nemo_gym.responses_converter

Shared Responses API ↔ Chat Completions converter.

This module contains the translation logic between OpenAI’s Responses API format and the Chat Completions API format. It is used by model servers that need to convert between the two formats (e.g. vllm_model, inference_provider).

Module Contents

Classes

Name	Description
`ResponsesConverter`	Converts between OpenAI Responses API and Chat Completions API formats.
`ResponsesConverterState`	-

Functions

Name	Description
`split_responses_input_output_items`	-

Data

VLLMConverter

VLLMConverterResponsesToChatCompletionsState

API

class nemo_gym.responses_converter.ResponsesConverter()

Bases: BaseModel

Converts between OpenAI Responses API and Chat Completions API formats.

THINK_TAG_PATTERN

ClassVar = re.compile('<think>(.*?)</think>', re.DOTALL)

return_token_id_information

bool

uses_reasoning_parser

bool = True

nemo_gym.responses_converter.ResponsesConverter._extract_reasoning_from_content(
    content: str
) -> typing.Tuple[typing.List[str], str]

nemo_gym.responses_converter.ResponsesConverter._format_function_call(
    m: dict,
    state: nemo_gym.responses_converter.ResponsesConverterState
) -> None

nemo_gym.responses_converter.ResponsesConverter._format_function_call_output(
    m: dict,
    state: nemo_gym.responses_converter.ResponsesConverterState
) -> None

nemo_gym.responses_converter.ResponsesConverter._format_message(
    m: dict,
    state: nemo_gym.responses_converter.ResponsesConverterState
) -> None

nemo_gym.responses_converter.ResponsesConverter._format_reasoning(
    m: dict,
    state: nemo_gym.responses_converter.ResponsesConverterState
) -> None

Collects text from ‘reasoning’ messages in responses api and appends it to a buffer.

This is done to group together one (or multiple) reasoning message(s) into a single, cohesive block, later prepending it to a subsequent assistant message. See: https://github.com/NVIDIA-NeMo/Gym/blob/main/docs/how-to-faq.md#faq-openai-responses-vs-chat-completions-api for an example of reasoning in responses api.

nemo_gym.responses_converter.ResponsesConverter._parse_think_tags(
    content: str
) -> typing.Tuple[typing.List[str], str]

classmethod

nemo_gym.responses_converter.ResponsesConverter._wrap_reasoning_in_think_tags(
    texts: typing.List[str]
) -> str

staticmethod

nemo_gym.responses_converter.ResponsesConverter.chat_completions_messages_to_responses_items(
    messages: typing.List[typing.Dict[str, typing.Any]]
) -> typing.List[nemo_gym.openai_utils.NeMoGymResponseOutputItem]

nemo_gym.responses_converter.ResponsesConverter.postprocess_assistant_message_dict(
    message_dict: typing.Dict[str, typing.Any]
) -> typing.List[nemo_gym.openai_utils.NeMoGymResponseOutputItem]

nemo_gym.responses_converter.ResponsesConverter.postprocess_chat_response(
    choice: nemo_gym.openai_utils.NeMoGymChoice
) -> typing.List[nemo_gym.openai_utils.NeMoGymResponseOutputItem]

nemo_gym.responses_converter.ResponsesConverter.responses_to_chat_completion_create_params(
    responses_create_params: nemo_gym.openai_utils.NeMoGymResponseCreateParamsNonStreaming
) -> nemo_gym.openai_utils.NeMoGymChatCompletionCreateParamsNonStreaming

class nemo_gym.responses_converter.ResponsesConverterState()

Bases: BaseModel

content_buffer

str = ''

messages

List[NeMoGymChatCompletionMessageParam] = Field(default_factory=list)

return_token_id_information

bool

token_information

Optional[TokenIDLogProbMixin] = None

tool_calls_buffer

List[NeMoGymChatCompletionMessageToolCallParam] = Field(default_factory=list)

nemo_gym.responses_converter.ResponsesConverterState.flush_assistant() -> None

nemo_gym.responses_converter.split_responses_input_output_items(
    items: typing.List[nemo_gym.openai_utils.NeMoGymResponseOutputItem]
) -> typing.Tuple[typing.List[nemo_gym.openai_utils.NeMoGymResponseOutputItem], typing.List[nemo_gym.openai_utils.NeMoGymResponseOutputItem]]

nemo_gym.responses_converter.VLLMConverter = ResponsesConverter

nemo_gym.responses_converter.VLLMConverterResponsesToChatCompletionsState = ResponsesConverterState