Embed
Generate vectors
Generate vector embeddings for input data. This endpoint uses Pinecone Inference.
For guidance and examples, see Embed data.
POST
Authorizations
Body
application/json
Generate embeddings for inputs.
List of inputs to generate embeddings for.
Additional model-specific parameters. Refer to the model guide for available model parameters.
Example:
{
"input_type": "passage",
"truncate": "END"
}
Response
200
application/json
OK
Embeddings generated for the input.
The model used to generate the embeddings
Example:
"multilingual-e5-large"
Indicates whether the response data contains 'dense' or 'sparse' embeddings.
Example:
"dense"
The embeddings generated for the inputs.
Embedding of a single input
Usage statistics for the model inference.
Was this page helpful?