# File generated from our OpenAPI spec by Stainless.

from __future__ import annotations

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

import httpx

from ..._types import NOT_GIVEN, Body, Query, Headers, NotGiven
from ..._utils import maybe_transform
from ..._compat import cached_property
from ..._resource import SyncAPIResource, AsyncAPIResource
from ..._response import (
    to_raw_response_wrapper,
    to_streamed_response_wrapper,
    async_to_raw_response_wrapper,
    async_to_streamed_response_wrapper,
)
from ..._streaming import Stream, AsyncStream
from ...types.chat import ChatCompletion, completion_create_params
from ..._base_client import (
    make_request_options,
)
from ...lib.chat_completion_chunk import ChatCompletionChunk

__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[completion_create_params.Message],
        model: str,
        frequency_penalty: float | NotGiven = NOT_GIVEN,
        logit_bias: Dict[str, int] | NotGiven = NOT_GIVEN,
        logprobs: bool | NotGiven = NOT_GIVEN,
        max_tokens: int | NotGiven = NOT_GIVEN,
        n: int | NotGiven = NOT_GIVEN,
        presence_penalty: float | NotGiven = NOT_GIVEN,
        response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
        seed: int | NotGiven = NOT_GIVEN,
        stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
        stream: Optional[Literal[False]] | NotGiven = NOT_GIVEN,
        temperature: float | NotGiven = NOT_GIVEN,
        tool_choice: completion_create_params.ToolChoice | NotGiven = NOT_GIVEN,
        tools: Iterable[completion_create_params.Tool] | NotGiven = NOT_GIVEN,
        top_logprobs: int | NotGiven = NOT_GIVEN,
        top_p: 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:
        ...

    @overload
    def create(
        self,
        *,
        messages: Iterable[completion_create_params.Message],
        model: str,
        frequency_penalty: float | NotGiven = NOT_GIVEN,
        logit_bias: Dict[str, int] | NotGiven = NOT_GIVEN,
        logprobs: bool | NotGiven = NOT_GIVEN,
        max_tokens: int | NotGiven = NOT_GIVEN,
        n: int | NotGiven = NOT_GIVEN,
        presence_penalty: float | NotGiven = NOT_GIVEN,
        response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
        seed: int | NotGiven = NOT_GIVEN,
        stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
        stream: Literal[True],
        temperature: float | NotGiven = NOT_GIVEN,
        tool_choice: completion_create_params.ToolChoice | NotGiven = NOT_GIVEN,
        tools: Iterable[completion_create_params.Tool] | NotGiven = NOT_GIVEN,
        top_logprobs: int | NotGiven = NOT_GIVEN,
        top_p: 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]:
        ...

    @overload
    def create(
        self,
        *,
        messages: Iterable[completion_create_params.Message],
        model: str,
        frequency_penalty: float | NotGiven = NOT_GIVEN,
        logit_bias: Dict[str, int] | NotGiven = NOT_GIVEN,
        logprobs: bool | NotGiven = NOT_GIVEN,
        max_tokens: int | NotGiven = NOT_GIVEN,
        n: int | NotGiven = NOT_GIVEN,
        presence_penalty: float | NotGiven = NOT_GIVEN,
        response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
        seed: int | NotGiven = NOT_GIVEN,
        stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
        stream: bool,
        temperature: float | NotGiven = NOT_GIVEN,
        tool_choice: completion_create_params.ToolChoice | NotGiven = NOT_GIVEN,
        tools: Iterable[completion_create_params.Tool] | NotGiven = NOT_GIVEN,
        top_logprobs: int | NotGiven = NOT_GIVEN,
        top_p: 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]:
        ...

    def create(
        self,
        *,
        messages: Iterable[completion_create_params.Message],
        model: str,
        frequency_penalty: float | NotGiven = NOT_GIVEN,
        logit_bias: Dict[str, int] | NotGiven = NOT_GIVEN,
        logprobs: bool | NotGiven = NOT_GIVEN,
        max_tokens: int | NotGiven = NOT_GIVEN,
        n: int | NotGiven = NOT_GIVEN,
        presence_penalty: float | NotGiven = NOT_GIVEN,
        response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
        seed: int | NotGiven = NOT_GIVEN,
        stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
        stream: Optional[Literal[False]] | Literal[True] | NotGiven = NOT_GIVEN,
        temperature: float | NotGiven = NOT_GIVEN,
        tool_choice: completion_create_params.ToolChoice | NotGiven = NOT_GIVEN,
        tools: Iterable[completion_create_params.Tool] | NotGiven = NOT_GIVEN,
        top_logprobs: int | NotGiven = NOT_GIVEN,
        top_p: 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 completion for a chat prompt

        Args:
          stop: Up to 4 sequences where the API will stop generating further tokens. The
              returned text will not contain the stop sequence.

          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
        """
        return self._post(
            "/openai/v1/chat/completions",
            body=maybe_transform(
                {
                    "messages": messages,
                    "model": model,
                    "frequency_penalty": frequency_penalty,
                    "logit_bias": logit_bias,
                    "logprobs": logprobs,
                    "max_tokens": max_tokens,
                    "n": n,
                    "presence_penalty": presence_penalty,
                    "response_format": response_format,
                    "seed": seed,
                    "stop": stop,
                    "stream": stream,
                    "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[completion_create_params.Message],
        model: str,
        frequency_penalty: float | NotGiven = NOT_GIVEN,
        logit_bias: Dict[str, int] | NotGiven = NOT_GIVEN,
        logprobs: bool | NotGiven = NOT_GIVEN,
        max_tokens: int | NotGiven = NOT_GIVEN,
        n: int | NotGiven = NOT_GIVEN,
        presence_penalty: float | NotGiven = NOT_GIVEN,
        response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
        seed: int | NotGiven = NOT_GIVEN,
        stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
        stream: Optional[Literal[False]] | NotGiven = NOT_GIVEN,
        temperature: float | NotGiven = NOT_GIVEN,
        tool_choice: completion_create_params.ToolChoice | NotGiven = NOT_GIVEN,
        tools: Iterable[completion_create_params.Tool] | NotGiven = NOT_GIVEN,
        top_logprobs: int | NotGiven = NOT_GIVEN,
        top_p: 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:
        ...

    @overload
    async def create(
        self,
        *,
        messages: Iterable[completion_create_params.Message],
        model: str,
        frequency_penalty: float | NotGiven = NOT_GIVEN,
        logit_bias: Dict[str, int] | NotGiven = NOT_GIVEN,
        logprobs: bool | NotGiven = NOT_GIVEN,
        max_tokens: int | NotGiven = NOT_GIVEN,
        n: int | NotGiven = NOT_GIVEN,
        presence_penalty: float | NotGiven = NOT_GIVEN,
        response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
        seed: int | NotGiven = NOT_GIVEN,
        stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
        stream: Literal[True],
        temperature: float | NotGiven = NOT_GIVEN,
        tool_choice: completion_create_params.ToolChoice | NotGiven = NOT_GIVEN,
        tools: Iterable[completion_create_params.Tool] | NotGiven = NOT_GIVEN,
        top_logprobs: int | NotGiven = NOT_GIVEN,
        top_p: 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]:
        ...

    @overload
    async def create(
        self,
        *,
        messages: Iterable[completion_create_params.Message],
        model: str,
        frequency_penalty: float | NotGiven = NOT_GIVEN,
        logit_bias: Dict[str, int] | NotGiven = NOT_GIVEN,
        logprobs: bool | NotGiven = NOT_GIVEN,
        max_tokens: int | NotGiven = NOT_GIVEN,
        n: int | NotGiven = NOT_GIVEN,
        presence_penalty: float | NotGiven = NOT_GIVEN,
        response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
        seed: int | NotGiven = NOT_GIVEN,
        stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
        stream: bool,
        temperature: float | NotGiven = NOT_GIVEN,
        tool_choice: completion_create_params.ToolChoice | NotGiven = NOT_GIVEN,
        tools: Iterable[completion_create_params.Tool] | NotGiven = NOT_GIVEN,
        top_logprobs: int | NotGiven = NOT_GIVEN,
        top_p: 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]:
        ...

    async def create(
        self,
        *,
        messages: Iterable[completion_create_params.Message],
        model: str,
        frequency_penalty: float | NotGiven = NOT_GIVEN,
        logit_bias: Dict[str, int] | NotGiven = NOT_GIVEN,
        logprobs: bool | NotGiven = NOT_GIVEN,
        max_tokens: int | NotGiven = NOT_GIVEN,
        n: int | NotGiven = NOT_GIVEN,
        presence_penalty: float | NotGiven = NOT_GIVEN,
        response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
        seed: int | NotGiven = NOT_GIVEN,
        stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
        stream: Optional[Literal[False]] | Literal[True] | NotGiven = NOT_GIVEN,
        temperature: float | NotGiven = NOT_GIVEN,
        tool_choice: completion_create_params.ToolChoice | NotGiven = NOT_GIVEN,
        tools: Iterable[completion_create_params.Tool] | NotGiven = NOT_GIVEN,
        top_logprobs: int | NotGiven = NOT_GIVEN,
        top_p: 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 completion for a chat prompt

        Args:
          stop: Up to 4 sequences where the API will stop generating further tokens. The
              returned text will not contain the stop sequence.

          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
        """
        return await self._post(
            "/openai/v1/chat/completions",
            body=maybe_transform(
                {
                    "messages": messages,
                    "model": model,
                    "frequency_penalty": frequency_penalty,
                    "logit_bias": logit_bias,
                    "logprobs": logprobs,
                    "max_tokens": max_tokens,
                    "n": n,
                    "presence_penalty": presence_penalty,
                    "response_format": response_format,
                    "seed": seed,
                    "stop": stop,
                    "stream": stream,
                    "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 = to_raw_response_wrapper(
            completions.create,
        )


class AsyncCompletionsWithRawResponse:
    def __init__(self, completions: AsyncCompletions) -> None:
        self._completions = completions

        self.create = 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,
        )