README.md

Dedicated.Embeddings

Overview

Available Operations

• embeddings - Embeddings

embeddings

Creates an embedding vector representing the input text.

Example Usage

import os

from friendli import SyncFriendli

with SyncFriendli(
    token=os.getenv("FRIENDLI_TOKEN", ""),
) as friendli:
    res = friendli.dedicated.embeddings.embeddings(
        model="(endpoint-id)",
        input_="The food was delicious and the waiter...",
        encoding_format="float",
    )

    # Handle response
    print(res)

Parameters

Parameter	Type	Required	Description	Example
model	str	✔️	ID of target endpoint. If you want to send request to specific adapter, use the format "YOUR_ENDPOINT_ID:YOUR_ADAPTER_ROUTE". Otherwise, you can just use "YOUR_ENDPOINT_ID" alone.	(endpoint-id)
input	models.Input	✔️	Input text to embed, encoded as a string or array of tokens. To embed multiple inputs in a single request, pass an array of strings or array of token arrays.	The food was delicious and the waiter...
x_friendli_team	OptionalNullable[str]	➖	ID of team to run requests as (optional parameter).
encoding_format	OptionalNullable[models.EncodingFormat]	➖	The format to return the embeddings in. Can be either float or base64.
retries	Optional[utils.RetryConfig]	➖	Configuration to override the default retry behavior of the client.

Response

models.DedicatedEmbeddingsSuccess

Errors

Error Type	Status Code	Content Type
models.SDKError	4XX, 5XX	*/*