`nemo_microservices.resources.v2.inference.gateway.openai`#

Module Contents#

Classes#

`AsyncOpenAIResource`
`AsyncOpenAIResourceWithRawResponse`
`AsyncOpenAIResourceWithStreamingResponse`
`OpenAIResource`
`OpenAIResourceWithRawResponse`
`OpenAIResourceWithStreamingResponse`

API#

class nemo_microservices.resources.v2.inference.gateway.openai.AsyncOpenAIResource( client: nemo_microservices._client.AsyncNeMoMicroservices, )#

Bases: nemo_microservices._resource.AsyncAPIResource

Initialization

async delete( trailing_uri: str, *, extra_headers: nemo_microservices._types.Headers | None = None, extra_query: nemo_microservices._types.Query | None = None, extra_body: nemo_microservices._types.Body | None = None, timeout: float | httpx.Timeout | None | nemo_microservices._types.NotGiven = not_given, ) → object#

Proxy requests to OpenAI-compatible inference endpoints.

This is a stub implementation that returns request details.

Args: 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

async get( trailing_uri: str, *, extra_headers: nemo_microservices._types.Headers | None = None, extra_query: nemo_microservices._types.Query | None = None, extra_body: nemo_microservices._types.Body | None = None, timeout: float | httpx.Timeout | None | nemo_microservices._types.NotGiven = not_given, ) → object#

Proxy requests to OpenAI-compatible inference endpoints.

This is a stub implementation that returns request details.

Args: 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

async patch( trailing_uri: str, *, extra_headers: nemo_microservices._types.Headers | None = None, extra_query: nemo_microservices._types.Query | None = None, extra_body: nemo_microservices._types.Body | None = None, timeout: float | httpx.Timeout | None | nemo_microservices._types.NotGiven = not_given, ) → object#

Proxy requests to OpenAI-compatible inference endpoints.

This is a stub implementation that returns request details.

Args: 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

async post( trailing_uri: str, *, extra_headers: nemo_microservices._types.Headers | None = None, extra_query: nemo_microservices._types.Query | None = None, extra_body: nemo_microservices._types.Body | None = None, timeout: float | httpx.Timeout | None | nemo_microservices._types.NotGiven = not_given, ) → object#

Proxy requests to OpenAI-compatible inference endpoints.

This is a stub implementation that returns request details.

Args: 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

async put( trailing_uri: str, *, extra_headers: nemo_microservices._types.Headers | None = None, extra_query: nemo_microservices._types.Query | None = None, extra_body: nemo_microservices._types.Body | None = None, timeout: float | httpx.Timeout | None | nemo_microservices._types.NotGiven = not_given, ) → object#

Proxy requests to OpenAI-compatible inference endpoints.

This is a stub implementation that returns request details.

Args: 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

property with_raw_response: nemo_microservices.resources.v2.inference.gateway.openai.AsyncOpenAIResourceWithRawResponse#

This property can be used as a prefix for any HTTP method call to return the raw response object instead of the parsed content.

For more information, see https://docs.nvidia.com/nemo/microservices/latest/pysdk/index.html#accessing-raw-response-data-e-g-headers

property with_streaming_response: nemo_microservices.resources.v2.inference.gateway.openai.AsyncOpenAIResourceWithStreamingResponse#

An alternative to .with_raw_response that doesn’t eagerly read the response body.

For more information, see https://docs.nvidia.com/nemo/microservices/latest/pysdk/index.html#with_streaming_response

class nemo_microservices.resources.v2.inference.gateway.openai.AsyncOpenAIResourceWithRawResponse( openai: nemo_microservices.resources.v2.inference.gateway.openai.AsyncOpenAIResource, )#: Initialization

class nemo_microservices.resources.v2.inference.gateway.openai.AsyncOpenAIResourceWithStreamingResponse( openai: nemo_microservices.resources.v2.inference.gateway.openai.AsyncOpenAIResource, )#: Initialization

class nemo_microservices.resources.v2.inference.gateway.openai.OpenAIResource(client: nemo_microservices._client.NeMoMicroservices)#

Bases: nemo_microservices._resource.SyncAPIResource

Initialization

delete( trailing_uri: str, *, extra_headers: nemo_microservices._types.Headers | None = None, extra_query: nemo_microservices._types.Query | None = None, extra_body: nemo_microservices._types.Body | None = None, timeout: float | httpx.Timeout | None | nemo_microservices._types.NotGiven = not_given, ) → object#

Proxy requests to OpenAI-compatible inference endpoints.

This is a stub implementation that returns request details.

Args: 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

get( trailing_uri: str, *, extra_headers: nemo_microservices._types.Headers | None = None, extra_query: nemo_microservices._types.Query | None = None, extra_body: nemo_microservices._types.Body | None = None, timeout: float | httpx.Timeout | None | nemo_microservices._types.NotGiven = not_given, ) → object#

Proxy requests to OpenAI-compatible inference endpoints.

This is a stub implementation that returns request details.

Args: 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

patch( trailing_uri: str, *, extra_headers: nemo_microservices._types.Headers | None = None, extra_query: nemo_microservices._types.Query | None = None, extra_body: nemo_microservices._types.Body | None = None, timeout: float | httpx.Timeout | None | nemo_microservices._types.NotGiven = not_given, ) → object#

Proxy requests to OpenAI-compatible inference endpoints.

This is a stub implementation that returns request details.

Args: 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

post( trailing_uri: str, *, extra_headers: nemo_microservices._types.Headers | None = None, extra_query: nemo_microservices._types.Query | None = None, extra_body: nemo_microservices._types.Body | None = None, timeout: float | httpx.Timeout | None | nemo_microservices._types.NotGiven = not_given, ) → object#

Proxy requests to OpenAI-compatible inference endpoints.

This is a stub implementation that returns request details.

Args: 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

put( trailing_uri: str, *, extra_headers: nemo_microservices._types.Headers | None = None, extra_query: nemo_microservices._types.Query | None = None, extra_body: nemo_microservices._types.Body | None = None, timeout: float | httpx.Timeout | None | nemo_microservices._types.NotGiven = not_given, ) → object#

Proxy requests to OpenAI-compatible inference endpoints.

This is a stub implementation that returns request details.

Args: 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

property with_raw_response: nemo_microservices.resources.v2.inference.gateway.openai.OpenAIResourceWithRawResponse#

This property can be used as a prefix for any HTTP method call to return the raw response object instead of the parsed content.

For more information, see https://docs.nvidia.com/nemo/microservices/latest/pysdk/index.html#accessing-raw-response-data-e-g-headers

property with_streaming_response: nemo_microservices.resources.v2.inference.gateway.openai.OpenAIResourceWithStreamingResponse#

An alternative to .with_raw_response that doesn’t eagerly read the response body.

For more information, see https://docs.nvidia.com/nemo/microservices/latest/pysdk/index.html#with_streaming_response

class nemo_microservices.resources.v2.inference.gateway.openai.OpenAIResourceWithRawResponse( openai: nemo_microservices.resources.v2.inference.gateway.openai.OpenAIResource, )#: Initialization

class nemo_microservices.resources.v2.inference.gateway.openai.OpenAIResourceWithStreamingResponse( openai: nemo_microservices.resources.v2.inference.gateway.openai.OpenAIResource, )#: Initialization

nemo_microservices.resources.v2.inference.gateway.openai#

Module Contents#

Classes#

API#

`nemo_microservices.resources.v2.inference.gateway.openai`#