lixinran
/
XinXiKuaiBaoYuan
2
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
XinXiKuaiBaoYuan/django-backend/venv/lib/python3.9/site-packages/openai/resources/completions.py

1172 lines
57 KiB
Python
Raw Normal View History

Initial commit: 知识采集分析Agent项目 - Django后端API服务 - Vue前端界面 - 集成王璞智能分析API - 任务管理和报告生成功能 - Element Plus UI组件 - 响应式布局设计
2025-10-14 07:47:56 +00:00
# File generated from our OpenAPI spec by Stainless.
from __future__ import annotations
from typing import TYPE_CHECKING, Dict, List, Union, Optional, overload
from typing_extensions import Literal
import httpx
from ..types import Completion, completion_create_params
from .._types import NOT_GIVEN, Body, Query, Headers, NotGiven
from .._utils import required_args, maybe_transform
from .._resource import SyncAPIResource, AsyncAPIResource
from .._response import to_raw_response_wrapper, async_to_raw_response_wrapper
from .._streaming import Stream, AsyncStream
from .._base_client import make_request_options
if TYPE_CHECKING:
from .._client import OpenAI, AsyncOpenAI
__all__ = ["Completions", "AsyncCompletions"]
class Completions(SyncAPIResource):
with_raw_response: CompletionsWithRawResponse
def __init__(self, client: OpenAI) -> None:
super().__init__(client)
self.with_raw_response = CompletionsWithRawResponse(self)
@overload
def create(
self,
*,
model: Union[
str,
Literal[
"babbage-002",
"davinci-002",
"gpt-3.5-turbo-instruct",
"text-davinci-003",
"text-davinci-002",
"text-davinci-001",
"code-davinci-002",
"text-curie-001",
"text-babbage-001",
"text-ada-001",
],
],
prompt: Union[str, List[str], List[int], List[List[int]], None],
best_of: Optional[int] | NotGiven = NOT_GIVEN,
echo: Optional[bool] | NotGiven = NOT_GIVEN,
frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
logprobs: Optional[int] | NotGiven = NOT_GIVEN,
max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
n: Optional[int] | NotGiven = NOT_GIVEN,
presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
seed: Optional[int] | NotGiven = NOT_GIVEN,
stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
stream: Optional[Literal[False]] | NotGiven = NOT_GIVEN,
suffix: Optional[str] | NotGiven = NOT_GIVEN,
temperature: Optional[float] | NotGiven = NOT_GIVEN,
top_p: Optional[float] | NotGiven = NOT_GIVEN,
user: str | 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:
"""
Creates a completion for the provided prompt and parameters.
Args:
model: ID of the model to use. You can use the
[List models](https://platform.openai.com/docs/api-reference/models/list) API to
see all of your available models, or see our
[Model overview](https://platform.openai.com/docs/models/overview) for
descriptions of them.
prompt: The prompt(s) to generate completions for, encoded as a string, array of
strings, array of tokens, or array of token arrays.
Note that <|endoftext|> is the document separator that the model sees during
training, so if a prompt is not specified the model will generate as if from the
beginning of a new document.
best_of: Generates `best_of` completions server-side and returns the "best" (the one with
the highest log probability per token). Results cannot be streamed.
When used with `n`, `best_of` controls the number of candidate completions and
`n` specifies how many to return – `best_of` must be greater than `n`.
**Note:** Because this parameter generates many completions, it can quickly
consume your token quota. Use carefully and ensure that you have reasonable
settings for `max_tokens` and `stop`.
echo: Echo back the prompt in addition to the completion
frequency_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on their
existing frequency in the text so far, decreasing the model's likelihood to
repeat the same line verbatim.
[See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/gpt/parameter-details)
logit_bias: Modify the likelihood of specified tokens appearing in the completion.
Accepts a JSON object that maps tokens (specified by their token ID in the GPT
tokenizer) to an associated bias value from -100 to 100. You can use this
[tokenizer tool](/tokenizer?view=bpe) (which works for both GPT-2 and GPT-3) to
convert text to token IDs. Mathematically, the bias is added to the logits
generated by the model prior to sampling. The exact effect will vary per model,
but values between -1 and 1 should decrease or increase likelihood of selection;
values like -100 or 100 should result in a ban or exclusive selection of the
relevant token.
As an example, you can pass `{"50256": -100}` to prevent the <|endoftext|> token
from being generated.
logprobs: Include the log probabilities on the `logprobs` most likely tokens, as well the
chosen tokens. For example, if `logprobs` is 5, the API will return a list of
the 5 most likely tokens. The API will always return the `logprob` of the
sampled token, so there may be up to `logprobs+1` elements in the response.
The maximum value for `logprobs` is 5.
max_tokens: The maximum number of [tokens](/tokenizer) to generate in the completion.
The token count of your prompt plus `max_tokens` cannot exceed the model's
context length.
[Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken)
for counting tokens.
n: How many completions to generate for each prompt.
**Note:** Because this parameter generates many completions, it can quickly
consume your token quota. Use carefully and ensure that you have reasonable
settings for `max_tokens` and `stop`.
presence_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on
whether they appear in the text so far, increasing the model's likelihood to
talk about new topics.
[See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/gpt/parameter-details)
seed: If specified, our system will make a best effort to sample deterministically,
such that repeated requests with the same `seed` and parameters should return
the same result.
Determinism is not guaranteed, and you should refer to the `system_fingerprint`
response parameter to monitor changes in the backend.
stop: Up to 4 sequences where the API will stop generating further tokens. The
returned text will not contain the stop sequence.
stream: Whether to stream back partial progress. If set, tokens will be sent as
data-only
[server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format)
as they become available, with the stream terminated by a `data: [DONE]`
message.
[Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions).
suffix: The suffix that comes after a completion of inserted text.
temperature: What sampling temperature to use, between 0 and 2. Higher values like 0.8 will
make the output more random, while lower values like 0.2 will make it more
focused and deterministic.
We generally recommend altering this or `top_p` but not both.
top_p: An alternative to sampling with temperature, called nucleus sampling, where the
model considers the results of the tokens with top_p probability mass. So 0.1
means only the tokens comprising the top 10% probability mass are considered.
We generally recommend altering this or `temperature` but not both.
user: A unique identifier representing your end-user, which can help OpenAI to monitor
and detect abuse.
[Learn more](https://platform.openai.com/docs/guides/safety-best-practices/end-user-ids).
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,
*,
model: Union[
str,
Literal[
"babbage-002",
"davinci-002",
"gpt-3.5-turbo-instruct",
"text-davinci-003",
"text-davinci-002",
"text-davinci-001",
"code-davinci-002",
"text-curie-001",
"text-babbage-001",
"text-ada-001",
],
],
prompt: Union[str, List[str], List[int], List[List[int]], None],
stream: Literal[True],
best_of: Optional[int] | NotGiven = NOT_GIVEN,
echo: Optional[bool] | NotGiven = NOT_GIVEN,
frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
logprobs: Optional[int] | NotGiven = NOT_GIVEN,
max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
n: Optional[int] | NotGiven = NOT_GIVEN,
presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
seed: Optional[int] | NotGiven = NOT_GIVEN,
stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
suffix: Optional[str] | NotGiven = NOT_GIVEN,
temperature: Optional[float] | NotGiven = NOT_GIVEN,
top_p: Optional[float] | NotGiven = NOT_GIVEN,
user: str | 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]:
"""
Creates a completion for the provided prompt and parameters.
Args:
model: ID of the model to use. You can use the
[List models](https://platform.openai.com/docs/api-reference/models/list) API to
see all of your available models, or see our
[Model overview](https://platform.openai.com/docs/models/overview) for
descriptions of them.
prompt: The prompt(s) to generate completions for, encoded as a string, array of
strings, array of tokens, or array of token arrays.
Note that <|endoftext|> is the document separator that the model sees during
training, so if a prompt is not specified the model will generate as if from the
beginning of a new document.
stream: Whether to stream back partial progress. If set, tokens will be sent as
data-only
[server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format)
as they become available, with the stream terminated by a `data: [DONE]`
message.
[Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions).
best_of: Generates `best_of` completions server-side and returns the "best" (the one with
the highest log probability per token). Results cannot be streamed.
When used with `n`, `best_of` controls the number of candidate completions and
`n` specifies how many to return – `best_of` must be greater than `n`.
**Note:** Because this parameter generates many completions, it can quickly
consume your token quota. Use carefully and ensure that you have reasonable
settings for `max_tokens` and `stop`.
echo: Echo back the prompt in addition to the completion
frequency_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on their
existing frequency in the text so far, decreasing the model's likelihood to
repeat the same line verbatim.
[See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/gpt/parameter-details)
logit_bias: Modify the likelihood of specified tokens appearing in the completion.
Accepts a JSON object that maps tokens (specified by their token ID in the GPT
tokenizer) to an associated bias value from -100 to 100. You can use this
[tokenizer tool](/tokenizer?view=bpe) (which works for both GPT-2 and GPT-3) to
convert text to token IDs. Mathematically, the bias is added to the logits
generated by the model prior to sampling. The exact effect will vary per model,
but values between -1 and 1 should decrease or increase likelihood of selection;
values like -100 or 100 should result in a ban or exclusive selection of the
relevant token.
As an example, you can pass `{"50256": -100}` to prevent the <|endoftext|> token
from being generated.
logprobs: Include the log probabilities on the `logprobs` most likely tokens, as well the
chosen tokens. For example, if `logprobs` is 5, the API will return a list of
the 5 most likely tokens. The API will always return the `logprob` of the
sampled token, so there may be up to `logprobs+1` elements in the response.
The maximum value for `logprobs` is 5.
max_tokens: The maximum number of [tokens](/tokenizer) to generate in the completion.
The token count of your prompt plus `max_tokens` cannot exceed the model's
context length.
[Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken)
for counting tokens.
n: How many completions to generate for each prompt.
**Note:** Because this parameter generates many completions, it can quickly
consume your token quota. Use carefully and ensure that you have reasonable
settings for `max_tokens` and `stop`.
presence_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on
whether they appear in the text so far, increasing the model's likelihood to
talk about new topics.
[See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/gpt/parameter-details)
seed: If specified, our system will make a best effort to sample deterministically,
such that repeated requests with the same `seed` and parameters should return
the same result.
Determinism is not guaranteed, and you should refer to the `system_fingerprint`
response parameter to monitor changes in the backend.
stop: Up to 4 sequences where the API will stop generating further tokens. The
returned text will not contain the stop sequence.
suffix: The suffix that comes after a completion of inserted text.
temperature: What sampling temperature to use, between 0 and 2. Higher values like 0.8 will
make the output more random, while lower values like 0.2 will make it more
focused and deterministic.
We generally recommend altering this or `top_p` but not both.
top_p: An alternative to sampling with temperature, called nucleus sampling, where the
model considers the results of the tokens with top_p probability mass. So 0.1
means only the tokens comprising the top 10% probability mass are considered.
We generally recommend altering this or `temperature` but not both.
user: A unique identifier representing your end-user, which can help OpenAI to monitor
and detect abuse.
[Learn more](https://platform.openai.com/docs/guides/safety-best-practices/end-user-ids).
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,
*,
model: Union[
str,
Literal[
"babbage-002",
"davinci-002",
"gpt-3.5-turbo-instruct",
"text-davinci-003",
"text-davinci-002",
"text-davinci-001",
"code-davinci-002",
"text-curie-001",
"text-babbage-001",
"text-ada-001",
],
],
prompt: Union[str, List[str], List[int], List[List[int]], None],
stream: bool,
best_of: Optional[int] | NotGiven = NOT_GIVEN,
echo: Optional[bool] | NotGiven = NOT_GIVEN,
frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
logprobs: Optional[int] | NotGiven = NOT_GIVEN,
max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
n: Optional[int] | NotGiven = NOT_GIVEN,
presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
seed: Optional[int] | NotGiven = NOT_GIVEN,
stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
suffix: Optional[str] | NotGiven = NOT_GIVEN,
temperature: Optional[float] | NotGiven = NOT_GIVEN,
top_p: Optional[float] | NotGiven = NOT_GIVEN,
user: str | 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]:
"""
Creates a completion for the provided prompt and parameters.
Args:
model: ID of the model to use. You can use the
[List models](https://platform.openai.com/docs/api-reference/models/list) API to
see all of your available models, or see our
[Model overview](https://platform.openai.com/docs/models/overview) for
descriptions of them.
prompt: The prompt(s) to generate completions for, encoded as a string, array of
strings, array of tokens, or array of token arrays.
Note that <|endoftext|> is the document separator that the model sees during
training, so if a prompt is not specified the model will generate as if from the
beginning of a new document.
stream: Whether to stream back partial progress. If set, tokens will be sent as
data-only
[server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format)
as they become available, with the stream terminated by a `data: [DONE]`
message.
[Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions).
best_of: Generates `best_of` completions server-side and returns the "best" (the one with
the highest log probability per token). Results cannot be streamed.
When used with `n`, `best_of` controls the number of candidate completions and
`n` specifies how many to return – `best_of` must be greater than `n`.
**Note:** Because this parameter generates many completions, it can quickly
consume your token quota. Use carefully and ensure that you have reasonable
settings for `max_tokens` and `stop`.
echo: Echo back the prompt in addition to the completion
frequency_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on their
existing frequency in the text so far, decreasing the model's likelihood to
repeat the same line verbatim.
[See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/gpt/parameter-details)
logit_bias: Modify the likelihood of specified tokens appearing in the completion.
Accepts a JSON object that maps tokens (specified by their token ID in the GPT
tokenizer) to an associated bias value from -100 to 100. You can use this
[tokenizer tool](/tokenizer?view=bpe) (which works for both GPT-2 and GPT-3) to
convert text to token IDs. Mathematically, the bias is added to the logits
generated by the model prior to sampling. The exact effect will vary per model,
but values between -1 and 1 should decrease or increase likelihood of selection;
values like -100 or 100 should result in a ban or exclusive selection of the
relevant token.
As an example, you can pass `{"50256": -100}` to prevent the <|endoftext|> token
from being generated.
logprobs: Include the log probabilities on the `logprobs` most likely tokens, as well the
chosen tokens. For example, if `logprobs` is 5, the API will return a list of
the 5 most likely tokens. The API will always return the `logprob` of the
sampled token, so there may be up to `logprobs+1` elements in the response.
The maximum value for `logprobs` is 5.
max_tokens: The maximum number of [tokens](/tokenizer) to generate in the completion.
The token count of your prompt plus `max_tokens` cannot exceed the model's
context length.
[Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken)
for counting tokens.
n: How many completions to generate for each prompt.
**Note:** Because this parameter generates many completions, it can quickly
consume your token quota. Use carefully and ensure that you have reasonable
settings for `max_tokens` and `stop`.
presence_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on
whether they appear in the text so far, increasing the model's likelihood to
talk about new topics.
[See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/gpt/parameter-details)
seed: If specified, our system will make a best effort to sample deterministically,
such that repeated requests with the same `seed` and parameters should return
the same result.
Determinism is not guaranteed, and you should refer to the `system_fingerprint`
response parameter to monitor changes in the backend.
stop: Up to 4 sequences where the API will stop generating further tokens. The
returned text will not contain the stop sequence.
suffix: The suffix that comes after a completion of inserted text.
temperature: What sampling temperature to use, between 0 and 2. Higher values like 0.8 will
make the output more random, while lower values like 0.2 will make it more
focused and deterministic.
We generally recommend altering this or `top_p` but not both.
top_p: An alternative to sampling with temperature, called nucleus sampling, where the
model considers the results of the tokens with top_p probability mass. So 0.1
means only the tokens comprising the top 10% probability mass are considered.
We generally recommend altering this or `temperature` but not both.
user: A unique identifier representing your end-user, which can help OpenAI to monitor
and detect abuse.
[Learn more](https://platform.openai.com/docs/guides/safety-best-practices/end-user-ids).
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(["model", "prompt"], ["model", "prompt", "stream"])
def create(
self,
*,
model: Union[
str,
Literal[
"babbage-002",
"davinci-002",
"gpt-3.5-turbo-instruct",
"text-davinci-003",
"text-davinci-002",
"text-davinci-001",
"code-davinci-002",
"text-curie-001",
"text-babbage-001",
"text-ada-001",
],
],
prompt: Union[str, List[str], List[int], List[List[int]], None],
best_of: Optional[int] | NotGiven = NOT_GIVEN,
echo: Optional[bool] | NotGiven = NOT_GIVEN,
frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
logprobs: Optional[int] | NotGiven = NOT_GIVEN,
max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
n: Optional[int] | NotGiven = NOT_GIVEN,
presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
seed: Optional[int] | NotGiven = NOT_GIVEN,
stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
stream: Optional[Literal[False]] | Literal[True] | NotGiven = NOT_GIVEN,
suffix: Optional[str] | NotGiven = NOT_GIVEN,
temperature: Optional[float] | NotGiven = NOT_GIVEN,
top_p: Optional[float] | NotGiven = NOT_GIVEN,
user: str | 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]:
return self._post(
"/completions",
body=maybe_transform(
{
"model": model,
"prompt": prompt,
"best_of": best_of,
"echo": echo,
"frequency_penalty": frequency_penalty,
"logit_bias": logit_bias,
"logprobs": logprobs,
"max_tokens": max_tokens,
"n": n,
"presence_penalty": presence_penalty,
"seed": seed,
"stop": stop,
"stream": stream,
"suffix": suffix,
"temperature": temperature,
"top_p": top_p,
"user": user,
},
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):
with_raw_response: AsyncCompletionsWithRawResponse
def __init__(self, client: AsyncOpenAI) -> None:
super().__init__(client)
self.with_raw_response = AsyncCompletionsWithRawResponse(self)
@overload
async def create(
self,
*,
model: Union[
str,
Literal[
"babbage-002",
"davinci-002",
"gpt-3.5-turbo-instruct",
"text-davinci-003",
"text-davinci-002",
"text-davinci-001",
"code-davinci-002",
"text-curie-001",
"text-babbage-001",
"text-ada-001",
],
],
prompt: Union[str, List[str], List[int], List[List[int]], None],
best_of: Optional[int] | NotGiven = NOT_GIVEN,
echo: Optional[bool] | NotGiven = NOT_GIVEN,
frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
logprobs: Optional[int] | NotGiven = NOT_GIVEN,
max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
n: Optional[int] | NotGiven = NOT_GIVEN,
presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
seed: Optional[int] | NotGiven = NOT_GIVEN,
stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
stream: Optional[Literal[False]] | NotGiven = NOT_GIVEN,
suffix: Optional[str] | NotGiven = NOT_GIVEN,
temperature: Optional[float] | NotGiven = NOT_GIVEN,
top_p: Optional[float] | NotGiven = NOT_GIVEN,
user: str | 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:
"""
Creates a completion for the provided prompt and parameters.
Args:
model: ID of the model to use. You can use the
[List models](https://platform.openai.com/docs/api-reference/models/list) API to
see all of your available models, or see our
[Model overview](https://platform.openai.com/docs/models/overview) for
descriptions of them.
prompt: The prompt(s) to generate completions for, encoded as a string, array of
strings, array of tokens, or array of token arrays.
Note that <|endoftext|> is the document separator that the model sees during
training, so if a prompt is not specified the model will generate as if from the
beginning of a new document.
best_of: Generates `best_of` completions server-side and returns the "best" (the one with
the highest log probability per token). Results cannot be streamed.
When used with `n`, `best_of` controls the number of candidate completions and
`n` specifies how many to return – `best_of` must be greater than `n`.
**Note:** Because this parameter generates many completions, it can quickly
consume your token quota. Use carefully and ensure that you have reasonable
settings for `max_tokens` and `stop`.
echo: Echo back the prompt in addition to the completion
frequency_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on their
existing frequency in the text so far, decreasing the model's likelihood to
repeat the same line verbatim.
[See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/gpt/parameter-details)
logit_bias: Modify the likelihood of specified tokens appearing in the completion.
Accepts a JSON object that maps tokens (specified by their token ID in the GPT
tokenizer) to an associated bias value from -100 to 100. You can use this
[tokenizer tool](/tokenizer?view=bpe) (which works for both GPT-2 and GPT-3) to
convert text to token IDs. Mathematically, the bias is added to the logits
generated by the model prior to sampling. The exact effect will vary per model,
but values between -1 and 1 should decrease or increase likelihood of selection;
values like -100 or 100 should result in a ban or exclusive selection of the
relevant token.
As an example, you can pass `{"50256": -100}` to prevent the <|endoftext|> token
from being generated.
logprobs: Include the log probabilities on the `logprobs` most likely tokens, as well the
chosen tokens. For example, if `logprobs` is 5, the API will return a list of
the 5 most likely tokens. The API will always return the `logprob` of the
sampled token, so there may be up to `logprobs+1` elements in the response.
The maximum value for `logprobs` is 5.
max_tokens: The maximum number of [tokens](/tokenizer) to generate in the completion.
The token count of your prompt plus `max_tokens` cannot exceed the model's
context length.
[Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken)
for counting tokens.
n: How many completions to generate for each prompt.
**Note:** Because this parameter generates many completions, it can quickly
consume your token quota. Use carefully and ensure that you have reasonable
settings for `max_tokens` and `stop`.
presence_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on
whether they appear in the text so far, increasing the model's likelihood to
talk about new topics.
[See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/gpt/parameter-details)
seed: If specified, our system will make a best effort to sample deterministically,
such that repeated requests with the same `seed` and parameters should return
the same result.
Determinism is not guaranteed, and you should refer to the `system_fingerprint`
response parameter to monitor changes in the backend.
stop: Up to 4 sequences where the API will stop generating further tokens. The
returned text will not contain the stop sequence.
stream: Whether to stream back partial progress. If set, tokens will be sent as
data-only
[server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format)
as they become available, with the stream terminated by a `data: [DONE]`
message.
[Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions).
suffix: The suffix that comes after a completion of inserted text.
temperature: What sampling temperature to use, between 0 and 2. Higher values like 0.8 will
make the output more random, while lower values like 0.2 will make it more
focused and deterministic.
We generally recommend altering this or `top_p` but not both.
top_p: An alternative to sampling with temperature, called nucleus sampling, where the
model considers the results of the tokens with top_p probability mass. So 0.1
means only the tokens comprising the top 10% probability mass are considered.
We generally recommend altering this or `temperature` but not both.
user: A unique identifier representing your end-user, which can help OpenAI to monitor
and detect abuse.
[Learn more](https://platform.openai.com/docs/guides/safety-best-practices/end-user-ids).
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,
*,
model: Union[
str,
Literal[
"babbage-002",
"davinci-002",
"gpt-3.5-turbo-instruct",
"text-davinci-003",
"text-davinci-002",
"text-davinci-001",
"code-davinci-002",
"text-curie-001",
"text-babbage-001",
"text-ada-001",
],
],
prompt: Union[str, List[str], List[int], List[List[int]], None],
stream: Literal[True],
best_of: Optional[int] | NotGiven = NOT_GIVEN,
echo: Optional[bool] | NotGiven = NOT_GIVEN,
frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
logprobs: Optional[int] | NotGiven = NOT_GIVEN,
max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
n: Optional[int] | NotGiven = NOT_GIVEN,
presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
seed: Optional[int] | NotGiven = NOT_GIVEN,
stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
suffix: Optional[str] | NotGiven = NOT_GIVEN,
temperature: Optional[float] | NotGiven = NOT_GIVEN,
top_p: Optional[float] | NotGiven = NOT_GIVEN,
user: str | 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]:
"""
Creates a completion for the provided prompt and parameters.
Args:
model: ID of the model to use. You can use the
[List models](https://platform.openai.com/docs/api-reference/models/list) API to
see all of your available models, or see our
[Model overview](https://platform.openai.com/docs/models/overview) for
descriptions of them.
prompt: The prompt(s) to generate completions for, encoded as a string, array of
strings, array of tokens, or array of token arrays.
Note that <|endoftext|> is the document separator that the model sees during
training, so if a prompt is not specified the model will generate as if from the
beginning of a new document.
stream: Whether to stream back partial progress. If set, tokens will be sent as
data-only
[server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format)
as they become available, with the stream terminated by a `data: [DONE]`
message.
[Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions).
best_of: Generates `best_of` completions server-side and returns the "best" (the one with
the highest log probability per token). Results cannot be streamed.
When used with `n`, `best_of` controls the number of candidate completions and
`n` specifies how many to return – `best_of` must be greater than `n`.
**Note:** Because this parameter generates many completions, it can quickly
consume your token quota. Use carefully and ensure that you have reasonable
settings for `max_tokens` and `stop`.
echo: Echo back the prompt in addition to the completion
frequency_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on their
existing frequency in the text so far, decreasing the model's likelihood to
repeat the same line verbatim.
[See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/gpt/parameter-details)
logit_bias: Modify the likelihood of specified tokens appearing in the completion.
Accepts a JSON object that maps tokens (specified by their token ID in the GPT
tokenizer) to an associated bias value from -100 to 100. You can use this
[tokenizer tool](/tokenizer?view=bpe) (which works for both GPT-2 and GPT-3) to
convert text to token IDs. Mathematically, the bias is added to the logits
generated by the model prior to sampling. The exact effect will vary per model,
but values between -1 and 1 should decrease or increase likelihood of selection;
values like -100 or 100 should result in a ban or exclusive selection of the
relevant token.
As an example, you can pass `{"50256": -100}` to prevent the <|endoftext|> token
from being generated.
logprobs: Include the log probabilities on the `logprobs` most likely tokens, as well the
chosen tokens. For example, if `logprobs` is 5, the API will return a list of
the 5 most likely tokens. The API will always return the `logprob` of the
sampled token, so there may be up to `logprobs+1` elements in the response.
The maximum value for `logprobs` is 5.
max_tokens: The maximum number of [tokens](/tokenizer) to generate in the completion.
The token count of your prompt plus `max_tokens` cannot exceed the model's
context length.
[Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken)
for counting tokens.
n: How many completions to generate for each prompt.
**Note:** Because this parameter generates many completions, it can quickly
consume your token quota. Use carefully and ensure that you have reasonable
settings for `max_tokens` and `stop`.
presence_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on
whether they appear in the text so far, increasing the model's likelihood to
talk about new topics.
[See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/gpt/parameter-details)
seed: If specified, our system will make a best effort to sample deterministically,
such that repeated requests with the same `seed` and parameters should return
the same result.
Determinism is not guaranteed, and you should refer to the `system_fingerprint`
response parameter to monitor changes in the backend.
stop: Up to 4 sequences where the API will stop generating further tokens. The
returned text will not contain the stop sequence.
suffix: The suffix that comes after a completion of inserted text.
temperature: What sampling temperature to use, between 0 and 2. Higher values like 0.8 will
make the output more random, while lower values like 0.2 will make it more
focused and deterministic.
We generally recommend altering this or `top_p` but not both.
top_p: An alternative to sampling with temperature, called nucleus sampling, where the
model considers the results of the tokens with top_p probability mass. So 0.1
means only the tokens comprising the top 10% probability mass are considered.
We generally recommend altering this or `temperature` but not both.
user: A unique identifier representing your end-user, which can help OpenAI to monitor
and detect abuse.
[Learn more](https://platform.openai.com/docs/guides/safety-best-practices/end-user-ids).
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,
*,
model: Union[
str,
Literal[
"babbage-002",
"davinci-002",
"gpt-3.5-turbo-instruct",
"text-davinci-003",
"text-davinci-002",
"text-davinci-001",
"code-davinci-002",
"text-curie-001",
"text-babbage-001",
"text-ada-001",
],
],
prompt: Union[str, List[str], List[int], List[List[int]], None],
stream: bool,
best_of: Optional[int] | NotGiven = NOT_GIVEN,
echo: Optional[bool] | NotGiven = NOT_GIVEN,
frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
logprobs: Optional[int] | NotGiven = NOT_GIVEN,
max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
n: Optional[int] | NotGiven = NOT_GIVEN,
presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
seed: Optional[int] | NotGiven = NOT_GIVEN,
stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
suffix: Optional[str] | NotGiven = NOT_GIVEN,
temperature: Optional[float] | NotGiven = NOT_GIVEN,
top_p: Optional[float] | NotGiven = NOT_GIVEN,
user: str | 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]:
"""
Creates a completion for the provided prompt and parameters.
Args:
model: ID of the model to use. You can use the
[List models](https://platform.openai.com/docs/api-reference/models/list) API to
see all of your available models, or see our
[Model overview](https://platform.openai.com/docs/models/overview) for
descriptions of them.
prompt: The prompt(s) to generate completions for, encoded as a string, array of
strings, array of tokens, or array of token arrays.
Note that <|endoftext|> is the document separator that the model sees during
training, so if a prompt is not specified the model will generate as if from the
beginning of a new document.
stream: Whether to stream back partial progress. If set, tokens will be sent as
data-only
[server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format)
as they become available, with the stream terminated by a `data: [DONE]`
message.
[Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions).
best_of: Generates `best_of` completions server-side and returns the "best" (the one with
the highest log probability per token). Results cannot be streamed.
When used with `n`, `best_of` controls the number of candidate completions and
`n` specifies how many to return – `best_of` must be greater than `n`.
**Note:** Because this parameter generates many completions, it can quickly
consume your token quota. Use carefully and ensure that you have reasonable
settings for `max_tokens` and `stop`.
echo: Echo back the prompt in addition to the completion
frequency_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on their
existing frequency in the text so far, decreasing the model's likelihood to
repeat the same line verbatim.
[See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/gpt/parameter-details)
logit_bias: Modify the likelihood of specified tokens appearing in the completion.
Accepts a JSON object that maps tokens (specified by their token ID in the GPT
tokenizer) to an associated bias value from -100 to 100. You can use this
[tokenizer tool](/tokenizer?view=bpe) (which works for both GPT-2 and GPT-3) to
convert text to token IDs. Mathematically, the bias is added to the logits
generated by the model prior to sampling. The exact effect will vary per model,
but values between -1 and 1 should decrease or increase likelihood of selection;
values like -100 or 100 should result in a ban or exclusive selection of the
relevant token.
As an example, you can pass `{"50256": -100}` to prevent the <|endoftext|> token
from being generated.
logprobs: Include the log probabilities on the `logprobs` most likely tokens, as well the
chosen tokens. For example, if `logprobs` is 5, the API will return a list of
the 5 most likely tokens. The API will always return the `logprob` of the
sampled token, so there may be up to `logprobs+1` elements in the response.
The maximum value for `logprobs` is 5.
max_tokens: The maximum number of [tokens](/tokenizer) to generate in the completion.
The token count of your prompt plus `max_tokens` cannot exceed the model's
context length.
[Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken)
for counting tokens.
n: How many completions to generate for each prompt.
**Note:** Because this parameter generates many completions, it can quickly
consume your token quota. Use carefully and ensure that you have reasonable
settings for `max_tokens` and `stop`.
presence_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on
whether they appear in the text so far, increasing the model's likelihood to
talk about new topics.
[See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/gpt/parameter-details)
seed: If specified, our system will make a best effort to sample deterministically,
such that repeated requests with the same `seed` and parameters should return
the same result.
Determinism is not guaranteed, and you should refer to the `system_fingerprint`
response parameter to monitor changes in the backend.
stop: Up to 4 sequences where the API will stop generating further tokens. The
returned text will not contain the stop sequence.
suffix: The suffix that comes after a completion of inserted text.
temperature: What sampling temperature to use, between 0 and 2. Higher values like 0.8 will
make the output more random, while lower values like 0.2 will make it more
focused and deterministic.
We generally recommend altering this or `top_p` but not both.
top_p: An alternative to sampling with temperature, called nucleus sampling, where the
model considers the results of the tokens with top_p probability mass. So 0.1
means only the tokens comprising the top 10% probability mass are considered.
We generally recommend altering this or `temperature` but not both.
user: A unique identifier representing your end-user, which can help OpenAI to monitor
and detect abuse.
[Learn more](https://platform.openai.com/docs/guides/safety-best-practices/end-user-ids).
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(["model", "prompt"], ["model", "prompt", "stream"])
async def create(
self,
*,
model: Union[
str,
Literal[
"babbage-002",
"davinci-002",
"gpt-3.5-turbo-instruct",
"text-davinci-003",
"text-davinci-002",
"text-davinci-001",
"code-davinci-002",
"text-curie-001",
"text-babbage-001",
"text-ada-001",
],
],
prompt: Union[str, List[str], List[int], List[List[int]], None],
best_of: Optional[int] | NotGiven = NOT_GIVEN,
echo: Optional[bool] | NotGiven = NOT_GIVEN,
frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
logprobs: Optional[int] | NotGiven = NOT_GIVEN,
max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
n: Optional[int] | NotGiven = NOT_GIVEN,
presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
seed: Optional[int] | NotGiven = NOT_GIVEN,
stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
stream: Optional[Literal[False]] | Literal[True] | NotGiven = NOT_GIVEN,
suffix: Optional[str] | NotGiven = NOT_GIVEN,
temperature: Optional[float] | NotGiven = NOT_GIVEN,
top_p: Optional[float] | NotGiven = NOT_GIVEN,
user: str | 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]:
return await self._post(
"/completions",
body=maybe_transform(
{
"model": model,
"prompt": prompt,
"best_of": best_of,
"echo": echo,
"frequency_penalty": frequency_penalty,
"logit_bias": logit_bias,
"logprobs": logprobs,
"max_tokens": max_tokens,
"n": n,
"presence_penalty": presence_penalty,
"seed": seed,
"stop": stop,
"stream": stream,
"suffix": suffix,
"temperature": temperature,
"top_p": top_p,
"user": user,
},
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.create = to_raw_response_wrapper(
completions.create,
)
class AsyncCompletionsWithRawResponse:
def __init__(self, completions: AsyncCompletions) -> None:
self.create = async_to_raw_response_wrapper(
completions.create,
)