the Nvidia endpoint. Valid values are:ingest: Mapped to Nvidia'spassagevalue in request. Used when generating embeddings during indexing.search: Mapped to Nvidia'squeryvalue in request. Used when generating embeddings during querying.
ImportantFor Nvidia endpoints, if the
input_typefield is not specified, it defaults toquery. -
Values:
ingestsearch -
truncateenum -
For a
text_embeddingtask, the method used by the Nvidia model to handle inputs longer than the maximum token length. Valid values are:END: When the input exceeds the maximum input token length, the end of the input is discarded.NONE: When the input exceeds the maximum input token length, an error is returned.START: When the input exceeds the maximum input token length, the start of the input is discarded.
-
Values:
ENDNONESTART
Response
-
chunking_settingsobject -
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. -
strategystring · default: sentence -
The chunking strategy:
sentence,word,noneorrecursive.- If
strategyis set torecursive, you must also specify:
max_chunk_size- either
separatorsorseparator_group
Learn more about different chunking strategies in the linked documentation.
- If
- Reference