completions.py•36.6 kB
# 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 Body, Omit, Query, Headers, NotGiven, SequenceNotStr, omit, not_given
from .._utils import is_given, required_args, maybe_transform, strip_not_given, 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
from ..types.anthropic_beta_param import AnthropicBetaParam
__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 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 | Omit = omit,
stop_sequences: SequenceNotStr[str] | Omit = omit,
stream: Literal[False] | Omit = omit,
temperature: float | Omit = omit,
top_k: int | Omit = omit,
top_p: float | Omit = omit,
betas: List[AnthropicBetaParam] | Omit = omit,
# 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.claude.com/en/api/messages) going forward.
Future models and features will not be compatible with Text Completions. See our
[migration guide](https://docs.claude.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.claude.com/en/api/prompt-validation) and
our guide to [prompt design](https://docs.claude.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.claude.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`.
betas: Optional header to specify the beta version(s) you want to use.
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 | Omit = omit,
stop_sequences: SequenceNotStr[str] | Omit = omit,
temperature: float | Omit = omit,
top_k: int | Omit = omit,
top_p: float | Omit = omit,
betas: List[AnthropicBetaParam] | Omit = omit,
# 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.claude.com/en/api/messages) going forward.
Future models and features will not be compatible with Text Completions. See our
[migration guide](https://docs.claude.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.claude.com/en/api/prompt-validation) and
our guide to [prompt design](https://docs.claude.com/en/docs/intro-to-prompting)
for more details.
stream: Whether to incrementally stream the response using server-sent events.
See [streaming](https://docs.claude.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`.
betas: Optional header to specify the beta version(s) you want to use.
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 | Omit = omit,
stop_sequences: SequenceNotStr[str] | Omit = omit,
temperature: float | Omit = omit,
top_k: int | Omit = omit,
top_p: float | Omit = omit,
betas: List[AnthropicBetaParam] | Omit = omit,
# 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.claude.com/en/api/messages) going forward.
Future models and features will not be compatible with Text Completions. See our
[migration guide](https://docs.claude.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.claude.com/en/api/prompt-validation) and
our guide to [prompt design](https://docs.claude.com/en/docs/intro-to-prompting)
for more details.
stream: Whether to incrementally stream the response using server-sent events.
See [streaming](https://docs.claude.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`.
betas: Optional header to specify the beta version(s) you want to use.
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 | Omit = omit,
stop_sequences: SequenceNotStr[str] | Omit = omit,
stream: Literal[False] | Literal[True] | Omit = omit,
temperature: float | Omit = omit,
top_k: int | Omit = omit,
top_p: float | Omit = omit,
betas: List[AnthropicBetaParam] | Omit = omit,
# 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
extra_headers = {
**strip_not_given({"anthropic-beta": ",".join(str(e) for e in betas) if is_given(betas) else not_given}),
**(extra_headers or {}),
}
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.CompletionCreateParamsStreaming
if stream
else completion_create_params.CompletionCreateParamsNonStreaming,
),
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 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 | Omit = omit,
stop_sequences: SequenceNotStr[str] | Omit = omit,
stream: Literal[False] | Omit = omit,
temperature: float | Omit = omit,
top_k: int | Omit = omit,
top_p: float | Omit = omit,
betas: List[AnthropicBetaParam] | Omit = omit,
# 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.claude.com/en/api/messages) going forward.
Future models and features will not be compatible with Text Completions. See our
[migration guide](https://docs.claude.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.claude.com/en/api/prompt-validation) and
our guide to [prompt design](https://docs.claude.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.claude.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`.
betas: Optional header to specify the beta version(s) you want to use.
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 | Omit = omit,
stop_sequences: SequenceNotStr[str] | Omit = omit,
temperature: float | Omit = omit,
top_k: int | Omit = omit,
top_p: float | Omit = omit,
betas: List[AnthropicBetaParam] | Omit = omit,
# 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.claude.com/en/api/messages) going forward.
Future models and features will not be compatible with Text Completions. See our
[migration guide](https://docs.claude.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.claude.com/en/api/prompt-validation) and
our guide to [prompt design](https://docs.claude.com/en/docs/intro-to-prompting)
for more details.
stream: Whether to incrementally stream the response using server-sent events.
See [streaming](https://docs.claude.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`.
betas: Optional header to specify the beta version(s) you want to use.
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 | Omit = omit,
stop_sequences: SequenceNotStr[str] | Omit = omit,
temperature: float | Omit = omit,
top_k: int | Omit = omit,
top_p: float | Omit = omit,
betas: List[AnthropicBetaParam] | Omit = omit,
# 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.claude.com/en/api/messages) going forward.
Future models and features will not be compatible with Text Completions. See our
[migration guide](https://docs.claude.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.claude.com/en/api/prompt-validation) and
our guide to [prompt design](https://docs.claude.com/en/docs/intro-to-prompting)
for more details.
stream: Whether to incrementally stream the response using server-sent events.
See [streaming](https://docs.claude.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`.
betas: Optional header to specify the beta version(s) you want to use.
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 | Omit = omit,
stop_sequences: SequenceNotStr[str] | Omit = omit,
stream: Literal[False] | Literal[True] | Omit = omit,
temperature: float | Omit = omit,
top_k: int | Omit = omit,
top_p: float | Omit = omit,
betas: List[AnthropicBetaParam] | Omit = omit,
# 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
extra_headers = {
**strip_not_given({"anthropic-beta": ",".join(str(e) for e in betas) if is_given(betas) else not_given}),
**(extra_headers or {}),
}
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.CompletionCreateParamsStreaming
if stream
else completion_create_params.CompletionCreateParamsNonStreaming,
),
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,
)