langgraph_agent_toolkit.core.models.chat_openai module

class langgraph_agent_toolkit.core.models.chat_openai.AzureChatOpenAIPatched(*args, name=None, cache=None, verbose=<factory>, callbacks=None, tags=None, metadata=None, custom_get_token_ids=None, rate_limiter=None, disable_streaming=False, output_version=<factory>, profile=None, client=None, async_client=None, root_client=None, root_async_client=None, model=None, temperature=None, model_kwargs=<factory>, api_key=<factory>, base_url=None, organization=None, openai_proxy=<factory>, timeout=None, stream_usage=None, max_retries=None, presence_penalty=None, frequency_penalty=None, seed=None, logprobs=None, top_logprobs=None, logit_bias=None, streaming=False, n=None, top_p=None, max_completion_tokens=None, reasoning_effort=None, reasoning=None, verbosity=None, tiktoken_model_name=None, default_headers=None, default_query=None, http_client=None, http_async_client=None, http_socket_options=None, stream_chunk_timeout=<factory>, stop_sequences=None, extra_body=None, include_response_headers=False, disabled_params=None, context_management=None, include=None, prompt_cache_options=None, service_tier=None, store=None, truncation=None, use_previous_response_id=False, use_responses_api=None, azure_endpoint=<factory>, azure_deployment=None, api_version=<factory>, azure_ad_token=<factory>, azure_ad_token_provider=None, azure_ad_async_token_provider=None, model_version='', openai_api_type=<factory>, validate_base_url=True)

Bases: _StreamCompatibility, AzureChatOpenAI

Preserve refusal text and normalize transport failures in Azure streams.

Parameters:

• args (Any)

• name (str | None)

• cache (BaseCache | bool | None)

• verbose (bool)

• callbacks (list[BaseCallbackHandler] | BaseCallbackManager | None)

• tags (list[str] | None)

• metadata (dict[str, Any] | None)

• custom_get_token_ids (Callable[[str], list[int]] | None)

• rate_limiter (BaseRateLimiter | None)

• disable_streaming (bool | Literal['tool_calling'])

• output_version (str | None)

• profile (ModelProfile | None)

• client (Any)

• async_client (Any)

• root_client (Any)

• root_async_client (Any)

• model (str | None)

• temperature (float | None)

• model_kwargs (dict[str, Any])

• api_key (SecretStr | None)

• base_url (str | None)

• organization (str | None)

• openai_proxy (str | None)

• timeout (float | tuple[float, float] | Any | None)

• stream_usage (bool | None)

• max_retries (int | None)

• presence_penalty (float | None)

• frequency_penalty (float | None)

• seed (int | None)

• logprobs (bool | None)

• top_logprobs (int | None)

• logit_bias (dict[int, int] | None)

• streaming (bool)

• n (int | None)

• top_p (float | None)

• max_completion_tokens (int | None)

• reasoning_effort (str | None)

• reasoning (dict[str, Any] | None)

• verbosity (str | None)

• tiktoken_model_name (str | None)

• default_headers (Mapping[str, str] | None)

• default_query (Mapping[str, object] | None)

• http_client (Any | None)

• http_async_client (Any | None)

• http_socket_options (Sequence[tuple[int, int, int]] | None)

• stream_chunk_timeout (float | None)

• stop_sequences (list[str] | str | None)

• extra_body (Mapping[str, Any] | None)

• include_response_headers (bool)

• disabled_params (dict[str, Any] | None)

• context_management (list[dict[str, Any]] | None)

• include (list[str] | None)

• prompt_cache_options (dict[str, Any] | None)

• service_tier (str | None)

• store (bool | None)

• truncation (str | None)

• use_previous_response_id (bool)

• use_responses_api (bool | None)

• azure_endpoint (str | None)

• azure_deployment (str | None)

• api_version (str | None)

• azure_ad_token (SecretStr | None)

• azure_ad_token_provider (Callable[[], str] | None)

• azure_ad_async_token_provider (Callable[[], Awaitable[str]] | None)

• model_version (str)

• openai_api_type (str | None)

• validate_base_url (bool)

model_config = {'arbitrary_types_allowed': True, 'extra': 'ignore', 'populate_by_name': True, 'protected_namespaces': (), 'validate_by_alias': True, 'validate_by_name': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class langgraph_agent_toolkit.core.models.chat_openai.ChatOpenAIPatched(*args, name=None, cache=None, verbose=<factory>, callbacks=None, tags=None, metadata=None, custom_get_token_ids=None, rate_limiter=None, disable_streaming=False, output_version=<factory>, profile=None, client=None, async_client=None, root_client=None, root_async_client=None, model='gpt-3.5-turbo', temperature=None, model_kwargs=<factory>, api_key=None, base_url=None, organization=None, openai_proxy=<factory>, timeout=None, stream_usage=None, max_retries=None, presence_penalty=None, frequency_penalty=None, seed=None, logprobs=None, top_logprobs=None, logit_bias=None, streaming=False, n=None, top_p=None, max_completion_tokens=None, reasoning_effort=None, reasoning=None, verbosity=None, tiktoken_model_name=None, default_headers=None, default_query=None, http_client=None, http_async_client=None, http_socket_options=None, stream_chunk_timeout=<factory>, stop_sequences=None, extra_body=None, include_response_headers=False, disabled_params=None, context_management=None, include=None, prompt_cache_options=None, service_tier=None, store=None, truncation=None, use_previous_response_id=False, use_responses_api=None)

Bases: _StreamCompatibility, ChatOpenAI

Parameters:

• args (Any)

• name (str | None)

• cache (BaseCache | bool | None)

• verbose (bool)

• callbacks (list[BaseCallbackHandler] | BaseCallbackManager | None)

• tags (list[str] | None)

• metadata (dict[str, Any] | None)

• custom_get_token_ids (Callable[[str], list[int]] | None)

• rate_limiter (BaseRateLimiter | None)

• disable_streaming (bool | Literal['tool_calling'])

• output_version (str | None)

• profile (ModelProfile | None)

• client (Any)

• async_client (Any)

• root_client (Any)

• root_async_client (Any)

• model (str)

• temperature (float | None)

• model_kwargs (dict[str, Any])

• api_key (SecretStr | None | Callable[[], str] | Callable[[], Awaitable[str]])

• base_url (str | None)

• organization (str | None)

• openai_proxy (str | None)

• timeout (float | tuple[float, float] | Any | None)

• stream_usage (bool | None)

• max_retries (int | None)

• presence_penalty (float | None)

• frequency_penalty (float | None)

• seed (int | None)

• logprobs (bool | None)

• top_logprobs (int | None)

• logit_bias (dict[int, int] | None)

• streaming (bool)

• n (int | None)

• top_p (float | None)

• max_completion_tokens (int | None)

• reasoning_effort (str | None)

• reasoning (dict[str, Any] | None)

• verbosity (str | None)

• tiktoken_model_name (str | None)

• default_headers (Mapping[str, str] | None)

• default_query (Mapping[str, object] | None)

• http_client (Any | None)

• http_async_client (Any | None)

• http_socket_options (Sequence[tuple[int, int, int]] | None)

• stream_chunk_timeout (float | None)

• stop_sequences (list[str] | str | None)

• extra_body (Mapping[str, Any] | None)

• include_response_headers (bool)

• disabled_params (dict[str, Any] | None)

• context_management (list[dict[str, Any]] | None)

• include (list[str] | None)

• prompt_cache_options (dict[str, Any] | None)

• service_tier (str | None)

• store (bool | None)

• truncation (str | None)

• use_previous_response_id (bool)

• use_responses_api (bool | None)

model_config = {'arbitrary_types_allowed': True, 'extra': 'ignore', 'populate_by_name': True, 'protected_namespaces': (), 'validate_by_alias': True, 'validate_by_name': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].