c63a5cfe-b235-4fbe-8bbb-82a9e02a482a-python 0.1.0a6__py3-none-any.whl → 0.1.0a7__py3-none-any.whl

gradientai/resources/agents/chat/completions.py

@@ -0,0 +1,385 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Dict, List, Union, Iterable, Optional
+
+import httpx
+
+from ...._types import NOT_GIVEN, Body, Query, Headers, NotGiven
+from ...._utils import maybe_transform, async_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 ...._base_client import make_request_options
+from ....types.agents.chat import completion_create_params
+from ....types.agents.chat.completion_create_response import CompletionCreateResponse
+
+__all__ = ["CompletionsResource", "AsyncCompletionsResource"]
+
+
+class CompletionsResource(SyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> CompletionsResourceWithRawResponse:
+        """
+        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://www.github.com/digitalocean/gradientai-python#accessing-raw-response-data-eg-headers
+        """
+        return CompletionsResourceWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> CompletionsResourceWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/digitalocean/gradientai-python#with_streaming_response
+        """
+        return CompletionsResourceWithStreamingResponse(self)
+
+    def create(
+        self,
+        *,
+        messages: Iterable[completion_create_params.Message],
+        model: str,
+        frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
+        logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
+        logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
+        max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
+        max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
+        metadata: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN,
+        n: Optional[int] | NotGiven = NOT_GIVEN,
+        presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
+        stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
+        stream: Optional[bool] | NotGiven = NOT_GIVEN,
+        stream_options: Optional[completion_create_params.StreamOptions] | NotGiven = NOT_GIVEN,
+        temperature: Optional[float] | NotGiven = NOT_GIVEN,
+        top_logprobs: Optional[int] | NotGiven = NOT_GIVEN,
+        top_p: Optional[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,
+    ) -> CompletionCreateResponse:
+        """
+        Creates a model response for the given chat conversation.
+
+        Args:
+          messages: A list of messages comprising the conversation so far.
+
+          model: Model ID used to generate the response.
+
+          frequency_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on their
+              existing frequency in the text so far, decreasing the model's likelihood to
+              repeat the same line verbatim.
+
+          logit_bias: Modify the likelihood of specified tokens appearing in the completion.
+
+              Accepts a JSON object that maps tokens (specified by their token ID in the
+              tokenizer) to an associated bias value from -100 to 100. Mathematically, the
+              bias is added to the logits generated by the model prior to sampling. The exact
+              effect will vary per model, but values between -1 and 1 should decrease or
+              increase likelihood of selection; values like -100 or 100 should result in a ban
+              or exclusive selection of the relevant token.
+
+          logprobs: Whether to return log probabilities of the output tokens or not. If true,
+              returns the log probabilities of each output token returned in the `content` of
+              `message`.
+
+          max_completion_tokens: The maximum number of completion tokens that may be used over the course of the
+              run. The run will make a best effort to use only the number of completion tokens
+              specified, across multiple turns of the run.
+
+          max_tokens: The maximum number of tokens that can be generated in the completion.
+
+              The token count of your prompt plus `max_tokens` cannot exceed the model's
+              context length.
+
+          metadata: Set of 16 key-value pairs that can be attached to an object. This can be useful
+              for storing additional information about the object in a structured format, and
+              querying for objects via API or the dashboard.
+
+              Keys are strings with a maximum length of 64 characters. Values are strings with
+              a maximum length of 512 characters.
+
+          n: How many chat completion choices to generate for each input message. Note that
+              you will be charged based on the number of generated tokens across all of the
+              choices. Keep `n` as `1` to minimize costs.
+
+          presence_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on
+              whether they appear in the text so far, increasing the model's likelihood to
+              talk about new topics.
+
+          stop: Up to 4 sequences where the API will stop generating further tokens. The
+              returned text will not contain the stop sequence.
+
+          stream: If set to true, the model response data will be streamed to the client as it is
+              generated using server-sent events.
+
+          stream_options: Options for streaming response. Only set this when you set `stream: true`.
+
+          temperature: What sampling temperature to use, between 0 and 2. Higher values like 0.8 will
+              make the output more random, while lower values like 0.2 will make it more
+              focused and deterministic. We generally recommend altering this or `top_p` but
+              not both.
+
+          top_logprobs: An integer between 0 and 20 specifying the number of most likely tokens to
+              return at each token position, each with an associated log probability.
+              `logprobs` must be set to `true` if this parameter is used.
+
+          top_p: An alternative to sampling with temperature, called nucleus sampling, where the
+              model considers the results of the tokens with top_p probability mass. So 0.1
+              means only the tokens comprising the top 10% probability mass are considered.
+
+              We generally recommend altering this or `temperature` but not both.
+
+          user: A unique identifier representing your end-user, which can help DigitalOcean to
+              monitor and detect abuse.
+
+          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(
+            "/chat/completions"
+            if self._client._base_url_overridden
+            else "https://inference.do-ai.run/v1/chat/completions",
+            body=maybe_transform(
+                {
+                    "messages": messages,
+                    "model": model,
+                    "frequency_penalty": frequency_penalty,
+                    "logit_bias": logit_bias,
+                    "logprobs": logprobs,
+                    "max_completion_tokens": max_completion_tokens,
+                    "max_tokens": max_tokens,
+                    "metadata": metadata,
+                    "n": n,
+                    "presence_penalty": presence_penalty,
+                    "stop": stop,
+                    "stream": stream,
+                    "stream_options": stream_options,
+                    "temperature": temperature,
+                    "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=CompletionCreateResponse,
+        )
+
+
+class AsyncCompletionsResource(AsyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> AsyncCompletionsResourceWithRawResponse:
+        """
+        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://www.github.com/digitalocean/gradientai-python#accessing-raw-response-data-eg-headers
+        """
+        return AsyncCompletionsResourceWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> AsyncCompletionsResourceWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/digitalocean/gradientai-python#with_streaming_response
+        """
+        return AsyncCompletionsResourceWithStreamingResponse(self)
+
+    async def create(
+        self,
+        *,
+        messages: Iterable[completion_create_params.Message],
+        model: str,
+        frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
+        logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
+        logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
+        max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
+        max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
+        metadata: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN,
+        n: Optional[int] | NotGiven = NOT_GIVEN,
+        presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
+        stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
+        stream: Optional[bool] | NotGiven = NOT_GIVEN,
+        stream_options: Optional[completion_create_params.StreamOptions] | NotGiven = NOT_GIVEN,
+        temperature: Optional[float] | NotGiven = NOT_GIVEN,
+        top_logprobs: Optional[int] | NotGiven = NOT_GIVEN,
+        top_p: Optional[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,
+    ) -> CompletionCreateResponse:
+        """
+        Creates a model response for the given chat conversation.
+
+        Args:
+          messages: A list of messages comprising the conversation so far.
+
+          model: Model ID used to generate the response.
+
+          frequency_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on their
+              existing frequency in the text so far, decreasing the model's likelihood to
+              repeat the same line verbatim.
+
+          logit_bias: Modify the likelihood of specified tokens appearing in the completion.
+
+              Accepts a JSON object that maps tokens (specified by their token ID in the
+              tokenizer) to an associated bias value from -100 to 100. Mathematically, the
+              bias is added to the logits generated by the model prior to sampling. The exact
+              effect will vary per model, but values between -1 and 1 should decrease or
+              increase likelihood of selection; values like -100 or 100 should result in a ban
+              or exclusive selection of the relevant token.
+
+          logprobs: Whether to return log probabilities of the output tokens or not. If true,
+              returns the log probabilities of each output token returned in the `content` of
+              `message`.
+
+          max_completion_tokens: The maximum number of completion tokens that may be used over the course of the
+              run. The run will make a best effort to use only the number of completion tokens
+              specified, across multiple turns of the run.
+
+          max_tokens: The maximum number of tokens that can be generated in the completion.
+
+              The token count of your prompt plus `max_tokens` cannot exceed the model's
+              context length.
+
+          metadata: Set of 16 key-value pairs that can be attached to an object. This can be useful
+              for storing additional information about the object in a structured format, and
+              querying for objects via API or the dashboard.
+
+              Keys are strings with a maximum length of 64 characters. Values are strings with
+              a maximum length of 512 characters.
+
+          n: How many chat completion choices to generate for each input message. Note that
+              you will be charged based on the number of generated tokens across all of the
+              choices. Keep `n` as `1` to minimize costs.
+
+          presence_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on
+              whether they appear in the text so far, increasing the model's likelihood to
+              talk about new topics.
+
+          stop: Up to 4 sequences where the API will stop generating further tokens. The
+              returned text will not contain the stop sequence.
+
+          stream: If set to true, the model response data will be streamed to the client as it is
+              generated using server-sent events.
+
+          stream_options: Options for streaming response. Only set this when you set `stream: true`.
+
+          temperature: What sampling temperature to use, between 0 and 2. Higher values like 0.8 will
+              make the output more random, while lower values like 0.2 will make it more
+              focused and deterministic. We generally recommend altering this or `top_p` but
+              not both.
+
+          top_logprobs: An integer between 0 and 20 specifying the number of most likely tokens to
+              return at each token position, each with an associated log probability.
+              `logprobs` must be set to `true` if this parameter is used.
+
+          top_p: An alternative to sampling with temperature, called nucleus sampling, where the
+              model considers the results of the tokens with top_p probability mass. So 0.1
+              means only the tokens comprising the top 10% probability mass are considered.
+
+              We generally recommend altering this or `temperature` but not both.
+
+          user: A unique identifier representing your end-user, which can help DigitalOcean to
+              monitor and detect abuse.
+
+          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(
+            "/chat/completions"
+            if self._client._base_url_overridden
+            else "https://inference.do-ai.run/v1/chat/completions",
+            body=await async_maybe_transform(
+                {
+                    "messages": messages,
+                    "model": model,
+                    "frequency_penalty": frequency_penalty,
+                    "logit_bias": logit_bias,
+                    "logprobs": logprobs,
+                    "max_completion_tokens": max_completion_tokens,
+                    "max_tokens": max_tokens,
+                    "metadata": metadata,
+                    "n": n,
+                    "presence_penalty": presence_penalty,
+                    "stop": stop,
+                    "stream": stream,
+                    "stream_options": stream_options,
+                    "temperature": temperature,
+                    "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=CompletionCreateResponse,
+        )
+
+
+class CompletionsResourceWithRawResponse:
+    def __init__(self, completions: CompletionsResource) -> None:
+        self._completions = completions
+
+        self.create = to_raw_response_wrapper(
+            completions.create,
+        )
+
+
+class AsyncCompletionsResourceWithRawResponse:
+    def __init__(self, completions: AsyncCompletionsResource) -> None:
+        self._completions = completions
+
+        self.create = async_to_raw_response_wrapper(
+            completions.create,
+        )
+
+
+class CompletionsResourceWithStreamingResponse:
+    def __init__(self, completions: CompletionsResource) -> None:
+        self._completions = completions
+
+        self.create = to_streamed_response_wrapper(
+            completions.create,
+        )
+
+
+class AsyncCompletionsResourceWithStreamingResponse:
+    def __init__(self, completions: AsyncCompletionsResource) -> None:
+        self._completions = completions
+
+        self.create = async_to_streamed_response_wrapper(
+            completions.create,
+        )

gradientai/resources/models.py

@@ -2,9 +2,14 @@
 
 from __future__ import annotations
 
+from typing import List
+from typing_extensions import Literal
+
 import httpx
 
+from ..types import model_list_params
 from .._types import NOT_GIVEN, Body, Query, Headers, NotGiven
+from .._utils import maybe_transform, async_maybe_transform
 from .._compat import cached_property
 from .._resource import SyncAPIResource, AsyncAPIResource
 from .._response import (
@@ -13,7 +18,6 @@ from .._response import (
     async_to_raw_response_wrapper,
     async_to_streamed_response_wrapper,
 )
-from ..types.model import Model
 from .._base_client import make_request_options
 from ..types.model_list_response import ModelListResponse
 
@@ -40,22 +44,52 @@ class ModelsResource(SyncAPIResource):
         """
         return ModelsResourceWithStreamingResponse(self)
 
-    def retrieve(
+    def list(
         self,
-        model: str,
         *,
+        page: int | NotGiven = NOT_GIVEN,
+        per_page: int | NotGiven = NOT_GIVEN,
+        public_only: bool | NotGiven = NOT_GIVEN,
+        usecases: List[
+            Literal[
+                "MODEL_USECASE_UNKNOWN",
+                "MODEL_USECASE_AGENT",
+                "MODEL_USECASE_FINETUNED",
+                "MODEL_USECASE_KNOWLEDGEBASE",
+                "MODEL_USECASE_GUARDRAIL",
+                "MODEL_USECASE_REASONING",
+                "MODEL_USECASE_SERVERLESS",
+            ]
+        ]
+        | 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,
-    ) -> Model:
+    ) -> ModelListResponse:
         """
-        Retrieves a model instance, providing basic information about the model such as
-        the owner and permissioning.
+        To list all models, send a GET request to `/v2/gen-ai/models`.
 
         Args:
+          page: page number.
+
+          per_page: items per page.
+
+          public_only: only include models that are publicly available.
+
+          usecases: include only models defined for the listed usecases.
+
+              - MODEL_USECASE_UNKNOWN: The use case of the model is unknown
+              - MODEL_USECASE_AGENT: The model maybe used in an agent
+              - MODEL_USECASE_FINETUNED: The model maybe used for fine tuning
+              - MODEL_USECASE_KNOWLEDGEBASE: The model maybe used for knowledge bases
+                (embedding models)
+              - MODEL_USECASE_GUARDRAIL: The model maybe used for guardrails
+              - MODEL_USECASE_REASONING: The model usecase for reasoning
+              - MODEL_USECASE_SERVERLESS: The model usecase for serverless inference
+
           extra_headers: Send extra headers
 
           extra_query: Add additional query parameters to the request
@@ -64,36 +98,24 @@ class ModelsResource(SyncAPIResource):
 
           timeout: Override the client-level default timeout for this request, in seconds
         """
-        if not model:
-            raise ValueError(f"Expected a non-empty value for `model` but received {model!r}")
         return self._get(
-            f"/models/{model}"
+            "/v2/gen-ai/models"
             if self._client._base_url_overridden
-            else f"https://inference.do-ai.run/v1/models/{model}",
+            else "https://api.digitalocean.com/v2/gen-ai/models",
             options=make_request_options(
-                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
-            ),
-            cast_to=Model,
-        )
-
-    def list(
-        self,
-        *,
-        # 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,
-    ) -> ModelListResponse:
-        """
-        Lists the currently available models, and provides basic information about each
-        one such as the owner and availability.
-        """
-        return self._get(
-            "/models" if self._client._base_url_overridden else "https://inference.do-ai.run/v1/models",
-            options=make_request_options(
-                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+                extra_headers=extra_headers,
+                extra_query=extra_query,
+                extra_body=extra_body,
+                timeout=timeout,
+                query=maybe_transform(
+                    {
+                        "page": page,
+                        "per_page": per_page,
+                        "public_only": public_only,
+                        "usecases": usecases,
+                    },
+                    model_list_params.ModelListParams,
+                ),
             ),
             cast_to=ModelListResponse,
         )
@@ -119,22 +141,52 @@ class AsyncModelsResource(AsyncAPIResource):
         """
         return AsyncModelsResourceWithStreamingResponse(self)
 
-    async def retrieve(
+    async def list(
         self,
-        model: str,
         *,
+        page: int | NotGiven = NOT_GIVEN,
+        per_page: int | NotGiven = NOT_GIVEN,
+        public_only: bool | NotGiven = NOT_GIVEN,
+        usecases: List[
+            Literal[
+                "MODEL_USECASE_UNKNOWN",
+                "MODEL_USECASE_AGENT",
+                "MODEL_USECASE_FINETUNED",
+                "MODEL_USECASE_KNOWLEDGEBASE",
+                "MODEL_USECASE_GUARDRAIL",
+                "MODEL_USECASE_REASONING",
+                "MODEL_USECASE_SERVERLESS",
+            ]
+        ]
+        | 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,
-    ) -> Model:
+    ) -> ModelListResponse:
         """
-        Retrieves a model instance, providing basic information about the model such as
-        the owner and permissioning.
+        To list all models, send a GET request to `/v2/gen-ai/models`.
 
         Args:
+          page: page number.
+
+          per_page: items per page.
+
+          public_only: only include models that are publicly available.
+
+          usecases: include only models defined for the listed usecases.
+
+              - MODEL_USECASE_UNKNOWN: The use case of the model is unknown
+              - MODEL_USECASE_AGENT: The model maybe used in an agent
+              - MODEL_USECASE_FINETUNED: The model maybe used for fine tuning
+              - MODEL_USECASE_KNOWLEDGEBASE: The model maybe used for knowledge bases
+                (embedding models)
+              - MODEL_USECASE_GUARDRAIL: The model maybe used for guardrails
+              - MODEL_USECASE_REASONING: The model usecase for reasoning
+              - MODEL_USECASE_SERVERLESS: The model usecase for serverless inference
+
           extra_headers: Send extra headers
 
           extra_query: Add additional query parameters to the request
@@ -143,36 +195,24 @@ class AsyncModelsResource(AsyncAPIResource):
 
           timeout: Override the client-level default timeout for this request, in seconds
         """
-        if not model:
-            raise ValueError(f"Expected a non-empty value for `model` but received {model!r}")
         return await self._get(
-            f"/models/{model}"
+            "/v2/gen-ai/models"
             if self._client._base_url_overridden
-            else f"https://inference.do-ai.run/v1/models/{model}",
-            options=make_request_options(
-                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
-            ),
-            cast_to=Model,
-        )
-
-    async def list(
-        self,
-        *,
-        # 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,
-    ) -> ModelListResponse:
-        """
-        Lists the currently available models, and provides basic information about each
-        one such as the owner and availability.
-        """
-        return await self._get(
-            "/models" if self._client._base_url_overridden else "https://inference.do-ai.run/v1/models",
+            else "https://api.digitalocean.com/v2/gen-ai/models",
             options=make_request_options(
-                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+                extra_headers=extra_headers,
+                extra_query=extra_query,
+                extra_body=extra_body,
+                timeout=timeout,
+                query=await async_maybe_transform(
+                    {
+                        "page": page,
+                        "per_page": per_page,
+                        "public_only": public_only,
+                        "usecases": usecases,
+                    },
+                    model_list_params.ModelListParams,
+                ),
             ),
             cast_to=ModelListResponse,
         )
@@ -182,9 +222,6 @@ class ModelsResourceWithRawResponse:
     def __init__(self, models: ModelsResource) -> None:
         self._models = models
 
-        self.retrieve = to_raw_response_wrapper(
-            models.retrieve,
-        )
         self.list = to_raw_response_wrapper(
             models.list,
         )
@@ -194,9 +231,6 @@ class AsyncModelsResourceWithRawResponse:
     def __init__(self, models: AsyncModelsResource) -> None:
         self._models = models
 
-        self.retrieve = async_to_raw_response_wrapper(
-            models.retrieve,
-        )
         self.list = async_to_raw_response_wrapper(
             models.list,
         )
@@ -206,9 +240,6 @@ class ModelsResourceWithStreamingResponse:
     def __init__(self, models: ModelsResource) -> None:
         self._models = models
 
-        self.retrieve = to_streamed_response_wrapper(
-            models.retrieve,
-        )
         self.list = to_streamed_response_wrapper(
             models.list,
         )
@@ -218,9 +249,6 @@ class AsyncModelsResourceWithStreamingResponse:
     def __init__(self, models: AsyncModelsResource) -> None:
         self._models = models
 
-        self.retrieve = async_to_streamed_response_wrapper(
-            models.retrieve,
-        )
         self.list = async_to_streamed_response_wrapper(
             models.list,
         )

gradientai/types/__init__.py

@@ -2,14 +2,15 @@
 
 from __future__ import annotations
 
-from .model import Model as Model
-from .shared import APIMeta as APIMeta, APILinks as APILinks
+from .shared import APIMeta as APIMeta, APILinks as APILinks, ChatCompletionTokenLogprob as ChatCompletionTokenLogprob
 from .api_agent import APIAgent as APIAgent
+from .api_model import APIModel as APIModel
 from .api_agreement import APIAgreement as APIAgreement
 from .api_workspace import APIWorkspace as APIWorkspace
 from .api_agent_model import APIAgentModel as APIAgentModel
 from .agent_list_params import AgentListParams as AgentListParams
 from .api_model_version import APIModelVersion as APIModelVersion
+from .model_list_params import ModelListParams as ModelListParams
 from .api_knowledge_base import APIKnowledgeBase as APIKnowledgeBase
 from .region_list_params import RegionListParams as RegionListParams
 from .agent_create_params import AgentCreateParams as AgentCreateParams