cURL
curl --request POST \ --url http://localhost:8080/v1/embeddings \ --header 'Content-Type: application/json' \ --data '{ "model": "<string>", "input": "<string>", "encoding_format": "float", "dimensions": 123 }'
{ "index": 123, "object": "<string>", "embedding": [ 123 ] }
Creates an embedding vector representing the input text.
Model identifier in 'provider/model' format
Input text or tokens to embed
The format to return the embeddings in.
float
base64
The number of dimensions the resulting output embeddings should have.
Successful response
Was this page helpful?