vectorvein 0.2.6__py3-none-any.whl → 0.2.8__py3-none-any.whl

vectorvein/chat_clients/base_client.py

@@ -4,10 +4,19 @@ import asyncio
 from abc import ABC, abstractmethod
 from collections import defaultdict
 from functools import cached_property
-from typing import Generator, AsyncGenerator, Any, overload, Literal, Iterable
+from typing import Generator, AsyncGenerator, Any, overload, Literal, Iterable, Optional, Dict, List, Union
 
 import httpx
 from openai import OpenAI, AsyncOpenAI, AzureOpenAI, AsyncAzureOpenAI
+from openai._types import Headers, Query, Body
+from openai.types.shared_params.metadata import Metadata
+from openai.types.chat.completion_create_params import ResponseFormat
+from openai.types.chat.chat_completion_modality import ChatCompletionModality
+from openai.types.chat.chat_completion_audio_param import ChatCompletionAudioParam
+from openai.types.chat.chat_completion_reasoning_effort import ChatCompletionReasoningEffort
+from openai.types.chat.chat_completion_stream_options_param import ChatCompletionStreamOptionsParam
+from openai.types.chat.chat_completion_prediction_content_param import ChatCompletionPredictionContentParam
+
 from anthropic import (
     Anthropic,
     AsyncAnthropic,
@@ -16,6 +25,7 @@ from anthropic import (
     AnthropicBedrock,
     AsyncAnthropicBedrock,
 )
+from anthropic.types.thinking_config_param import ThinkingConfigParam
 
 from ..settings import settings
 from ..types import defaults as defs
@@ -25,10 +35,10 @@ from ..types.llm_parameters import (
     NOT_GIVEN,
     ToolParam,
     ToolChoice,
+    OpenAINotGiven,
     EndpointSetting,
     ChatCompletionMessage,
     ChatCompletionDeltaMessage,
-    ChatCompletionStreamOptionsParam,
 )
 from ..utilities.rate_limiter import SyncMemoryRateLimiter, SyncRedisRateLimiter, SyncDiskCacheRateLimiter
 from ..utilities.rate_limiter import AsyncMemoryRateLimiter, AsyncRedisRateLimiter, AsyncDiskCacheRateLimiter
@@ -172,11 +182,33 @@ class BaseChatClient(ABC):
         max_tokens: int | None = None,
         tools: Iterable[ToolParam] | NotGiven = NOT_GIVEN,
         tool_choice: ToolChoice | NotGiven = NOT_GIVEN,
-        response_format: dict | None = None,
+        response_format: ResponseFormat | NotGiven = NOT_GIVEN,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
         skip_cutoff: bool = False,
-        **kwargs,
+        audio: Optional[ChatCompletionAudioParam] | OpenAINotGiven = NOT_GIVEN,
+        frequency_penalty: Optional[float] | OpenAINotGiven = NOT_GIVEN,
+        logit_bias: Optional[Dict[str, int]] | OpenAINotGiven = NOT_GIVEN,
+        logprobs: Optional[bool] | OpenAINotGiven = NOT_GIVEN,
+        max_completion_tokens: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        metadata: Optional[Metadata] | OpenAINotGiven = NOT_GIVEN,
+        modalities: Optional[List[ChatCompletionModality]] | OpenAINotGiven = NOT_GIVEN,
+        n: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        parallel_tool_calls: bool | OpenAINotGiven = NOT_GIVEN,
+        prediction: Optional[ChatCompletionPredictionContentParam] | OpenAINotGiven = NOT_GIVEN,
+        presence_penalty: Optional[float] | OpenAINotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[ChatCompletionReasoningEffort] | OpenAINotGiven = NOT_GIVEN,
+        thinking: ThinkingConfigParam | None | NotGiven = NOT_GIVEN,
+        seed: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "default"]] | OpenAINotGiven = NOT_GIVEN,
+        stop: Union[Optional[str], List[str]] | OpenAINotGiven = NOT_GIVEN,
+        store: Optional[bool] | OpenAINotGiven = NOT_GIVEN,
+        top_logprobs: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        user: str | OpenAINotGiven = NOT_GIVEN,
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | OpenAINotGiven = NOT_GIVEN,
     ) -> ChatCompletionMessage:
         pass
 
@@ -192,11 +224,33 @@ class BaseChatClient(ABC):
         max_tokens: int | None = None,
         tools: Iterable[ToolParam] | NotGiven = NOT_GIVEN,
         tool_choice: ToolChoice | NotGiven = NOT_GIVEN,
-        response_format: dict | None = None,
+        response_format: ResponseFormat | NotGiven = NOT_GIVEN,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
         skip_cutoff: bool = False,
-        **kwargs,
+        audio: Optional[ChatCompletionAudioParam] | OpenAINotGiven = NOT_GIVEN,
+        frequency_penalty: Optional[float] | OpenAINotGiven = NOT_GIVEN,
+        logit_bias: Optional[Dict[str, int]] | OpenAINotGiven = NOT_GIVEN,
+        logprobs: Optional[bool] | OpenAINotGiven = NOT_GIVEN,
+        max_completion_tokens: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        metadata: Optional[Metadata] | OpenAINotGiven = NOT_GIVEN,
+        modalities: Optional[List[ChatCompletionModality]] | OpenAINotGiven = NOT_GIVEN,
+        n: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        parallel_tool_calls: bool | OpenAINotGiven = NOT_GIVEN,
+        prediction: Optional[ChatCompletionPredictionContentParam] | OpenAINotGiven = NOT_GIVEN,
+        presence_penalty: Optional[float] | OpenAINotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[ChatCompletionReasoningEffort] | OpenAINotGiven = NOT_GIVEN,
+        thinking: ThinkingConfigParam | None | NotGiven = NOT_GIVEN,
+        seed: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "default"]] | OpenAINotGiven = NOT_GIVEN,
+        stop: Union[Optional[str], List[str]] | OpenAINotGiven = NOT_GIVEN,
+        store: Optional[bool] | OpenAINotGiven = NOT_GIVEN,
+        top_logprobs: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        user: str | OpenAINotGiven = NOT_GIVEN,
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | OpenAINotGiven = NOT_GIVEN,
     ) -> Generator[ChatCompletionDeltaMessage, Any, None]:
         pass
 
@@ -212,11 +266,33 @@ class BaseChatClient(ABC):
         max_tokens: int | None = None,
         tools: Iterable[ToolParam] | NotGiven = NOT_GIVEN,
         tool_choice: ToolChoice | NotGiven = NOT_GIVEN,
-        response_format: dict | None = None,
+        response_format: ResponseFormat | NotGiven = NOT_GIVEN,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
         skip_cutoff: bool = False,
-        **kwargs,
+        audio: Optional[ChatCompletionAudioParam] | OpenAINotGiven = NOT_GIVEN,
+        frequency_penalty: Optional[float] | OpenAINotGiven = NOT_GIVEN,
+        logit_bias: Optional[Dict[str, int]] | OpenAINotGiven = NOT_GIVEN,
+        logprobs: Optional[bool] | OpenAINotGiven = NOT_GIVEN,
+        max_completion_tokens: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        metadata: Optional[Metadata] | OpenAINotGiven = NOT_GIVEN,
+        modalities: Optional[List[ChatCompletionModality]] | OpenAINotGiven = NOT_GIVEN,
+        n: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        parallel_tool_calls: bool | OpenAINotGiven = NOT_GIVEN,
+        prediction: Optional[ChatCompletionPredictionContentParam] | OpenAINotGiven = NOT_GIVEN,
+        presence_penalty: Optional[float] | OpenAINotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[ChatCompletionReasoningEffort] | OpenAINotGiven = NOT_GIVEN,
+        thinking: ThinkingConfigParam | None | NotGiven = NOT_GIVEN,
+        seed: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "default"]] | OpenAINotGiven = NOT_GIVEN,
+        stop: Union[Optional[str], List[str]] | OpenAINotGiven = NOT_GIVEN,
+        store: Optional[bool] | OpenAINotGiven = NOT_GIVEN,
+        top_logprobs: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        user: str | OpenAINotGiven = NOT_GIVEN,
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | OpenAINotGiven = NOT_GIVEN,
     ) -> ChatCompletionMessage | Generator[ChatCompletionDeltaMessage, Any, None]:
         pass
 
@@ -231,11 +307,33 @@ class BaseChatClient(ABC):
         max_tokens: int | None = None,
         tools: Iterable[ToolParam] | NotGiven = NOT_GIVEN,
         tool_choice: ToolChoice | NotGiven = NOT_GIVEN,
-        response_format: dict | None = None,
+        response_format: ResponseFormat | NotGiven = NOT_GIVEN,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
         skip_cutoff: bool = False,
-        **kwargs,
+        audio: Optional[ChatCompletionAudioParam] | OpenAINotGiven = NOT_GIVEN,
+        frequency_penalty: Optional[float] | OpenAINotGiven = NOT_GIVEN,
+        logit_bias: Optional[Dict[str, int]] | OpenAINotGiven = NOT_GIVEN,
+        logprobs: Optional[bool] | OpenAINotGiven = NOT_GIVEN,
+        max_completion_tokens: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        metadata: Optional[Metadata] | OpenAINotGiven = NOT_GIVEN,
+        modalities: Optional[List[ChatCompletionModality]] | OpenAINotGiven = NOT_GIVEN,
+        n: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        parallel_tool_calls: bool | OpenAINotGiven = NOT_GIVEN,
+        prediction: Optional[ChatCompletionPredictionContentParam] | OpenAINotGiven = NOT_GIVEN,
+        presence_penalty: Optional[float] | OpenAINotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[ChatCompletionReasoningEffort] | OpenAINotGiven = NOT_GIVEN,
+        thinking: ThinkingConfigParam | None | NotGiven = NOT_GIVEN,
+        seed: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "default"]] | OpenAINotGiven = NOT_GIVEN,
+        stop: Union[Optional[str], List[str]] | OpenAINotGiven = NOT_GIVEN,
+        store: Optional[bool] | OpenAINotGiven = NOT_GIVEN,
+        top_logprobs: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        user: str | OpenAINotGiven = NOT_GIVEN,
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | OpenAINotGiven = NOT_GIVEN,
     ) -> ChatCompletionMessage | Generator[ChatCompletionDeltaMessage, Any, None]:
         pass
 
@@ -248,10 +346,33 @@ class BaseChatClient(ABC):
         max_tokens: int | None = None,
         tools: Iterable[ToolParam] | NotGiven = NOT_GIVEN,
         tool_choice: ToolChoice | NotGiven = NOT_GIVEN,
-        response_format: dict | None = None,
+        response_format: ResponseFormat | NotGiven = NOT_GIVEN,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
-        **kwargs,
+        skip_cutoff: bool = False,
+        audio: Optional[ChatCompletionAudioParam] | OpenAINotGiven = NOT_GIVEN,
+        frequency_penalty: Optional[float] | OpenAINotGiven = NOT_GIVEN,
+        logit_bias: Optional[Dict[str, int]] | OpenAINotGiven = NOT_GIVEN,
+        logprobs: Optional[bool] | OpenAINotGiven = NOT_GIVEN,
+        max_completion_tokens: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        metadata: Optional[Metadata] | OpenAINotGiven = NOT_GIVEN,
+        modalities: Optional[List[ChatCompletionModality]] | OpenAINotGiven = NOT_GIVEN,
+        n: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        parallel_tool_calls: bool | OpenAINotGiven = NOT_GIVEN,
+        prediction: Optional[ChatCompletionPredictionContentParam] | OpenAINotGiven = NOT_GIVEN,
+        presence_penalty: Optional[float] | OpenAINotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[ChatCompletionReasoningEffort] | OpenAINotGiven = NOT_GIVEN,
+        thinking: ThinkingConfigParam | None | NotGiven = NOT_GIVEN,
+        seed: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "default"]] | OpenAINotGiven = NOT_GIVEN,
+        stop: Union[Optional[str], List[str]] | OpenAINotGiven = NOT_GIVEN,
+        store: Optional[bool] | OpenAINotGiven = NOT_GIVEN,
+        top_logprobs: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        user: str | OpenAINotGiven = NOT_GIVEN,
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | OpenAINotGiven = NOT_GIVEN,
     ) -> Generator[ChatCompletionDeltaMessage, Any, None]:
         return self.create_completion(
             messages=messages,
@@ -264,7 +385,30 @@ class BaseChatClient(ABC):
             response_format=response_format,
             stream_options=stream_options,
             top_p=top_p,
-            **kwargs,
+            skip_cutoff=skip_cutoff,
+            audio=audio,
+            frequency_penalty=frequency_penalty,
+            logit_bias=logit_bias,
+            logprobs=logprobs,
+            max_completion_tokens=max_completion_tokens,
+            metadata=metadata,
+            modalities=modalities,
+            n=n,
+            parallel_tool_calls=parallel_tool_calls,
+            prediction=prediction,
+            presence_penalty=presence_penalty,
+            reasoning_effort=reasoning_effort,
+            thinking=thinking,
+            seed=seed,
+            service_tier=service_tier,
+            stop=stop,
+            store=store,
+            top_logprobs=top_logprobs,
+            user=user,
+            extra_headers=extra_headers,
+            extra_query=extra_query,
+            extra_body=extra_body,
+            timeout=timeout,
         )
 
 
@@ -416,11 +560,33 @@ class BaseAsyncChatClient(ABC):
         max_tokens: int | None = None,
         tools: list | NotGiven = NOT_GIVEN,
         tool_choice: ToolChoice | NotGiven = NOT_GIVEN,
-        response_format: dict | None = None,
+        response_format: ResponseFormat | NotGiven = NOT_GIVEN,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
         skip_cutoff: bool = False,
-        **kwargs,
+        audio: Optional[ChatCompletionAudioParam] | OpenAINotGiven = NOT_GIVEN,
+        frequency_penalty: Optional[float] | OpenAINotGiven = NOT_GIVEN,
+        logit_bias: Optional[Dict[str, int]] | OpenAINotGiven = NOT_GIVEN,
+        logprobs: Optional[bool] | OpenAINotGiven = NOT_GIVEN,
+        max_completion_tokens: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        metadata: Optional[Metadata] | OpenAINotGiven = NOT_GIVEN,
+        modalities: Optional[List[ChatCompletionModality]] | OpenAINotGiven = NOT_GIVEN,
+        n: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        parallel_tool_calls: bool | OpenAINotGiven = NOT_GIVEN,
+        prediction: Optional[ChatCompletionPredictionContentParam] | OpenAINotGiven = NOT_GIVEN,
+        presence_penalty: Optional[float] | OpenAINotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[ChatCompletionReasoningEffort] | OpenAINotGiven = NOT_GIVEN,
+        thinking: ThinkingConfigParam | None | NotGiven = NOT_GIVEN,
+        seed: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "default"]] | OpenAINotGiven = NOT_GIVEN,
+        stop: Union[Optional[str], List[str]] | OpenAINotGiven = NOT_GIVEN,
+        store: Optional[bool] | OpenAINotGiven = NOT_GIVEN,
+        top_logprobs: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        user: str | OpenAINotGiven = NOT_GIVEN,
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | OpenAINotGiven = NOT_GIVEN,
     ) -> ChatCompletionMessage:
         pass
 
@@ -436,11 +602,33 @@ class BaseAsyncChatClient(ABC):
         max_tokens: int | None = None,
         tools: list | NotGiven = NOT_GIVEN,
         tool_choice: ToolChoice | NotGiven = NOT_GIVEN,
-        response_format: dict | None = None,
+        response_format: ResponseFormat | NotGiven = NOT_GIVEN,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
         skip_cutoff: bool = False,
-        **kwargs,
+        audio: Optional[ChatCompletionAudioParam] | OpenAINotGiven = NOT_GIVEN,
+        frequency_penalty: Optional[float] | OpenAINotGiven = NOT_GIVEN,
+        logit_bias: Optional[Dict[str, int]] | OpenAINotGiven = NOT_GIVEN,
+        logprobs: Optional[bool] | OpenAINotGiven = NOT_GIVEN,
+        max_completion_tokens: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        metadata: Optional[Metadata] | OpenAINotGiven = NOT_GIVEN,
+        modalities: Optional[List[ChatCompletionModality]] | OpenAINotGiven = NOT_GIVEN,
+        n: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        parallel_tool_calls: bool | OpenAINotGiven = NOT_GIVEN,
+        prediction: Optional[ChatCompletionPredictionContentParam] | OpenAINotGiven = NOT_GIVEN,
+        presence_penalty: Optional[float] | OpenAINotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[ChatCompletionReasoningEffort] | OpenAINotGiven = NOT_GIVEN,
+        thinking: ThinkingConfigParam | None | NotGiven = NOT_GIVEN,
+        seed: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "default"]] | OpenAINotGiven = NOT_GIVEN,
+        stop: Union[Optional[str], List[str]] | OpenAINotGiven = NOT_GIVEN,
+        store: Optional[bool] | OpenAINotGiven = NOT_GIVEN,
+        top_logprobs: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        user: str | OpenAINotGiven = NOT_GIVEN,
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | OpenAINotGiven = NOT_GIVEN,
     ) -> AsyncGenerator[ChatCompletionDeltaMessage, None]:
         pass
 
@@ -456,11 +644,33 @@ class BaseAsyncChatClient(ABC):
         max_tokens: int | None = None,
         tools: list | NotGiven = NOT_GIVEN,
         tool_choice: ToolChoice | NotGiven = NOT_GIVEN,
-        response_format: dict | None = None,
+        response_format: ResponseFormat | NotGiven = NOT_GIVEN,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
         skip_cutoff: bool = False,
-        **kwargs,
+        audio: Optional[ChatCompletionAudioParam] | OpenAINotGiven = NOT_GIVEN,
+        frequency_penalty: Optional[float] | OpenAINotGiven = NOT_GIVEN,
+        logit_bias: Optional[Dict[str, int]] | OpenAINotGiven = NOT_GIVEN,
+        logprobs: Optional[bool] | OpenAINotGiven = NOT_GIVEN,
+        max_completion_tokens: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        metadata: Optional[Metadata] | OpenAINotGiven = NOT_GIVEN,
+        modalities: Optional[List[ChatCompletionModality]] | OpenAINotGiven = NOT_GIVEN,
+        n: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        parallel_tool_calls: bool | OpenAINotGiven = NOT_GIVEN,
+        prediction: Optional[ChatCompletionPredictionContentParam] | OpenAINotGiven = NOT_GIVEN,
+        presence_penalty: Optional[float] | OpenAINotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[ChatCompletionReasoningEffort] | OpenAINotGiven = NOT_GIVEN,
+        thinking: ThinkingConfigParam | None | NotGiven = NOT_GIVEN,
+        seed: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "default"]] | OpenAINotGiven = NOT_GIVEN,
+        stop: Union[Optional[str], List[str]] | OpenAINotGiven = NOT_GIVEN,
+        store: Optional[bool] | OpenAINotGiven = NOT_GIVEN,
+        top_logprobs: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        user: str | OpenAINotGiven = NOT_GIVEN,
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | OpenAINotGiven = NOT_GIVEN,
     ) -> ChatCompletionMessage | AsyncGenerator[ChatCompletionDeltaMessage, None]:
         pass
 
@@ -475,11 +685,33 @@ class BaseAsyncChatClient(ABC):
         max_tokens: int | None = None,
         tools: list | NotGiven = NOT_GIVEN,
         tool_choice: ToolChoice | NotGiven = NOT_GIVEN,
-        response_format: dict | None = None,
+        response_format: ResponseFormat | NotGiven = NOT_GIVEN,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
         skip_cutoff: bool = False,
-        **kwargs,
+        audio: Optional[ChatCompletionAudioParam] | OpenAINotGiven = NOT_GIVEN,
+        frequency_penalty: Optional[float] | OpenAINotGiven = NOT_GIVEN,
+        logit_bias: Optional[Dict[str, int]] | OpenAINotGiven = NOT_GIVEN,
+        logprobs: Optional[bool] | OpenAINotGiven = NOT_GIVEN,
+        max_completion_tokens: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        metadata: Optional[Metadata] | OpenAINotGiven = NOT_GIVEN,
+        modalities: Optional[List[ChatCompletionModality]] | OpenAINotGiven = NOT_GIVEN,
+        n: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        parallel_tool_calls: bool | OpenAINotGiven = NOT_GIVEN,
+        prediction: Optional[ChatCompletionPredictionContentParam] | OpenAINotGiven = NOT_GIVEN,
+        presence_penalty: Optional[float] | OpenAINotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[ChatCompletionReasoningEffort] | OpenAINotGiven = NOT_GIVEN,
+        thinking: ThinkingConfigParam | None | NotGiven = NOT_GIVEN,
+        seed: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "default"]] | OpenAINotGiven = NOT_GIVEN,
+        stop: Union[Optional[str], List[str]] | OpenAINotGiven = NOT_GIVEN,
+        store: Optional[bool] | OpenAINotGiven = NOT_GIVEN,
+        top_logprobs: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        user: str | OpenAINotGiven = NOT_GIVEN,
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | OpenAINotGiven = NOT_GIVEN,
     ) -> ChatCompletionMessage | AsyncGenerator[ChatCompletionDeltaMessage, None]:
         pass
 
@@ -492,10 +724,33 @@ class BaseAsyncChatClient(ABC):
         max_tokens: int | None = None,
         tools: list | NotGiven = NOT_GIVEN,
         tool_choice: ToolChoice | NotGiven = NOT_GIVEN,
-        response_format: dict | None = None,
+        response_format: ResponseFormat | NotGiven = NOT_GIVEN,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
-        **kwargs,
+        skip_cutoff: bool = False,
+        audio: Optional[ChatCompletionAudioParam] | OpenAINotGiven = NOT_GIVEN,
+        frequency_penalty: Optional[float] | OpenAINotGiven = NOT_GIVEN,
+        logit_bias: Optional[Dict[str, int]] | OpenAINotGiven = NOT_GIVEN,
+        logprobs: Optional[bool] | OpenAINotGiven = NOT_GIVEN,
+        max_completion_tokens: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        metadata: Optional[Metadata] | OpenAINotGiven = NOT_GIVEN,
+        modalities: Optional[List[ChatCompletionModality]] | OpenAINotGiven = NOT_GIVEN,
+        n: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        parallel_tool_calls: bool | OpenAINotGiven = NOT_GIVEN,
+        prediction: Optional[ChatCompletionPredictionContentParam] | OpenAINotGiven = NOT_GIVEN,
+        presence_penalty: Optional[float] | OpenAINotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[ChatCompletionReasoningEffort] | OpenAINotGiven = NOT_GIVEN,
+        thinking: ThinkingConfigParam | None | NotGiven = NOT_GIVEN,
+        seed: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "default"]] | OpenAINotGiven = NOT_GIVEN,
+        stop: Union[Optional[str], List[str]] | OpenAINotGiven = NOT_GIVEN,
+        store: Optional[bool] | OpenAINotGiven = NOT_GIVEN,
+        top_logprobs: Optional[int] | OpenAINotGiven = NOT_GIVEN,
+        user: str | OpenAINotGiven = NOT_GIVEN,
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | OpenAINotGiven = NOT_GIVEN,
     ) -> AsyncGenerator[ChatCompletionDeltaMessage, None]:
         return await self.create_completion(
             messages=messages,
@@ -508,5 +763,28 @@ class BaseAsyncChatClient(ABC):
             response_format=response_format,
             stream_options=stream_options,
             top_p=top_p,
-            **kwargs,
+            skip_cutoff=skip_cutoff,
+            audio=audio,
+            frequency_penalty=frequency_penalty,
+            logit_bias=logit_bias,
+            logprobs=logprobs,
+            max_completion_tokens=max_completion_tokens,
+            metadata=metadata,
+            modalities=modalities,
+            n=n,
+            parallel_tool_calls=parallel_tool_calls,
+            prediction=prediction,
+            presence_penalty=presence_penalty,
+            reasoning_effort=reasoning_effort,
+            thinking=thinking,
+            seed=seed,
+            service_tier=service_tier,
+            stop=stop,
+            store=store,
+            top_logprobs=top_logprobs,
+            user=user,
+            extra_headers=extra_headers,
+            extra_query=extra_query,
+            extra_body=extra_body,
+            timeout=timeout,
         )