README.md

Completions

(container.completions)

Overview

Available Operations

• complete - Completions
• stream - Stream completions

complete

Generate text based on the given text prompt.

Example Usage

import os

from friendli import SyncFriendli

with SyncFriendli(
    token=os.getenv("FRIENDLI_TOKEN", ""),
) as friendli:
    res = friendli.container.completions.complete(
        request={
            "prompt": "Say this is a test!",
            "stream": False,
        }
    )

    # Handle response
    print(res)

Parameters

Parameter	Type	Required	Description
request	models.ContainerCompletionsBody	✔️	The request object to use for the request.
retries	Optional[utils.RetryConfig]	➖	Configuration to override the default retry behavior of the client.
server_url	Optional[str]	➖	An optional server URL to use.

Response

models.ContainerCompletionsSuccess

Errors

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

stream

Generate text based on the given text prompt.

Example Usage

import os

from friendli import SyncFriendli

with SyncFriendli(
    token=os.getenv("FRIENDLI_TOKEN", ""),
) as friendli:
    res = friendli.container.completions.stream(
        request={
            "prompt": "Say this is a test!",
            "stream": True,
        }
    )

    with res as event_stream:
        for event in event_stream:
            # handle event
            print(event, flush=True)

Parameters

Parameter	Type	Required	Description
request	models.ContainerCompletionsStreamBody	✔️	The request object to use for the request.
retries	Optional[utils.RetryConfig]	➖	Configuration to override the default retry behavior of the client.
server_url	Optional[str]	➖	An optional server URL to use.

Response

Union[eventstreaming.EventStream[models.ContainerCompletionsStreamSuccess], eventstreaming.EventStreamAsync[models.ContainerCompletionsStreamSuccess]]

Errors

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