Create a VoyageAI inference endpoint
- PUT /_inference/{task_type}/{voyageai_inference_id}
Create an inference endpoint to perform an inference task with the voyageai service.
Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.
Required authorization
- Cluster privileges manage_inference
Request body
-
chunking_settingsobject -
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. -
servicerequired -
The type of service supported for the specified task type. In this case,
voyageai. -
Values:
voyageai -
service_settingsobjectrequired -
Settings used to install the inference model. These settings are specific to the
voyageaiservice. -
dimensionsnumber -
The number of dimensions for resulting output embeddings. This setting maps to
output_dimensionin the VoyageAI documentation. Only for thetext_embeddingtask type. - External docs
-
model_idstringrequired -
The name of the model to use for the inference task. Refer to the VoyageAI documentation for the list of available text embedding and rerank models.
- External docs
-
rate_limitobject -
This setting helps to minimize the number of rate limit errors returned from VoyageAI. The
voyageaiservice sets a default number of requests allowed per minute depending on the task type. For bothtext_embeddingandrerank, it is set to2000. -
embedding_typenumber -
The data type for the embeddings to be returned. This setting maps to
output_dtypein the VoyageAI documentation. Permitted values: float, int8, bit.int8is a synonym ofbytein the VoyageAI documentation.bitis a synonym ofbinaryin the VoyageAI documentation. Only for thetext_embeddingtask type. - External docs
-
task_settingsobject -
Settings to configure the inference task. These settings are specific to the task type you specified.
-
input_typestring -
Type of the input text. Permitted values:
ingest(maps todocumentin the VoyageAI documentation),search(maps toqueryin the VoyageAI documentation). Only for thetext_embeddingtask type. -
return_documentsboolean · default: false -
Whether to return the source documents in the response. Only for the
reranktask type.
Response
-
chunking_settingsobject -
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.