completions.py

# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.

from __future__ import annotations

import inspect
from typing import Dict, List, Union, Iterable, Optional, overload
from typing_extensions import Literal

import httpx
import pydantic

from ... import _legacy_response
from ..._types import NOT_GIVEN, Body, Query, Headers, NotGiven
from ..._utils import (
    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 ..._streaming import Stream, AsyncStream
from ...types.chat import completion_create_params
from ..._base_client import make_request_options
from ...types.chat_model import ChatModel
from ...types.chat.chat_completion import ChatCompletion
from ...types.chat.chat_completion_chunk import ChatCompletionChunk
from ...types.chat.chat_completion_tool_param import ChatCompletionToolParam
from ...types.chat.chat_completion_message_param import ChatCompletionMessageParam
from ...types.chat.chat_completion_stream_options_param import ChatCompletionStreamOptionsParam
from ...types.chat.chat_completion_tool_choice_option_param import ChatCompletionToolChoiceOptionParam

__all__ = ["Completions", "AsyncCompletions"]


class Completions(SyncAPIResource):
    @cached_property
    def with_raw_response(self) -> CompletionsWithRawResponse:
        return CompletionsWithRawResponse(self)

    @cached_property
    def with_streaming_response(self) -> CompletionsWithStreamingResponse:
        return CompletionsWithStreamingResponse(self)

    @overload
    def create(
        self,
        *,
        messages: Iterable[ChatCompletionMessageParam],
        model: Union[str, ChatModel],
        frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
        function_call: completion_create_params.FunctionCall | NotGiven = NOT_GIVEN,
        functions: Iterable[completion_create_params.Function] | NotGiven = NOT_GIVEN,
        logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
        logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
        max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
        n: Optional[int] | NotGiven = NOT_GIVEN,
        parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
        presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
        response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
        seed: Optional[int] | NotGiven = NOT_GIVEN,
        service_tier: Optional[Literal["auto", "default"]] | NotGiven = NOT_GIVEN,
        stop: Union[Optional[str], List[str]] | NotGiven = NOT_GIVEN,
        stream: Optional[Literal[False]] | NotGiven = NOT_GIVEN,
        stream_options: Optional[ChatCompletionStreamOptionsParam] | NotGiven = NOT_GIVEN,
        temperature: Optional[float] | NotGiven = NOT_GIVEN,
        tool_choice: ChatCompletionToolChoiceOptionParam | NotGiven = NOT_GIVEN,
        tools: Iterable[ChatCompletionToolParam] | NotGiven = NOT_GIVEN,
        top_logprobs: Optional[int] | 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,
    ) -> ChatCompletion:
        """
        Creates a model response for the given chat conversation.

        Args:
          messages: A list of messages comprising the conversation so far.
              [Example Python code](https://cookbook.openai.com/examples/how_to_format_inputs_to_chatgpt_models).

          model: ID of the model to use. See the
              [model endpoint compatibility](https://platform.openai.com/docs/models/model-endpoint-compatibility)
              table for details on which models work with the Chat API.

          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/text-generation/parameter-details)

          function_call: Deprecated in favor of `tool_choice`.

              Controls which (if any) function is called by the model. `none` means the model
              will not call a function and instead generates a message. `auto` means the model
              can pick between generating a message or calling a function. Specifying a
              particular function via `{"name": "my_function"}` forces the model to call that
              function.

              `none` is the default when no functions are present. `auto` is the default if
              functions are present.

          functions: Deprecated in favor of `tools`.

              A list of functions the model may generate JSON inputs for.

          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
              tokenizer) to an associated bias value from -100 to 100. 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.

          logprobs: Whether to return log probabilities of the output tokens or not. If true,
              returns the log probabilities of each output token returned in the `content` of
              `message`.

          max_tokens: The maximum number of [tokens](/tokenizer) that can be generated in the chat
              completion.

              The total length of input tokens and generated tokens is limited by 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 chat completion choices to generate for each input message. Note that
              you will be charged based on the number of generated tokens across all of the
              choices. Keep `n` as `1` to minimize costs.

          parallel_tool_calls: Whether to enable
              [parallel function calling](https://platform.openai.com/docs/guides/function-calling/parallel-function-calling)
              during tool use.

          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/text-generation/parameter-details)

          response_format: An object specifying the format that the model must output. Compatible with
              [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
              [GPT-4o mini](https://platform.openai.com/docs/models/gpt-4o-mini),
              [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo) and
              all GPT-3.5 Turbo models newer than `gpt-3.5-turbo-1106`.

              Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
              Outputs which guarantees the model will match your supplied JSON schema. Learn
              more in the
              [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).

              Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
              message the model generates is valid JSON.

              **Important:** when using JSON mode, you **must** also instruct the model to
              produce JSON yourself via a system or user message. Without this, the model may
              generate an unending stream of whitespace until the generation reaches the token
              limit, resulting in a long-running and seemingly "stuck" request. Also note that
              the message content may be partially cut off if `finish_reason="length"`, which
              indicates the generation exceeded `max_tokens` or the conversation exceeded the
              max context length.

          seed: This feature is in Beta. 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.

          service_tier: Specifies the latency tier to use for processing the request. This parameter is
              relevant for customers subscribed to the scale tier service:

              - If set to 'auto', the system will utilize scale tier credits until they are
                exhausted.
              - If set to 'default', the request will be processed using the default service
                tier with a lower uptime SLA and no latency guarentee.
              - When not set, the default behavior is 'auto'.

              When this parameter is set, the response body will include the `service_tier`
              utilized.

          stop: Up to 4 sequences where the API will stop generating further tokens.

          stream: If set, partial message deltas will be sent, like in ChatGPT. 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).

          stream_options: Options for streaming response. Only set this when you set `stream: true`.

          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.

          tool_choice: Controls which (if any) tool is called by the model. `none` means the model will
              not call any tool and instead generates a message. `auto` means the model can
              pick between generating a message or calling one or more tools. `required` means
              the model must call one or more tools. Specifying a particular tool via
              `{"type": "function", "function": {"name": "my_function"}}` forces the model to
              call that tool.

              `none` is the default when no tools are present. `auto` is the default if tools
              are present.

          tools: A list of tools the model may call. Currently, only functions are supported as a
              tool. Use this to provide a list of functions the model may generate JSON inputs
              for. A max of 128 functions are supported.

          top_logprobs: An integer between 0 and 20 specifying the number of most likely tokens to
              return at each token position, each with an associated log probability.
              `logprobs` must be set to `true` if this parameter is used.

          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,
        *,
        messages: Iterable[ChatCompletionMessageParam],
        model: Union[str, ChatModel],
        stream: Literal[True],
        frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
        function_call: completion_create_params.FunctionCall | NotGiven = NOT_GIVEN,
        functions: Iterable[completion_create_params.Function] | NotGiven = NOT_GIVEN,
        logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
        logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
        max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
        n: Optional[int] | NotGiven = NOT_GIVEN,
        parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
        presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
        response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
        seed: Optional[int] | NotGiven = NOT_GIVEN,
        service_tier: Optional[Literal["auto", "default"]] | NotGiven = NOT_GIVEN,
        stop: Union[Optional[str], List[str]] | NotGiven = NOT_GIVEN,
        stream_options: Optional[ChatCompletionStreamOptionsParam] | NotGiven = NOT_GIVEN,
        temperature: Optional[float] | NotGiven = NOT_GIVEN,
        tool_choice: ChatCompletionToolChoiceOptionParam | NotGiven = NOT_GIVEN,
        tools: Iterable[ChatCompletionToolParam] | NotGiven = NOT_GIVEN,
        top_logprobs: Optional[int] | 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[ChatCompletionChunk]:
        """
        Creates a model response for the given chat conversation.

        Args:
          messages: A list of messages comprising the conversation so far.
              [Example Python code](https://cookbook.openai.com/examples/how_to_format_inputs_to_chatgpt_models).

          model: ID of the model to use. See the
              [model endpoint compatibility](https://platform.openai.com/docs/models/model-endpoint-compatibility)
              table for details on which models work with the Chat API.

          stream: If set, partial message deltas will be sent, like in ChatGPT. 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).

          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/text-generation/parameter-details)

          function_call: Deprecated in favor of `tool_choice`.

              Controls which (if any) function is called by the model. `none` means the model
              will not call a function and instead generates a message. `auto` means the model
              can pick between generating a message or calling a function. Specifying a
              particular function via `{"name": "my_function"}` forces the model to call that
              function.

              `none` is the default when no functions are present. `auto` is the default if
              functions are present.

          functions: Deprecated in favor of `tools`.

              A list of functions the model may generate JSON inputs for.

          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
              tokenizer) to an associated bias value from -100 to 100. 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.

          logprobs: Whether to return log probabilities of the output tokens or not. If true,
              returns the log probabilities of each output token returned in the `content` of
              `message`.

          max_tokens: The maximum number of [tokens](/tokenizer) that can be generated in the chat
              completion.

              The total length of input tokens and generated tokens is limited by 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 chat completion choices to generate for each input message. Note that
              you will be charged based on the number of generated tokens across all of the
              choices. Keep `n` as `1` to minimize costs.

          parallel_tool_calls: Whether to enable
              [parallel function calling](https://platform.openai.com/docs/guides/function-calling/parallel-function-calling)
              during tool use.

          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/text-generation/parameter-details)

          response_format: An object specifying the format that the model must output. Compatible with
              [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
              [GPT-4o mini](https://platform.openai.com/docs/models/gpt-4o-mini),
              [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo) and
              all GPT-3.5 Turbo models newer than `gpt-3.5-turbo-1106`.

              Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
              Outputs which guarantees the model will match your supplied JSON schema. Learn
              more in the
              [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).

              Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
              message the model generates is valid JSON.

              **Important:** when using JSON mode, you **must** also instruct the model to
              produce JSON yourself via a system or user message. Without this, the model may
              generate an unending stream of whitespace until the generation reaches the token
              limit, resulting in a long-running and seemingly "stuck" request. Also note that
              the message content may be partially cut off if `finish_reason="length"`, which
              indicates the generation exceeded `max_tokens` or the conversation exceeded the
              max context length.

          seed: This feature is in Beta. 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.

          service_tier: Specifies the latency tier to use for processing the request. This parameter is
              relevant for customers subscribed to the scale tier service:

              - If set to 'auto', the system will utilize scale tier credits until they are
                exhausted.
              - If set to 'default', the request will be processed using the default service
                tier with a lower uptime SLA and no latency guarentee.
              - When not set, the default behavior is 'auto'.

              When this parameter is set, the response body will include the `service_tier`
              utilized.

          stop: Up to 4 sequences where the API will stop generating further tokens.

          stream_options: Options for streaming response. Only set this when you set `stream: true`.

          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.

          tool_choice: Controls which (if any) tool is called by the model. `none` means the model will
              not call any tool and instead generates a message. `auto` means the model can
              pick between generating a message or calling one or more tools. `required` means
              the model must call one or more tools. Specifying a particular tool via
              `{"type": "function", "function": {"name": "my_function"}}` forces the model to
              call that tool.

              `none` is the default when no tools are present. `auto` is the default if tools
              are present.

          tools: A list of tools the model may call. Currently, only functions are supported as a
              tool. Use this to provide a list of functions the model may generate JSON inputs
              for. A max of 128 functions are supported.

          top_logprobs: An integer between 0 and 20 specifying the number of most likely tokens to
              return at each token position, each with an associated log probability.
              `logprobs` must be set to `true` if this parameter is used.

          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,
        *,
        messages: Iterable[ChatCompletionMessageParam],
        model: Union[str, ChatModel],
        stream: bool,
        frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
        function_call: completion_create_params.FunctionCall | NotGiven = NOT_GIVEN,
        functions: Iterable[completion_create_params.Function] | NotGiven = NOT_GIVEN,
        logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
        logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
        max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
        n: Optional[int] | NotGiven = NOT_GIVEN,
        parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
        presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
        response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
        seed: Optional[int] | NotGiven = NOT_GIVEN,
        service_tier: Optional[Literal["auto", "default"]] | NotGiven = NOT_GIVEN,
        stop: Union[Optional[str], List[str]] | NotGiven = NOT_GIVEN,
        stream_options: Optional[ChatCompletionStreamOptionsParam] | NotGiven = NOT_GIVEN,
        temperature: Optional[float] | NotGiven = NOT_GIVEN,
        tool_choice: ChatCompletionToolChoiceOptionParam | NotGiven = NOT_GIVEN,
        tools: Iterable[ChatCompletionToolParam] | NotGiven = NOT_GIVEN,
        top_logprobs: Optional[int] | 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,
    ) -> ChatCompletion | Stream[ChatCompletionChunk]:
        """
        Creates a model response for the given chat conversation.

        Args:
          messages: A list of messages comprising the conversation so far.
              [Example Python code](https://cookbook.openai.com/examples/how_to_format_inputs_to_chatgpt_models).

          model: ID of the model to use. See the
              [model endpoint compatibility](https://platform.openai.com/docs/models/model-endpoint-compatibility)
              table for details on which models work with the Chat API.

          stream: If set, partial message deltas will be sent, like in ChatGPT. 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).

          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/text-generation/parameter-details)

          function_call: Deprecated in favor of `tool_choice`.

              Controls which (if any) function is called by the model. `none` means the model
              will not call a function and instead generates a message. `auto` means the model
              can pick between generating a message or calling a function. Specifying a
              particular function via `{"name": "my_function"}` forces the model to call that
              function.

              `none` is the default when no functions are present. `auto` is the default if
              functions are present.

          functions: Deprecated in favor of `tools`.

              A list of functions the model may generate JSON inputs for.

          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
              tokenizer) to an associated bias value from -100 to 100. 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.

          logprobs: Whether to return log probabilities of the output tokens or not. If true,
              returns the log probabilities of each output token returned in the `content` of
              `message`.

          max_tokens: The maximum number of [tokens](/tokenizer) that can be generated in the chat
              completion.

              The total length of input tokens and generated tokens is limited by 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 chat completion choices to generate for each input message. Note that
              you will be charged based on the number of generated tokens across all of the
              choices. Keep `n` as `1` to minimize costs.

          parallel_tool_calls: Whether to enable
              [parallel function calling](https://platform.openai.com/docs/guides/function-calling/parallel-function-calling)
              during tool use.

          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/text-generation/parameter-details)

          response_format: An object specifying the format that the model must output. Compatible with
              [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
              [GPT-4o mini](https://platform.openai.com/docs/models/gpt-4o-mini),
              [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo) and
              all GPT-3.5 Turbo models newer than `gpt-3.5-turbo-1106`.

              Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
              Outputs which guarantees the model will match your supplied JSON schema. Learn
              more in the
              [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).

              Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
              message the model generates is valid JSON.

              **Important:** when using JSON mode, you **must** also instruct the model to
              produce JSON yourself via a system or user message. Without this, the model may
              generate an unending stream of whitespace until the generation reaches the token
              limit, resulting in a long-running and seemingly "stuck" request. Also note that
              the message content may be partially cut off if `finish_reason="length"`, which
              indicates the generation exceeded `max_tokens` or the conversation exceeded the
              max context length.

          seed: This feature is in Beta. 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.

          service_tier: Specifies the latency tier to use for processing the request. This parameter is
              relevant for customers subscribed to the scale tier service:

              - If set to 'auto', the system will utilize scale tier credits until they are
                exhausted.
              - If set to 'default', the request will be processed using the default service
                tier with a lower uptime SLA and no latency guarentee.
              - When not set, the default behavior is 'auto'.

              When this parameter is set, the response body will include the `service_tier`
              utilized.

          stop: Up to 4 sequences where the API will stop generating further tokens.

          stream_options: Options for streaming response. Only set this when you set `stream: true`.

          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.

          tool_choice: Controls which (if any) tool is called by the model. `none` means the model will
              not call any tool and instead generates a message. `auto` means the model can
              pick between generating a message or calling one or more tools. `required` means
              the model must call one or more tools. Specifying a particular tool via
              `{"type": "function", "function": {"name": "my_function"}}` forces the model to
              call that tool.

              `none` is the default when no tools are present. `auto` is the default if tools
              are present.

          tools: A list of tools the model may call. Currently, only functions are supported as a
              tool. Use this to provide a list of functions the model may generate JSON inputs
              for. A max of 128 functions are supported.

          top_logprobs: An integer between 0 and 20 specifying the number of most likely tokens to
              return at each token position, each with an associated log probability.
              `logprobs` must be set to `true` if this parameter is used.

          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(["messages", "model"], ["messages", "model", "stream"])
    def create(
        self,
        *,
        messages: Iterable[ChatCompletionMessageParam],
        model: Union[str, ChatModel],
        frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
        function_call: completion_create_params.FunctionCall | NotGiven = NOT_GIVEN,
        functions: Iterable[completion_create_params.Function] | NotGiven = NOT_GIVEN,
        logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
        logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
        max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
        n: Optional[int] | NotGiven = NOT_GIVEN,
        parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
        presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
        response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
        seed: Optional[int] | NotGiven = NOT_GIVEN,
        service_tier: Optional[Literal["auto", "default"]] | NotGiven = NOT_GIVEN,
        stop: Union[Optional[str], List[str]] | NotGiven = NOT_GIVEN,
        stream: Optional[Literal[False]] | Literal[True] | NotGiven = NOT_GIVEN,
        stream_options: Optional[ChatCompletionStreamOptionsParam] | NotGiven = NOT_GIVEN,
        temperature: Optional[float] | NotGiven = NOT_GIVEN,
        tool_choice: ChatCompletionToolChoiceOptionParam | NotGiven = NOT_GIVEN,
        tools: Iterable[ChatCompletionToolParam] | NotGiven = NOT_GIVEN,
        top_logprobs: Optional[int] | 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,
    ) -> ChatCompletion | Stream[ChatCompletionChunk]:
        validate_response_format(response_format)
        return self._post(
            "/chat/completions",
            body=maybe_transform(
                {
                    "messages": messages,
                    "model": model,
                    "frequency_penalty": frequency_penalty,
                    "function_call": function_call,
                    "functions": functions,
                    "logit_bias": logit_bias,
                    "logprobs": logprobs,
                    "max_tokens": max_tokens,
                    "n": n,
                    "parallel_tool_calls": parallel_tool_calls,
                    "presence_penalty": presence_penalty,
                    "response_format": response_format,
                    "seed": seed,
                    "service_tier": service_tier,
                    "stop": stop,
                    "stream": stream,
                    "stream_options": stream_options,
                    "temperature": temperature,
                    "tool_choice": tool_choice,
                    "tools": tools,
                    "top_logprobs": top_logprobs,
                    "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=ChatCompletion,
            stream=stream or False,
            stream_cls=Stream[ChatCompletionChunk],
        )


class AsyncCompletions(AsyncAPIResource):
    @cached_property
    def with_raw_response(self) -> AsyncCompletionsWithRawResponse:
        return AsyncCompletionsWithRawResponse(self)

    @cached_property
    def with_streaming_response(self) -> AsyncCompletionsWithStreamingResponse:
        return AsyncCompletionsWithStreamingResponse(self)

    @overload
    async def create(
        self,
        *,
        messages: Iterable[ChatCompletionMessageParam],
        model: Union[str, ChatModel],
        frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
        function_call: completion_create_params.FunctionCall | NotGiven = NOT_GIVEN,
        functions: Iterable[completion_create_params.Function] | NotGiven = NOT_GIVEN,
        logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
        logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
        max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
        n: Optional[int] | NotGiven = NOT_GIVEN,
        parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
        presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
        response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
        seed: Optional[int] | NotGiven = NOT_GIVEN,
        service_tier: Optional[Literal["auto", "default"]] | NotGiven = NOT_GIVEN,
        stop: Union[Optional[str], List[str]] | NotGiven = NOT_GIVEN,
        stream: Optional[Literal[False]] | NotGiven = NOT_GIVEN,
        stream_options: Optional[ChatCompletionStreamOptionsParam] | NotGiven = NOT_GIVEN,
        temperature: Optional[float] | NotGiven = NOT_GIVEN,
        tool_choice: ChatCompletionToolChoiceOptionParam | NotGiven = NOT_GIVEN,
        tools: Iterable[ChatCompletionToolParam] | NotGiven = NOT_GIVEN,
        top_logprobs: Optional[int] | 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,
    ) -> ChatCompletion:
        """
        Creates a model response for the given chat conversation.

        Args:
          messages: A list of messages comprising the conversation so far.
              [Example Python code](https://cookbook.openai.com/examples/how_to_format_inputs_to_chatgpt_models).

          model: ID of the model to use. See the
              [model endpoint compatibility](https://platform.openai.com/docs/models/model-endpoint-compatibility)
              table for details on which models work with the Chat API.

          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/text-generation/parameter-details)

          function_call: Deprecated in favor of `tool_choice`.

              Controls which (if any) function is called by the model. `none` means the model
              will not call a function and instead generates a message. `auto` means the model
              can pick between generating a message or calling a function. Specifying a
              particular function via `{"name": "my_function"}` forces the model to call that
              function.

              `none` is the default when no functions are present. `auto` is the default if
              functions are present.

          functions: Deprecated in favor of `tools`.

              A list of functions the model may generate JSON inputs for.

          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
              tokenizer) to an associated bias value from -100 to 100. 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.

          logprobs: Whether to return log probabilities of the output tokens or not. If true,
              returns the log probabilities of each output token returned in the `content` of
              `message`.

          max_tokens: The maximum number of [tokens](/tokenizer) that can be generated in the chat
              completion.

              The total length of input tokens and generated tokens is limited by 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 chat completion choices to generate for each input message. Note that
              you will be charged based on the number of generated tokens across all of the
              choices. Keep `n` as `1` to minimize costs.

          parallel_tool_calls: Whether to enable
              [parallel function calling](https://platform.openai.com/docs/guides/function-calling/parallel-function-calling)
              during tool use.

          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/text-generation/parameter-details)

          response_format: An object specifying the format that the model must output. Compatible with
              [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
              [GPT-4o mini](https://platform.openai.com/docs/models/gpt-4o-mini),
              [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo) and
              all GPT-3.5 Turbo models newer than `gpt-3.5-turbo-1106`.

              Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
              Outputs which guarantees the model will match your supplied JSON schema. Learn
              more in the
              [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).

              Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
              message the model generates is valid JSON.

              **Important:** when using JSON mode, you **must** also instruct the model to
              produce JSON yourself via a system or user message. Without this, the model may
              generate an unending stream of whitespace until the generation reaches the token
              limit, resulting in a long-running and seemingly "stuck" request. Also note that
              the message content may be partially cut off if `finish_reason="length"`, which
              indicates the generation exceeded `max_tokens` or the conversation exceeded the
              max context length.

          seed: This feature is in Beta. 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.

          service_tier: Specifies the latency tier to use for processing the request. This parameter is
              relevant for customers subscribed to the scale tier service:

              - If set to 'auto', the system will utilize scale tier credits until they are
                exhausted.
              - If set to 'default', the request will be processed using the default service
                tier with a lower uptime SLA and no latency guarentee.
              - When not set, the default behavior is 'auto'.

              When this parameter is set, the response body will include the `service_tier`
              utilized.

          stop: Up to 4 sequences where the API will stop generating further tokens.

          stream: If set, partial message deltas will be sent, like in ChatGPT. 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).

          stream_options: Options for streaming response. Only set this when you set `stream: true`.

          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.

          tool_choice: Controls which (if any) tool is called by the model. `none` means the model will
              not call any tool and instead generates a message. `auto` means the model can
              pick between generating a message or calling one or more tools. `required` means
              the model must call one or more tools. Specifying a particular tool via
              `{"type": "function", "function": {"name": "my_function"}}` forces the model to
              call that tool.

              `none` is the default when no tools are present. `auto` is the default if tools
              are present.

          tools: A list of tools the model may call. Currently, only functions are supported as a
              tool. Use this to provide a list of functions the model may generate JSON inputs
              for. A max of 128 functions are supported.

          top_logprobs: An integer between 0 and 20 specifying the number of most likely tokens to
              return at each token position, each with an associated log probability.
              `logprobs` must be set to `true` if this parameter is used.

          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,
        *,
        messages: Iterable[ChatCompletionMessageParam],
        model: Union[str, ChatModel],
        stream: Literal[True],
        frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
        function_call: completion_create_params.FunctionCall | NotGiven = NOT_GIVEN,
        functions: Iterable[completion_create_params.Function] | NotGiven = NOT_GIVEN,
        logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
        logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
        max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
        n: Optional[int] | NotGiven = NOT_GIVEN,
        parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
        presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
        response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
        seed: Optional[int] | NotGiven = NOT_GIVEN,
        service_tier: Optional[Literal["auto", "default"]] | NotGiven = NOT_GIVEN,
        stop: Union[Optional[str], List[str]] | NotGiven = NOT_GIVEN,
        stream_options: Optional[ChatCompletionStreamOptionsParam] | NotGiven = NOT_GIVEN,
        temperature: Optional[float] | NotGiven = NOT_GIVEN,
        tool_choice: ChatCompletionToolChoiceOptionParam | NotGiven = NOT_GIVEN,
        tools: Iterable[ChatCompletionToolParam] | NotGiven = NOT_GIVEN,
        top_logprobs: Optional[int] | 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[ChatCompletionChunk]:
        """
        Creates a model response for the given chat conversation.

        Args:
          messages: A list of messages comprising the conversation so far.
              [Example Python code](https://cookbook.openai.com/examples/how_to_format_inputs_to_chatgpt_models).

          model: ID of the model to use. See the
              [model endpoint compatibility](https://platform.openai.com/docs/models/model-endpoint-compatibility)
              table for details on which models work with the Chat API.

          stream: If set, partial message deltas will be sent, like in ChatGPT. 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).

          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/text-generation/parameter-details)

          function_call: Deprecated in favor of `tool_choice`.

              Controls which (if any) function is called by the model. `none` means the model
              will not call a function and instead generates a message. `auto` means the model
              can pick between generating a message or calling a function. Specifying a
              particular function via `{"name": "my_function"}` forces the model to call that
              function.

              `none` is the default when no functions are present. `auto` is the default if
              functions are present.

          functions: Deprecated in favor of `tools`.

              A list of functions the model may generate JSON inputs for.

          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
              tokenizer) to an associated bias value from -100 to 100. 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.

          logprobs: Whether to return log probabilities of the output tokens or not. If true,
              returns the log probabilities of each output token returned in the `content` of
              `message`.

          max_tokens: The maximum number of [tokens](/tokenizer) that can be generated in the chat
              completion.

              The total length of input tokens and generated tokens is limited by 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 chat completion choices to generate for each input message. Note that
              you will be charged based on the number of generated tokens across all of the
              choices. Keep `n` as `1` to minimize costs.

          parallel_tool_calls: Whether to enable
              [parallel function calling](https://platform.openai.com/docs/guides/function-calling/parallel-function-calling)
              during tool use.

          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/text-generation/parameter-details)

          response_format: An object specifying the format that the model must output. Compatible with
              [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
              [GPT-4o mini](https://platform.openai.com/docs/models/gpt-4o-mini),
              [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo) and
              all GPT-3.5 Turbo models newer than `gpt-3.5-turbo-1106`.

              Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
              Outputs which guarantees the model will match your supplied JSON schema. Learn
              more in the
              [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).

              Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
              message the model generates is valid JSON.

              **Important:** when using JSON mode, you **must** also instruct the model to
              produce JSON yourself via a system or user message. Without this, the model may
              generate an unending stream of whitespace until the generation reaches the token
              limit, resulting in a long-running and seemingly "stuck" request. Also note that
              the message content may be partially cut off if `finish_reason="length"`, which
              indicates the generation exceeded `max_tokens` or the conversation exceeded the
              max context length.

          seed: This feature is in Beta. 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.

          service_tier: Specifies the latency tier to use for processing the request. This parameter is
              relevant for customers subscribed to the scale tier service:

              - If set to 'auto', the system will utilize scale tier credits until they are
                exhausted.
              - If set to 'default', the request will be processed using the default service
                tier with a lower uptime SLA and no latency guarentee.
              - When not set, the default behavior is 'auto'.

              When this parameter is set, the response body will include the `service_tier`
              utilized.

          stop: Up to 4 sequences where the API will stop generating further tokens.

          stream_options: Options for streaming response. Only set this when you set `stream: true`.

          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.

          tool_choice: Controls which (if any) tool is called by the model. `none` means the model will
              not call any tool and instead generates a message. `auto` means the model can
              pick between generating a message or calling one or more tools. `required` means
              the model must call one or more tools. Specifying a particular tool via
              `{"type": "function", "function": {"name": "my_function"}}` forces the model to
              call that tool.

              `none` is the default when no tools are present. `auto` is the default if tools
              are present.

          tools: A list of tools the model may call. Currently, only functions are supported as a
              tool. Use this to provide a list of functions the model may generate JSON inputs
              for. A max of 128 functions are supported.

          top_logprobs: An integer between 0 and 20 specifying the number of most likely tokens to
              return at each token position, each with an associated log probability.
              `logprobs` must be set to `true` if this parameter is used.

          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,
        *,
        messages: Iterable[ChatCompletionMessageParam],
        model: Union[str, ChatModel],
        stream: bool,
        frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
        function_call: completion_create_params.FunctionCall | NotGiven = NOT_GIVEN,
        functions: Iterable[completion_create_params.Function] | NotGiven = NOT_GIVEN,
        logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
        logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
        max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
        n: Optional[int] | NotGiven = NOT_GIVEN,
        parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
        presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
        response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
        seed: Optional[int] | NotGiven = NOT_GIVEN,
        service_tier: Optional[Literal["auto", "default"]] | NotGiven = NOT_GIVEN,
        stop: Union[Optional[str], List[str]] | NotGiven = NOT_GIVEN,
        stream_options: Optional[ChatCompletionStreamOptionsParam] | NotGiven = NOT_GIVEN,
        temperature: Optional[float] | NotGiven = NOT_GIVEN,
        tool_choice: ChatCompletionToolChoiceOptionParam | NotGiven = NOT_GIVEN,
        tools: Iterable[ChatCompletionToolParam] | NotGiven = NOT_GIVEN,
        top_logprobs: Optional[int] | 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,
    ) -> ChatCompletion | AsyncStream[ChatCompletionChunk]:
        """
        Creates a model response for the given chat conversation.

        Args:
          messages: A list of messages comprising the conversation so far.
              [Example Python code](https://cookbook.openai.com/examples/how_to_format_inputs_to_chatgpt_models).

          model: ID of the model to use. See the
              [model endpoint compatibility](https://platform.openai.com/docs/models/model-endpoint-compatibility)
              table for details on which models work with the Chat API.

          stream: If set, partial message deltas will be sent, like in ChatGPT. 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).

          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/text-generation/parameter-details)

          function_call: Deprecated in favor of `tool_choice`.

              Controls which (if any) function is called by the model. `none` means the model
              will not call a function and instead generates a message. `auto` means the model
              can pick between generating a message or calling a function. Specifying a
              particular function via `{"name": "my_function"}` forces the model to call that
              function.

              `none` is the default when no functions are present. `auto` is the default if
              functions are present.

          functions: Deprecated in favor of `tools`.

              A list of functions the model may generate JSON inputs for.

          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
              tokenizer) to an associated bias value from -100 to 100. 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.

          logprobs: Whether to return log probabilities of the output tokens or not. If true,
              returns the log probabilities of each output token returned in the `content` of
              `message`.

          max_tokens: The maximum number of [tokens](/tokenizer) that can be generated in the chat
              completion.

              The total length of input tokens and generated tokens is limited by 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 chat completion choices to generate for each input message. Note that
              you will be charged based on the number of generated tokens across all of the
              choices. Keep `n` as `1` to minimize costs.

          parallel_tool_calls: Whether to enable
              [parallel function calling](https://platform.openai.com/docs/guides/function-calling/parallel-function-calling)
              during tool use.

          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/text-generation/parameter-details)

          response_format: An object specifying the format that the model must output. Compatible with
              [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
              [GPT-4o mini](https://platform.openai.com/docs/models/gpt-4o-mini),
              [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo) and
              all GPT-3.5 Turbo models newer than `gpt-3.5-turbo-1106`.

              Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
              Outputs which guarantees the model will match your supplied JSON schema. Learn
              more in the
              [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).

              Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
              message the model generates is valid JSON.

              **Important:** when using JSON mode, you **must** also instruct the model to
              produce JSON yourself via a system or user message. Without this, the model may
              generate an unending stream of whitespace until the generation reaches the token
              limit, resulting in a long-running and seemingly "stuck" request. Also note that
              the message content may be partially cut off if `finish_reason="length"`, which
              indicates the generation exceeded `max_tokens` or the conversation exceeded the
              max context length.

          seed: This feature is in Beta. 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.

          service_tier: Specifies the latency tier to use for processing the request. This parameter is
              relevant for customers subscribed to the scale tier service:

              - If set to 'auto', the system will utilize scale tier credits until they are
                exhausted.
              - If set to 'default', the request will be processed using the default service
                tier with a lower uptime SLA and no latency guarentee.
              - When not set, the default behavior is 'auto'.

              When this parameter is set, the response body will include the `service_tier`
              utilized.

          stop: Up to 4 sequences where the API will stop generating further tokens.

          stream_options: Options for streaming response. Only set this when you set `stream: true`.

          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.

          tool_choice: Controls which (if any) tool is called by the model. `none` means the model will
              not call any tool and instead generates a message. `auto` means the model can
              pick between generating a message or calling one or more tools. `required` means
              the model must call one or more tools. Specifying a particular tool via
              `{"type": "function", "function": {"name": "my_function"}}` forces the model to
              call that tool.

              `none` is the default when no tools are present. `auto` is the default if tools
              are present.

          tools: A list of tools the model may call. Currently, only functions are supported as a
              tool. Use this to provide a list of functions the model may generate JSON inputs
              for. A max of 128 functions are supported.

          top_logprobs: An integer between 0 and 20 specifying the number of most likely tokens to
              return at each token position, each with an associated log probability.
              `logprobs` must be set to `true` if this parameter is used.

          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(["messages", "model"], ["messages", "model", "stream"])
    async def create(
        self,
        *,
        messages: Iterable[ChatCompletionMessageParam],
        model: Union[str, ChatModel],
        frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
        function_call: completion_create_params.FunctionCall | NotGiven = NOT_GIVEN,
        functions: Iterable[completion_create_params.Function] | NotGiven = NOT_GIVEN,
        logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
        logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
        max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
        n: Optional[int] | NotGiven = NOT_GIVEN,
        parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
        presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
        response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
        seed: Optional[int] | NotGiven = NOT_GIVEN,
        service_tier: Optional[Literal["auto", "default"]] | NotGiven = NOT_GIVEN,
        stop: Union[Optional[str], List[str]] | NotGiven = NOT_GIVEN,
        stream: Optional[Literal[False]] | Literal[True] | NotGiven = NOT_GIVEN,
        stream_options: Optional[ChatCompletionStreamOptionsParam] | NotGiven = NOT_GIVEN,
        temperature: Optional[float] | NotGiven = NOT_GIVEN,
        tool_choice: ChatCompletionToolChoiceOptionParam | NotGiven = NOT_GIVEN,
        tools: Iterable[ChatCompletionToolParam] | NotGiven = NOT_GIVEN,
        top_logprobs: Optional[int] | 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,
    ) -> ChatCompletion | AsyncStream[ChatCompletionChunk]:
        validate_response_format(response_format)
        return await self._post(
            "/chat/completions",
            body=await async_maybe_transform(
                {
                    "messages": messages,
                    "model": model,
                    "frequency_penalty": frequency_penalty,
                    "function_call": function_call,
                    "functions": functions,
                    "logit_bias": logit_bias,
                    "logprobs": logprobs,
                    "max_tokens": max_tokens,
                    "n": n,
                    "parallel_tool_calls": parallel_tool_calls,
                    "presence_penalty": presence_penalty,
                    "response_format": response_format,
                    "seed": seed,
                    "service_tier": service_tier,
                    "stop": stop,
                    "stream": stream,
                    "stream_options": stream_options,
                    "temperature": temperature,
                    "tool_choice": tool_choice,
                    "tools": tools,
                    "top_logprobs": top_logprobs,
                    "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=ChatCompletion,
            stream=stream or False,
            stream_cls=AsyncStream[ChatCompletionChunk],
        )


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,
        )


def validate_response_format(response_format: object) -> None:
    if inspect.isclass(response_format) and issubclass(response_format, pydantic.BaseModel):
        raise TypeError(
            "You tried to pass a `BaseModel` class to `chat.completions.create()`; You must use `beta.chat.completions.parse()` instead"
        )