# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details. from __future__ import annotations from typing import List from typing_extensions import Literal, overload import httpx from .. import _legacy_response from ..types import completion_create_params from .._types import NOT_GIVEN, Body, Query, Headers, NotGiven from .._utils import ( is_given, required_args, maybe_transform, async_maybe_transform, ) from .._compat import cached_property from .._resource import SyncAPIResource, AsyncAPIResource from .._response import to_streamed_response_wrapper, async_to_streamed_response_wrapper from .._constants import DEFAULT_TIMEOUT from .._streaming import Stream, AsyncStream from .._base_client import make_request_options from ..types.completion import Completion from ..types.model_param import ModelParam from ..types.metadata_param import MetadataParam __all__ = ["Completions", "AsyncCompletions"] class Completions(SyncAPIResource): @cached_property def with_raw_response(self) -> CompletionsWithRawResponse: """ This property can be used as a prefix for any HTTP method call to return the the raw response object instead of the parsed content. For more information, see https://www.github.com/anthropics/anthropic-sdk-python#accessing-raw-response-data-eg-headers """ return CompletionsWithRawResponse(self) @cached_property def with_streaming_response(self) -> CompletionsWithStreamingResponse: """ An alternative to `.with_raw_response` that doesn't eagerly read the response body. For more information, see https://www.github.com/anthropics/anthropic-sdk-python#with_streaming_response """ return CompletionsWithStreamingResponse(self) @overload def create( self, *, max_tokens_to_sample: int, model: ModelParam, prompt: str, metadata: MetadataParam | NotGiven = NOT_GIVEN, stop_sequences: List[str] | NotGiven = NOT_GIVEN, stream: Literal[False] | NotGiven = NOT_GIVEN, temperature: float | NotGiven = NOT_GIVEN, top_k: int | NotGiven = NOT_GIVEN, top_p: float | NotGiven = NOT_GIVEN, # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs. # The extra values given here take precedence over values defined on the client or passed to this method. extra_headers: Headers | None = None, extra_query: Query | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> Completion: """[Legacy] Create a Text Completion. The Text Completions API is a legacy API. We recommend using the [Messages API](https://docs.anthropic.com/en/api/messages) going forward. Future models and features will not be compatible with Text Completions. See our [migration guide](https://docs.anthropic.com/en/api/migrating-from-text-completions-to-messages) for guidance in migrating from Text Completions to Messages. Args: max_tokens_to_sample: The maximum number of tokens to generate before stopping. Note that our models may stop _before_ reaching this maximum. This parameter only specifies the absolute maximum number of tokens to generate. model: The model that will complete your prompt.\n\nSee [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. prompt: The prompt that you want Claude to complete. For proper response generation you will need to format your prompt using alternating `\n\nHuman:` and `\n\nAssistant:` conversational turns. For example: ``` "\n\nHuman: {userQuestion}\n\nAssistant:" ``` See [prompt validation](https://docs.anthropic.com/en/api/prompt-validation) and our guide to [prompt design](https://docs.anthropic.com/en/docs/intro-to-prompting) for more details. metadata: An object describing metadata about the request. stop_sequences: Sequences that will cause the model to stop generating. Our models stop on `"\n\nHuman:"`, and may include additional built-in stop sequences in the future. By providing the stop_sequences parameter, you may include additional strings that will cause the model to stop generating. stream: Whether to incrementally stream the response using server-sent events. See [streaming](https://docs.anthropic.com/en/api/streaming) for details. temperature: Amount of randomness injected into the response. Defaults to `1.0`. Ranges from `0.0` to `1.0`. Use `temperature` closer to `0.0` for analytical / multiple choice, and closer to `1.0` for creative and generative tasks. Note that even with `temperature` of `0.0`, the results will not be fully deterministic. top_k: Only sample from the top K options for each subsequent token. Used to remove "long tail" low probability responses. [Learn more technical details here](https://towardsdatascience.com/how-to-sample-from-language-models-682bceb97277). Recommended for advanced use cases only. You usually only need to use `temperature`. top_p: Use nucleus sampling. In nucleus sampling, we compute the cumulative distribution over all the options for each subsequent token in decreasing probability order and cut it off once it reaches a particular probability specified by `top_p`. You should either alter `temperature` or `top_p`, but not both. Recommended for advanced use cases only. You usually only need to use `temperature`. extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds """ ... @overload def create( self, *, max_tokens_to_sample: int, model: ModelParam, prompt: str, stream: Literal[True], metadata: MetadataParam | NotGiven = NOT_GIVEN, stop_sequences: List[str] | NotGiven = NOT_GIVEN, temperature: float | NotGiven = NOT_GIVEN, top_k: int | NotGiven = NOT_GIVEN, top_p: float | NotGiven = NOT_GIVEN, # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs. # The extra values given here take precedence over values defined on the client or passed to this method. extra_headers: Headers | None = None, extra_query: Query | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> Stream[Completion]: """[Legacy] Create a Text Completion. The Text Completions API is a legacy API. We recommend using the [Messages API](https://docs.anthropic.com/en/api/messages) going forward. Future models and features will not be compatible with Text Completions. See our [migration guide](https://docs.anthropic.com/en/api/migrating-from-text-completions-to-messages) for guidance in migrating from Text Completions to Messages. Args: max_tokens_to_sample: The maximum number of tokens to generate before stopping. Note that our models may stop _before_ reaching this maximum. This parameter only specifies the absolute maximum number of tokens to generate. model: The model that will complete your prompt.\n\nSee [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. prompt: The prompt that you want Claude to complete. For proper response generation you will need to format your prompt using alternating `\n\nHuman:` and `\n\nAssistant:` conversational turns. For example: ``` "\n\nHuman: {userQuestion}\n\nAssistant:" ``` See [prompt validation](https://docs.anthropic.com/en/api/prompt-validation) and our guide to [prompt design](https://docs.anthropic.com/en/docs/intro-to-prompting) for more details. stream: Whether to incrementally stream the response using server-sent events. See [streaming](https://docs.anthropic.com/en/api/streaming) for details. metadata: An object describing metadata about the request. stop_sequences: Sequences that will cause the model to stop generating. Our models stop on `"\n\nHuman:"`, and may include additional built-in stop sequences in the future. By providing the stop_sequences parameter, you may include additional strings that will cause the model to stop generating. temperature: Amount of randomness injected into the response. Defaults to `1.0`. Ranges from `0.0` to `1.0`. Use `temperature` closer to `0.0` for analytical / multiple choice, and closer to `1.0` for creative and generative tasks. Note that even with `temperature` of `0.0`, the results will not be fully deterministic. top_k: Only sample from the top K options for each subsequent token. Used to remove "long tail" low probability responses. [Learn more technical details here](https://towardsdatascience.com/how-to-sample-from-language-models-682bceb97277). Recommended for advanced use cases only. You usually only need to use `temperature`. top_p: Use nucleus sampling. In nucleus sampling, we compute the cumulative distribution over all the options for each subsequent token in decreasing probability order and cut it off once it reaches a particular probability specified by `top_p`. You should either alter `temperature` or `top_p`, but not both. Recommended for advanced use cases only. You usually only need to use `temperature`. extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds """ ... @overload def create( self, *, max_tokens_to_sample: int, model: ModelParam, prompt: str, stream: bool, metadata: MetadataParam | NotGiven = NOT_GIVEN, stop_sequences: List[str] | NotGiven = NOT_GIVEN, temperature: float | NotGiven = NOT_GIVEN, top_k: int | NotGiven = NOT_GIVEN, top_p: float | NotGiven = NOT_GIVEN, # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs. # The extra values given here take precedence over values defined on the client or passed to this method. extra_headers: Headers | None = None, extra_query: Query | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> Completion | Stream[Completion]: """[Legacy] Create a Text Completion. The Text Completions API is a legacy API. We recommend using the [Messages API](https://docs.anthropic.com/en/api/messages) going forward. Future models and features will not be compatible with Text Completions. See our [migration guide](https://docs.anthropic.com/en/api/migrating-from-text-completions-to-messages) for guidance in migrating from Text Completions to Messages. Args: max_tokens_to_sample: The maximum number of tokens to generate before stopping. Note that our models may stop _before_ reaching this maximum. This parameter only specifies the absolute maximum number of tokens to generate. model: The model that will complete your prompt.\n\nSee [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. prompt: The prompt that you want Claude to complete. For proper response generation you will need to format your prompt using alternating `\n\nHuman:` and `\n\nAssistant:` conversational turns. For example: ``` "\n\nHuman: {userQuestion}\n\nAssistant:" ``` See [prompt validation](https://docs.anthropic.com/en/api/prompt-validation) and our guide to [prompt design](https://docs.anthropic.com/en/docs/intro-to-prompting) for more details. stream: Whether to incrementally stream the response using server-sent events. See [streaming](https://docs.anthropic.com/en/api/streaming) for details. metadata: An object describing metadata about the request. stop_sequences: Sequences that will cause the model to stop generating. Our models stop on `"\n\nHuman:"`, and may include additional built-in stop sequences in the future. By providing the stop_sequences parameter, you may include additional strings that will cause the model to stop generating. temperature: Amount of randomness injected into the response. Defaults to `1.0`. Ranges from `0.0` to `1.0`. Use `temperature` closer to `0.0` for analytical / multiple choice, and closer to `1.0` for creative and generative tasks. Note that even with `temperature` of `0.0`, the results will not be fully deterministic. top_k: Only sample from the top K options for each subsequent token. Used to remove "long tail" low probability responses. [Learn more technical details here](https://towardsdatascience.com/how-to-sample-from-language-models-682bceb97277). Recommended for advanced use cases only. You usually only need to use `temperature`. top_p: Use nucleus sampling. In nucleus sampling, we compute the cumulative distribution over all the options for each subsequent token in decreasing probability order and cut it off once it reaches a particular probability specified by `top_p`. You should either alter `temperature` or `top_p`, but not both. Recommended for advanced use cases only. You usually only need to use `temperature`. extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds """ ... @required_args(["max_tokens_to_sample", "model", "prompt"], ["max_tokens_to_sample", "model", "prompt", "stream"]) def create( self, *, max_tokens_to_sample: int, model: ModelParam, prompt: str, metadata: MetadataParam | NotGiven = NOT_GIVEN, stop_sequences: List[str] | NotGiven = NOT_GIVEN, stream: Literal[False] | Literal[True] | NotGiven = NOT_GIVEN, temperature: float | NotGiven = NOT_GIVEN, top_k: int | NotGiven = NOT_GIVEN, top_p: float | NotGiven = NOT_GIVEN, # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs. # The extra values given here take precedence over values defined on the client or passed to this method. extra_headers: Headers | None = None, extra_query: Query | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> Completion | Stream[Completion]: if not is_given(timeout) and self._client.timeout == DEFAULT_TIMEOUT: timeout = 600 return self._post( "/v1/complete", body=maybe_transform( { "max_tokens_to_sample": max_tokens_to_sample, "model": model, "prompt": prompt, "metadata": metadata, "stop_sequences": stop_sequences, "stream": stream, "temperature": temperature, "top_k": top_k, "top_p": top_p, }, completion_create_params.CompletionCreateParams, ), options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout ), cast_to=Completion, stream=stream or False, stream_cls=Stream[Completion], ) class AsyncCompletions(AsyncAPIResource): @cached_property def with_raw_response(self) -> AsyncCompletionsWithRawResponse: """ This property can be used as a prefix for any HTTP method call to return the the raw response object instead of the parsed content. For more information, see https://www.github.com/anthropics/anthropic-sdk-python#accessing-raw-response-data-eg-headers """ return AsyncCompletionsWithRawResponse(self) @cached_property def with_streaming_response(self) -> AsyncCompletionsWithStreamingResponse: """ An alternative to `.with_raw_response` that doesn't eagerly read the response body. For more information, see https://www.github.com/anthropics/anthropic-sdk-python#with_streaming_response """ return AsyncCompletionsWithStreamingResponse(self) @overload async def create( self, *, max_tokens_to_sample: int, model: ModelParam, prompt: str, metadata: MetadataParam | NotGiven = NOT_GIVEN, stop_sequences: List[str] | NotGiven = NOT_GIVEN, stream: Literal[False] | NotGiven = NOT_GIVEN, temperature: float | NotGiven = NOT_GIVEN, top_k: int | NotGiven = NOT_GIVEN, top_p: float | NotGiven = NOT_GIVEN, # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs. # The extra values given here take precedence over values defined on the client or passed to this method. extra_headers: Headers | None = None, extra_query: Query | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> Completion: """[Legacy] Create a Text Completion. The Text Completions API is a legacy API. We recommend using the [Messages API](https://docs.anthropic.com/en/api/messages) going forward. Future models and features will not be compatible with Text Completions. See our [migration guide](https://docs.anthropic.com/en/api/migrating-from-text-completions-to-messages) for guidance in migrating from Text Completions to Messages. Args: max_tokens_to_sample: The maximum number of tokens to generate before stopping. Note that our models may stop _before_ reaching this maximum. This parameter only specifies the absolute maximum number of tokens to generate. model: The model that will complete your prompt.\n\nSee [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. prompt: The prompt that you want Claude to complete. For proper response generation you will need to format your prompt using alternating `\n\nHuman:` and `\n\nAssistant:` conversational turns. For example: ``` "\n\nHuman: {userQuestion}\n\nAssistant:" ``` See [prompt validation](https://docs.anthropic.com/en/api/prompt-validation) and our guide to [prompt design](https://docs.anthropic.com/en/docs/intro-to-prompting) for more details. metadata: An object describing metadata about the request. stop_sequences: Sequences that will cause the model to stop generating. Our models stop on `"\n\nHuman:"`, and may include additional built-in stop sequences in the future. By providing the stop_sequences parameter, you may include additional strings that will cause the model to stop generating. stream: Whether to incrementally stream the response using server-sent events. See [streaming](https://docs.anthropic.com/en/api/streaming) for details. temperature: Amount of randomness injected into the response. Defaults to `1.0`. Ranges from `0.0` to `1.0`. Use `temperature` closer to `0.0` for analytical / multiple choice, and closer to `1.0` for creative and generative tasks. Note that even with `temperature` of `0.0`, the results will not be fully deterministic. top_k: Only sample from the top K options for each subsequent token. Used to remove "long tail" low probability responses. [Learn more technical details here](https://towardsdatascience.com/how-to-sample-from-language-models-682bceb97277). Recommended for advanced use cases only. You usually only need to use `temperature`. top_p: Use nucleus sampling. In nucleus sampling, we compute the cumulative distribution over all the options for each subsequent token in decreasing probability order and cut it off once it reaches a particular probability specified by `top_p`. You should either alter `temperature` or `top_p`, but not both. Recommended for advanced use cases only. You usually only need to use `temperature`. extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds """ ... @overload async def create( self, *, max_tokens_to_sample: int, model: ModelParam, prompt: str, stream: Literal[True], metadata: MetadataParam | NotGiven = NOT_GIVEN, stop_sequences: List[str] | NotGiven = NOT_GIVEN, temperature: float | NotGiven = NOT_GIVEN, top_k: int | NotGiven = NOT_GIVEN, top_p: float | NotGiven = NOT_GIVEN, # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs. # The extra values given here take precedence over values defined on the client or passed to this method. extra_headers: Headers | None = None, extra_query: Query | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> AsyncStream[Completion]: """[Legacy] Create a Text Completion. The Text Completions API is a legacy API. We recommend using the [Messages API](https://docs.anthropic.com/en/api/messages) going forward. Future models and features will not be compatible with Text Completions. See our [migration guide](https://docs.anthropic.com/en/api/migrating-from-text-completions-to-messages) for guidance in migrating from Text Completions to Messages. Args: max_tokens_to_sample: The maximum number of tokens to generate before stopping. Note that our models may stop _before_ reaching this maximum. This parameter only specifies the absolute maximum number of tokens to generate. model: The model that will complete your prompt.\n\nSee [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. prompt: The prompt that you want Claude to complete. For proper response generation you will need to format your prompt using alternating `\n\nHuman:` and `\n\nAssistant:` conversational turns. For example: ``` "\n\nHuman: {userQuestion}\n\nAssistant:" ``` See [prompt validation](https://docs.anthropic.com/en/api/prompt-validation) and our guide to [prompt design](https://docs.anthropic.com/en/docs/intro-to-prompting) for more details. stream: Whether to incrementally stream the response using server-sent events. See [streaming](https://docs.anthropic.com/en/api/streaming) for details. metadata: An object describing metadata about the request. stop_sequences: Sequences that will cause the model to stop generating. Our models stop on `"\n\nHuman:"`, and may include additional built-in stop sequences in the future. By providing the stop_sequences parameter, you may include additional strings that will cause the model to stop generating. temperature: Amount of randomness injected into the response. Defaults to `1.0`. Ranges from `0.0` to `1.0`. Use `temperature` closer to `0.0` for analytical / multiple choice, and closer to `1.0` for creative and generative tasks. Note that even with `temperature` of `0.0`, the results will not be fully deterministic. top_k: Only sample from the top K options for each subsequent token. Used to remove "long tail" low probability responses. [Learn more technical details here](https://towardsdatascience.com/how-to-sample-from-language-models-682bceb97277). Recommended for advanced use cases only. You usually only need to use `temperature`. top_p: Use nucleus sampling. In nucleus sampling, we compute the cumulative distribution over all the options for each subsequent token in decreasing probability order and cut it off once it reaches a particular probability specified by `top_p`. You should either alter `temperature` or `top_p`, but not both. Recommended for advanced use cases only. You usually only need to use `temperature`. extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds """ ... @overload async def create( self, *, max_tokens_to_sample: int, model: ModelParam, prompt: str, stream: bool, metadata: MetadataParam | NotGiven = NOT_GIVEN, stop_sequences: List[str] | NotGiven = NOT_GIVEN, temperature: float | NotGiven = NOT_GIVEN, top_k: int | NotGiven = NOT_GIVEN, top_p: float | NotGiven = NOT_GIVEN, # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs. # The extra values given here take precedence over values defined on the client or passed to this method. extra_headers: Headers | None = None, extra_query: Query | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> Completion | AsyncStream[Completion]: """[Legacy] Create a Text Completion. The Text Completions API is a legacy API. We recommend using the [Messages API](https://docs.anthropic.com/en/api/messages) going forward. Future models and features will not be compatible with Text Completions. See our [migration guide](https://docs.anthropic.com/en/api/migrating-from-text-completions-to-messages) for guidance in migrating from Text Completions to Messages. Args: max_tokens_to_sample: The maximum number of tokens to generate before stopping. Note that our models may stop _before_ reaching this maximum. This parameter only specifies the absolute maximum number of tokens to generate. model: The model that will complete your prompt.\n\nSee [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. prompt: The prompt that you want Claude to complete. For proper response generation you will need to format your prompt using alternating `\n\nHuman:` and `\n\nAssistant:` conversational turns. For example: ``` "\n\nHuman: {userQuestion}\n\nAssistant:" ``` See [prompt validation](https://docs.anthropic.com/en/api/prompt-validation) and our guide to [prompt design](https://docs.anthropic.com/en/docs/intro-to-prompting) for more details. stream: Whether to incrementally stream the response using server-sent events. See [streaming](https://docs.anthropic.com/en/api/streaming) for details. metadata: An object describing metadata about the request. stop_sequences: Sequences that will cause the model to stop generating. Our models stop on `"\n\nHuman:"`, and may include additional built-in stop sequences in the future. By providing the stop_sequences parameter, you may include additional strings that will cause the model to stop generating. temperature: Amount of randomness injected into the response. Defaults to `1.0`. Ranges from `0.0` to `1.0`. Use `temperature` closer to `0.0` for analytical / multiple choice, and closer to `1.0` for creative and generative tasks. Note that even with `temperature` of `0.0`, the results will not be fully deterministic. top_k: Only sample from the top K options for each subsequent token. Used to remove "long tail" low probability responses. [Learn more technical details here](https://towardsdatascience.com/how-to-sample-from-language-models-682bceb97277). Recommended for advanced use cases only. You usually only need to use `temperature`. top_p: Use nucleus sampling. In nucleus sampling, we compute the cumulative distribution over all the options for each subsequent token in decreasing probability order and cut it off once it reaches a particular probability specified by `top_p`. You should either alter `temperature` or `top_p`, but not both. Recommended for advanced use cases only. You usually only need to use `temperature`. extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds """ ... @required_args(["max_tokens_to_sample", "model", "prompt"], ["max_tokens_to_sample", "model", "prompt", "stream"]) async def create( self, *, max_tokens_to_sample: int, model: ModelParam, prompt: str, metadata: MetadataParam | NotGiven = NOT_GIVEN, stop_sequences: List[str] | NotGiven = NOT_GIVEN, stream: Literal[False] | Literal[True] | NotGiven = NOT_GIVEN, temperature: float | NotGiven = NOT_GIVEN, top_k: int | NotGiven = NOT_GIVEN, top_p: float | NotGiven = NOT_GIVEN, # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs. # The extra values given here take precedence over values defined on the client or passed to this method. extra_headers: Headers | None = None, extra_query: Query | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> Completion | AsyncStream[Completion]: if not is_given(timeout) and self._client.timeout == DEFAULT_TIMEOUT: timeout = 600 return await self._post( "/v1/complete", body=await async_maybe_transform( { "max_tokens_to_sample": max_tokens_to_sample, "model": model, "prompt": prompt, "metadata": metadata, "stop_sequences": stop_sequences, "stream": stream, "temperature": temperature, "top_k": top_k, "top_p": top_p, }, completion_create_params.CompletionCreateParams, ), options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout ), cast_to=Completion, stream=stream or False, stream_cls=AsyncStream[Completion], ) class CompletionsWithRawResponse: def __init__(self, completions: Completions) -> None: self._completions = completions self.create = _legacy_response.to_raw_response_wrapper( completions.create, ) class AsyncCompletionsWithRawResponse: def __init__(self, completions: AsyncCompletions) -> None: self._completions = completions self.create = _legacy_response.async_to_raw_response_wrapper( completions.create, ) class CompletionsWithStreamingResponse: def __init__(self, completions: Completions) -> None: self._completions = completions self.create = to_streamed_response_wrapper( completions.create, ) class AsyncCompletionsWithStreamingResponse: def __init__(self, completions: AsyncCompletions) -> None: self._completions = completions self.create = async_to_streamed_response_wrapper( completions.create, )