aimlapi-sdk-python 2.8.1b0__py3-none-any.whl

openai/resources/beta/assistants.py

@@ -0,0 +1,1049 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Union, Iterable, Optional
+from typing_extensions import Literal
+
+import httpx
+
+from ... import _legacy_response
+from ..._types import Body, Omit, Query, Headers, NotGiven, omit, not_given
+from ..._utils import maybe_transform, async_maybe_transform
+from ..._compat import cached_property
+from ..._resource import SyncAPIResource, AsyncAPIResource
+from ..._response import to_streamed_response_wrapper, async_to_streamed_response_wrapper
+from ...pagination import SyncCursorPage, AsyncCursorPage
+from ...types.beta import (
+    assistant_list_params,
+    assistant_create_params,
+    assistant_update_params,
+)
+from ..._base_client import AsyncPaginator, make_request_options
+from ...types.beta.assistant import Assistant
+from ...types.shared.chat_model import ChatModel
+from ...types.beta.assistant_deleted import AssistantDeleted
+from ...types.shared_params.metadata import Metadata
+from ...types.shared.reasoning_effort import ReasoningEffort
+from ...types.beta.assistant_tool_param import AssistantToolParam
+from ...types.beta.assistant_response_format_option_param import AssistantResponseFormatOptionParam
+
+__all__ = ["Assistants", "AsyncAssistants"]
+
+
+class Assistants(SyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> AssistantsWithRawResponse:
+        """
+        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/openai/openai-python#accessing-raw-response-data-eg-headers
+        """
+        return AssistantsWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> AssistantsWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/openai/openai-python#with_streaming_response
+        """
+        return AssistantsWithStreamingResponse(self)
+
+    def create(
+        self,
+        *,
+        model: Union[str, ChatModel],
+        description: Optional[str] | Omit = omit,
+        instructions: Optional[str] | Omit = omit,
+        metadata: Optional[Metadata] | Omit = omit,
+        name: Optional[str] | Omit = omit,
+        reasoning_effort: Optional[ReasoningEffort] | Omit = omit,
+        response_format: Optional[AssistantResponseFormatOptionParam] | Omit = omit,
+        temperature: Optional[float] | Omit = omit,
+        tool_resources: Optional[assistant_create_params.ToolResources] | Omit = omit,
+        tools: Iterable[AssistantToolParam] | Omit = omit,
+        top_p: Optional[float] | Omit = omit,
+        # 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,
+    ) -> Assistant:
+        """
+        Create an assistant with a model and instructions.
+
+        Args:
+          model: ID of the model to use. You can use the
+              [List models](https://platform.openai.com/docs/api-reference/models/list) API to
+              see all of your available models, or see our
+              [Model overview](https://platform.openai.com/docs/models) for descriptions of
+              them.
+
+          description: The description of the assistant. The maximum length is 512 characters.
+
+          instructions: The system instructions that the assistant uses. The maximum length is 256,000
+              characters.
+
+          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.
+
+          name: The name of the assistant. The maximum length is 256 characters.
+
+          reasoning_effort: Constrains effort on reasoning for
+              [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
+              supported values are `none`, `minimal`, `low`, `medium`, and `high`. Reducing
+              reasoning effort can result in faster responses and fewer tokens used on
+              reasoning in a response.
+
+              - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported
+                reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool
+                calls are supported for all reasoning values in gpt-5.1.
+              - All models before `gpt-5.1` default to `medium` reasoning effort, and do not
+                support `none`.
+              - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.
+
+          response_format: Specifies the format that the model must output. Compatible with
+              [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
+              [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
+              and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
+
+              Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
+              Outputs which ensures the model will match your supplied JSON schema. Learn more
+              in the
+              [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
+
+              Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the
+              message the model generates is valid JSON.
+
+              **Important:** when using JSON mode, you **must** also instruct the model to
+              produce JSON yourself via a system or user message. Without this, the model may
+              generate an unending stream of whitespace until the generation reaches the token
+              limit, resulting in a long-running and seemingly "stuck" request. Also note that
+              the message content may be partially cut off if `finish_reason="length"`, which
+              indicates the generation exceeded `max_tokens` or the conversation exceeded the
+              max context length.
+
+          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.
+
+          tool_resources: A set of resources that are used by the assistant's tools. The resources are
+              specific to the type of tool. For example, the `code_interpreter` tool requires
+              a list of file IDs, while the `file_search` tool requires a list of vector store
+              IDs.
+
+          tools: A list of tool enabled on the assistant. There can be a maximum of 128 tools per
+              assistant. Tools can be of types `code_interpreter`, `file_search`, or
+              `function`.
+
+          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.
+
+          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
+        """
+        extra_headers = {"OpenAI-Beta": "assistants=v2", **(extra_headers or {})}
+        return self._post(
+            "/assistants",
+            body=maybe_transform(
+                {
+                    "model": model,
+                    "description": description,
+                    "instructions": instructions,
+                    "metadata": metadata,
+                    "name": name,
+                    "reasoning_effort": reasoning_effort,
+                    "response_format": response_format,
+                    "temperature": temperature,
+                    "tool_resources": tool_resources,
+                    "tools": tools,
+                    "top_p": top_p,
+                },
+                assistant_create_params.AssistantCreateParams,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=Assistant,
+        )
+
+    def retrieve(
+        self,
+        assistant_id: str,
+        *,
+        # 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,
+    ) -> Assistant:
+        """
+        Retrieves an assistant.
+
+        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
+        """
+        if not assistant_id:
+            raise ValueError(f"Expected a non-empty value for `assistant_id` but received {assistant_id!r}")
+        extra_headers = {"OpenAI-Beta": "assistants=v2", **(extra_headers or {})}
+        return self._get(
+            f"/assistants/{assistant_id}",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=Assistant,
+        )
+
+    def update(
+        self,
+        assistant_id: str,
+        *,
+        description: Optional[str] | Omit = omit,
+        instructions: Optional[str] | Omit = omit,
+        metadata: Optional[Metadata] | Omit = omit,
+        model: Union[
+            str,
+            Literal[
+                "gpt-5",
+                "gpt-5-mini",
+                "gpt-5-nano",
+                "gpt-5-2025-08-07",
+                "gpt-5-mini-2025-08-07",
+                "gpt-5-nano-2025-08-07",
+                "gpt-4.1",
+                "gpt-4.1-mini",
+                "gpt-4.1-nano",
+                "gpt-4.1-2025-04-14",
+                "gpt-4.1-mini-2025-04-14",
+                "gpt-4.1-nano-2025-04-14",
+                "o3-mini",
+                "o3-mini-2025-01-31",
+                "o1",
+                "o1-2024-12-17",
+                "gpt-4o",
+                "gpt-4o-2024-11-20",
+                "gpt-4o-2024-08-06",
+                "gpt-4o-2024-05-13",
+                "gpt-4o-mini",
+                "gpt-4o-mini-2024-07-18",
+                "gpt-4.5-preview",
+                "gpt-4.5-preview-2025-02-27",
+                "gpt-4-turbo",
+                "gpt-4-turbo-2024-04-09",
+                "gpt-4-0125-preview",
+                "gpt-4-turbo-preview",
+                "gpt-4-1106-preview",
+                "gpt-4-vision-preview",
+                "gpt-4",
+                "gpt-4-0314",
+                "gpt-4-0613",
+                "gpt-4-32k",
+                "gpt-4-32k-0314",
+                "gpt-4-32k-0613",
+                "gpt-3.5-turbo",
+                "gpt-3.5-turbo-16k",
+                "gpt-3.5-turbo-0613",
+                "gpt-3.5-turbo-1106",
+                "gpt-3.5-turbo-0125",
+                "gpt-3.5-turbo-16k-0613",
+            ],
+        ]
+        | Omit = omit,
+        name: Optional[str] | Omit = omit,
+        reasoning_effort: Optional[ReasoningEffort] | Omit = omit,
+        response_format: Optional[AssistantResponseFormatOptionParam] | Omit = omit,
+        temperature: Optional[float] | Omit = omit,
+        tool_resources: Optional[assistant_update_params.ToolResources] | Omit = omit,
+        tools: Iterable[AssistantToolParam] | Omit = omit,
+        top_p: Optional[float] | Omit = omit,
+        # 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,
+    ) -> Assistant:
+        """Modifies an assistant.
+
+        Args:
+          description: The description of the assistant.
+
+        The maximum length is 512 characters.
+
+          instructions: The system instructions that the assistant uses. The maximum length is 256,000
+              characters.
+
+          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.
+
+          model: ID of the model to use. You can use the
+              [List models](https://platform.openai.com/docs/api-reference/models/list) API to
+              see all of your available models, or see our
+              [Model overview](https://platform.openai.com/docs/models) for descriptions of
+              them.
+
+          name: The name of the assistant. The maximum length is 256 characters.
+
+          reasoning_effort: Constrains effort on reasoning for
+              [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
+              supported values are `none`, `minimal`, `low`, `medium`, and `high`. Reducing
+              reasoning effort can result in faster responses and fewer tokens used on
+              reasoning in a response.
+
+              - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported
+                reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool
+                calls are supported for all reasoning values in gpt-5.1.
+              - All models before `gpt-5.1` default to `medium` reasoning effort, and do not
+                support `none`.
+              - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.
+
+          response_format: Specifies the format that the model must output. Compatible with
+              [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
+              [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
+              and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
+
+              Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
+              Outputs which ensures the model will match your supplied JSON schema. Learn more
+              in the
+              [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
+
+              Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the
+              message the model generates is valid JSON.
+
+              **Important:** when using JSON mode, you **must** also instruct the model to
+              produce JSON yourself via a system or user message. Without this, the model may
+              generate an unending stream of whitespace until the generation reaches the token
+              limit, resulting in a long-running and seemingly "stuck" request. Also note that
+              the message content may be partially cut off if `finish_reason="length"`, which
+              indicates the generation exceeded `max_tokens` or the conversation exceeded the
+              max context length.
+
+          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.
+
+          tool_resources: A set of resources that are used by the assistant's tools. The resources are
+              specific to the type of tool. For example, the `code_interpreter` tool requires
+              a list of file IDs, while the `file_search` tool requires a list of vector store
+              IDs.
+
+          tools: A list of tool enabled on the assistant. There can be a maximum of 128 tools per
+              assistant. Tools can be of types `code_interpreter`, `file_search`, or
+              `function`.
+
+          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.
+
+          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
+        """
+        if not assistant_id:
+            raise ValueError(f"Expected a non-empty value for `assistant_id` but received {assistant_id!r}")
+        extra_headers = {"OpenAI-Beta": "assistants=v2", **(extra_headers or {})}
+        return self._post(
+            f"/assistants/{assistant_id}",
+            body=maybe_transform(
+                {
+                    "description": description,
+                    "instructions": instructions,
+                    "metadata": metadata,
+                    "model": model,
+                    "name": name,
+                    "reasoning_effort": reasoning_effort,
+                    "response_format": response_format,
+                    "temperature": temperature,
+                    "tool_resources": tool_resources,
+                    "tools": tools,
+                    "top_p": top_p,
+                },
+                assistant_update_params.AssistantUpdateParams,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=Assistant,
+        )
+
+    def list(
+        self,
+        *,
+        after: str | Omit = omit,
+        before: str | Omit = omit,
+        limit: int | Omit = omit,
+        order: Literal["asc", "desc"] | Omit = omit,
+        # 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,
+    ) -> SyncCursorPage[Assistant]:
+        """Returns a list of assistants.
+
+        Args:
+          after: A cursor for use in pagination.
+
+        `after` is an object ID that defines your place
+              in the list. For instance, if you make a list request and receive 100 objects,
+              ending with obj_foo, your subsequent call can include after=obj_foo in order to
+              fetch the next page of the list.
+
+          before: A cursor for use in pagination. `before` is an object ID that defines your place
+              in the list. For instance, if you make a list request and receive 100 objects,
+              starting with obj_foo, your subsequent call can include before=obj_foo in order
+              to fetch the previous page of the list.
+
+          limit: A limit on the number of objects to be returned. Limit can range between 1 and
+              100, and the default is 20.
+
+          order: Sort order by the `created_at` timestamp of the objects. `asc` for ascending
+              order and `desc` for descending order.
+
+          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
+        """
+        extra_headers = {"OpenAI-Beta": "assistants=v2", **(extra_headers or {})}
+        return self._get_api_list(
+            "/assistants",
+            page=SyncCursorPage[Assistant],
+            options=make_request_options(
+                extra_headers=extra_headers,
+                extra_query=extra_query,
+                extra_body=extra_body,
+                timeout=timeout,
+                query=maybe_transform(
+                    {
+                        "after": after,
+                        "before": before,
+                        "limit": limit,
+                        "order": order,
+                    },
+                    assistant_list_params.AssistantListParams,
+                ),
+            ),
+            model=Assistant,
+        )
+
+    def delete(
+        self,
+        assistant_id: str,
+        *,
+        # 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,
+    ) -> AssistantDeleted:
+        """
+        Delete an assistant.
+
+        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
+        """
+        if not assistant_id:
+            raise ValueError(f"Expected a non-empty value for `assistant_id` but received {assistant_id!r}")
+        extra_headers = {"OpenAI-Beta": "assistants=v2", **(extra_headers or {})}
+        return self._delete(
+            f"/assistants/{assistant_id}",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=AssistantDeleted,
+        )
+
+
+class AsyncAssistants(AsyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> AsyncAssistantsWithRawResponse:
+        """
+        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/openai/openai-python#accessing-raw-response-data-eg-headers
+        """
+        return AsyncAssistantsWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> AsyncAssistantsWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/openai/openai-python#with_streaming_response
+        """
+        return AsyncAssistantsWithStreamingResponse(self)
+
+    async def create(
+        self,
+        *,
+        model: Union[str, ChatModel],
+        description: Optional[str] | Omit = omit,
+        instructions: Optional[str] | Omit = omit,
+        metadata: Optional[Metadata] | Omit = omit,
+        name: Optional[str] | Omit = omit,
+        reasoning_effort: Optional[ReasoningEffort] | Omit = omit,
+        response_format: Optional[AssistantResponseFormatOptionParam] | Omit = omit,
+        temperature: Optional[float] | Omit = omit,
+        tool_resources: Optional[assistant_create_params.ToolResources] | Omit = omit,
+        tools: Iterable[AssistantToolParam] | Omit = omit,
+        top_p: Optional[float] | Omit = omit,
+        # 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,
+    ) -> Assistant:
+        """
+        Create an assistant with a model and instructions.
+
+        Args:
+          model: ID of the model to use. You can use the
+              [List models](https://platform.openai.com/docs/api-reference/models/list) API to
+              see all of your available models, or see our
+              [Model overview](https://platform.openai.com/docs/models) for descriptions of
+              them.
+
+          description: The description of the assistant. The maximum length is 512 characters.
+
+          instructions: The system instructions that the assistant uses. The maximum length is 256,000
+              characters.
+
+          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.
+
+          name: The name of the assistant. The maximum length is 256 characters.
+
+          reasoning_effort: Constrains effort on reasoning for
+              [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
+              supported values are `none`, `minimal`, `low`, `medium`, and `high`. Reducing
+              reasoning effort can result in faster responses and fewer tokens used on
+              reasoning in a response.
+
+              - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported
+                reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool
+                calls are supported for all reasoning values in gpt-5.1.
+              - All models before `gpt-5.1` default to `medium` reasoning effort, and do not
+                support `none`.
+              - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.
+
+          response_format: Specifies the format that the model must output. Compatible with
+              [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
+              [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
+              and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
+
+              Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
+              Outputs which ensures the model will match your supplied JSON schema. Learn more
+              in the
+              [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
+
+              Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the
+              message the model generates is valid JSON.
+
+              **Important:** when using JSON mode, you **must** also instruct the model to
+              produce JSON yourself via a system or user message. Without this, the model may
+              generate an unending stream of whitespace until the generation reaches the token
+              limit, resulting in a long-running and seemingly "stuck" request. Also note that
+              the message content may be partially cut off if `finish_reason="length"`, which
+              indicates the generation exceeded `max_tokens` or the conversation exceeded the
+              max context length.
+
+          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.
+
+          tool_resources: A set of resources that are used by the assistant's tools. The resources are
+              specific to the type of tool. For example, the `code_interpreter` tool requires
+              a list of file IDs, while the `file_search` tool requires a list of vector store
+              IDs.
+
+          tools: A list of tool enabled on the assistant. There can be a maximum of 128 tools per
+              assistant. Tools can be of types `code_interpreter`, `file_search`, or
+              `function`.
+
+          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.
+
+          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
+        """
+        extra_headers = {"OpenAI-Beta": "assistants=v2", **(extra_headers or {})}
+        return await self._post(
+            "/assistants",
+            body=await async_maybe_transform(
+                {
+                    "model": model,
+                    "description": description,
+                    "instructions": instructions,
+                    "metadata": metadata,
+                    "name": name,
+                    "reasoning_effort": reasoning_effort,
+                    "response_format": response_format,
+                    "temperature": temperature,
+                    "tool_resources": tool_resources,
+                    "tools": tools,
+                    "top_p": top_p,
+                },
+                assistant_create_params.AssistantCreateParams,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=Assistant,
+        )
+
+    async def retrieve(
+        self,
+        assistant_id: str,
+        *,
+        # 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,
+    ) -> Assistant:
+        """
+        Retrieves an assistant.
+
+        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
+        """
+        if not assistant_id:
+            raise ValueError(f"Expected a non-empty value for `assistant_id` but received {assistant_id!r}")
+        extra_headers = {"OpenAI-Beta": "assistants=v2", **(extra_headers or {})}
+        return await self._get(
+            f"/assistants/{assistant_id}",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=Assistant,
+        )
+
+    async def update(
+        self,
+        assistant_id: str,
+        *,
+        description: Optional[str] | Omit = omit,
+        instructions: Optional[str] | Omit = omit,
+        metadata: Optional[Metadata] | Omit = omit,
+        model: Union[
+            str,
+            Literal[
+                "gpt-5",
+                "gpt-5-mini",
+                "gpt-5-nano",
+                "gpt-5-2025-08-07",
+                "gpt-5-mini-2025-08-07",
+                "gpt-5-nano-2025-08-07",
+                "gpt-4.1",
+                "gpt-4.1-mini",
+                "gpt-4.1-nano",
+                "gpt-4.1-2025-04-14",
+                "gpt-4.1-mini-2025-04-14",
+                "gpt-4.1-nano-2025-04-14",
+                "o3-mini",
+                "o3-mini-2025-01-31",
+                "o1",
+                "o1-2024-12-17",
+                "gpt-4o",
+                "gpt-4o-2024-11-20",
+                "gpt-4o-2024-08-06",
+                "gpt-4o-2024-05-13",
+                "gpt-4o-mini",
+                "gpt-4o-mini-2024-07-18",
+                "gpt-4.5-preview",
+                "gpt-4.5-preview-2025-02-27",
+                "gpt-4-turbo",
+                "gpt-4-turbo-2024-04-09",
+                "gpt-4-0125-preview",
+                "gpt-4-turbo-preview",
+                "gpt-4-1106-preview",
+                "gpt-4-vision-preview",
+                "gpt-4",
+                "gpt-4-0314",
+                "gpt-4-0613",
+                "gpt-4-32k",
+                "gpt-4-32k-0314",
+                "gpt-4-32k-0613",
+                "gpt-3.5-turbo",
+                "gpt-3.5-turbo-16k",
+                "gpt-3.5-turbo-0613",
+                "gpt-3.5-turbo-1106",
+                "gpt-3.5-turbo-0125",
+                "gpt-3.5-turbo-16k-0613",
+            ],
+        ]
+        | Omit = omit,
+        name: Optional[str] | Omit = omit,
+        reasoning_effort: Optional[ReasoningEffort] | Omit = omit,
+        response_format: Optional[AssistantResponseFormatOptionParam] | Omit = omit,
+        temperature: Optional[float] | Omit = omit,
+        tool_resources: Optional[assistant_update_params.ToolResources] | Omit = omit,
+        tools: Iterable[AssistantToolParam] | Omit = omit,
+        top_p: Optional[float] | Omit = omit,
+        # 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,
+    ) -> Assistant:
+        """Modifies an assistant.
+
+        Args:
+          description: The description of the assistant.
+
+        The maximum length is 512 characters.
+
+          instructions: The system instructions that the assistant uses. The maximum length is 256,000
+              characters.
+
+          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.
+
+          model: ID of the model to use. You can use the
+              [List models](https://platform.openai.com/docs/api-reference/models/list) API to
+              see all of your available models, or see our
+              [Model overview](https://platform.openai.com/docs/models) for descriptions of
+              them.
+
+          name: The name of the assistant. The maximum length is 256 characters.
+
+          reasoning_effort: Constrains effort on reasoning for
+              [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
+              supported values are `none`, `minimal`, `low`, `medium`, and `high`. Reducing
+              reasoning effort can result in faster responses and fewer tokens used on
+              reasoning in a response.
+
+              - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported
+                reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool
+                calls are supported for all reasoning values in gpt-5.1.
+              - All models before `gpt-5.1` default to `medium` reasoning effort, and do not
+                support `none`.
+              - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.
+
+          response_format: Specifies the format that the model must output. Compatible with
+              [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
+              [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
+              and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
+
+              Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
+              Outputs which ensures the model will match your supplied JSON schema. Learn more
+              in the
+              [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
+
+              Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the
+              message the model generates is valid JSON.
+
+              **Important:** when using JSON mode, you **must** also instruct the model to
+              produce JSON yourself via a system or user message. Without this, the model may
+              generate an unending stream of whitespace until the generation reaches the token
+              limit, resulting in a long-running and seemingly "stuck" request. Also note that
+              the message content may be partially cut off if `finish_reason="length"`, which
+              indicates the generation exceeded `max_tokens` or the conversation exceeded the
+              max context length.
+
+          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.
+
+          tool_resources: A set of resources that are used by the assistant's tools. The resources are
+              specific to the type of tool. For example, the `code_interpreter` tool requires
+              a list of file IDs, while the `file_search` tool requires a list of vector store
+              IDs.
+
+          tools: A list of tool enabled on the assistant. There can be a maximum of 128 tools per
+              assistant. Tools can be of types `code_interpreter`, `file_search`, or
+              `function`.
+
+          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.
+
+          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
+        """
+        if not assistant_id:
+            raise ValueError(f"Expected a non-empty value for `assistant_id` but received {assistant_id!r}")
+        extra_headers = {"OpenAI-Beta": "assistants=v2", **(extra_headers or {})}
+        return await self._post(
+            f"/assistants/{assistant_id}",
+            body=await async_maybe_transform(
+                {
+                    "description": description,
+                    "instructions": instructions,
+                    "metadata": metadata,
+                    "model": model,
+                    "name": name,
+                    "reasoning_effort": reasoning_effort,
+                    "response_format": response_format,
+                    "temperature": temperature,
+                    "tool_resources": tool_resources,
+                    "tools": tools,
+                    "top_p": top_p,
+                },
+                assistant_update_params.AssistantUpdateParams,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=Assistant,
+        )
+
+    def list(
+        self,
+        *,
+        after: str | Omit = omit,
+        before: str | Omit = omit,
+        limit: int | Omit = omit,
+        order: Literal["asc", "desc"] | Omit = omit,
+        # 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,
+    ) -> AsyncPaginator[Assistant, AsyncCursorPage[Assistant]]:
+        """Returns a list of assistants.
+
+        Args:
+          after: A cursor for use in pagination.
+
+        `after` is an object ID that defines your place
+              in the list. For instance, if you make a list request and receive 100 objects,
+              ending with obj_foo, your subsequent call can include after=obj_foo in order to
+              fetch the next page of the list.
+
+          before: A cursor for use in pagination. `before` is an object ID that defines your place
+              in the list. For instance, if you make a list request and receive 100 objects,
+              starting with obj_foo, your subsequent call can include before=obj_foo in order
+              to fetch the previous page of the list.
+
+          limit: A limit on the number of objects to be returned. Limit can range between 1 and
+              100, and the default is 20.
+
+          order: Sort order by the `created_at` timestamp of the objects. `asc` for ascending
+              order and `desc` for descending order.
+
+          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
+        """
+        extra_headers = {"OpenAI-Beta": "assistants=v2", **(extra_headers or {})}
+        return self._get_api_list(
+            "/assistants",
+            page=AsyncCursorPage[Assistant],
+            options=make_request_options(
+                extra_headers=extra_headers,
+                extra_query=extra_query,
+                extra_body=extra_body,
+                timeout=timeout,
+                query=maybe_transform(
+                    {
+                        "after": after,
+                        "before": before,
+                        "limit": limit,
+                        "order": order,
+                    },
+                    assistant_list_params.AssistantListParams,
+                ),
+            ),
+            model=Assistant,
+        )
+
+    async def delete(
+        self,
+        assistant_id: str,
+        *,
+        # 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,
+    ) -> AssistantDeleted:
+        """
+        Delete an assistant.
+
+        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
+        """
+        if not assistant_id:
+            raise ValueError(f"Expected a non-empty value for `assistant_id` but received {assistant_id!r}")
+        extra_headers = {"OpenAI-Beta": "assistants=v2", **(extra_headers or {})}
+        return await self._delete(
+            f"/assistants/{assistant_id}",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=AssistantDeleted,
+        )
+
+
+class AssistantsWithRawResponse:
+    def __init__(self, assistants: Assistants) -> None:
+        self._assistants = assistants
+
+        self.create = _legacy_response.to_raw_response_wrapper(
+            assistants.create,
+        )
+        self.retrieve = _legacy_response.to_raw_response_wrapper(
+            assistants.retrieve,
+        )
+        self.update = _legacy_response.to_raw_response_wrapper(
+            assistants.update,
+        )
+        self.list = _legacy_response.to_raw_response_wrapper(
+            assistants.list,
+        )
+        self.delete = _legacy_response.to_raw_response_wrapper(
+            assistants.delete,
+        )
+
+
+class AsyncAssistantsWithRawResponse:
+    def __init__(self, assistants: AsyncAssistants) -> None:
+        self._assistants = assistants
+
+        self.create = _legacy_response.async_to_raw_response_wrapper(
+            assistants.create,
+        )
+        self.retrieve = _legacy_response.async_to_raw_response_wrapper(
+            assistants.retrieve,
+        )
+        self.update = _legacy_response.async_to_raw_response_wrapper(
+            assistants.update,
+        )
+        self.list = _legacy_response.async_to_raw_response_wrapper(
+            assistants.list,
+        )
+        self.delete = _legacy_response.async_to_raw_response_wrapper(
+            assistants.delete,
+        )
+
+
+class AssistantsWithStreamingResponse:
+    def __init__(self, assistants: Assistants) -> None:
+        self._assistants = assistants
+
+        self.create = to_streamed_response_wrapper(
+            assistants.create,
+        )
+        self.retrieve = to_streamed_response_wrapper(
+            assistants.retrieve,
+        )
+        self.update = to_streamed_response_wrapper(
+            assistants.update,
+        )
+        self.list = to_streamed_response_wrapper(
+            assistants.list,
+        )
+        self.delete = to_streamed_response_wrapper(
+            assistants.delete,
+        )
+
+
+class AsyncAssistantsWithStreamingResponse:
+    def __init__(self, assistants: AsyncAssistants) -> None:
+        self._assistants = assistants
+
+        self.create = async_to_streamed_response_wrapper(
+            assistants.create,
+        )
+        self.retrieve = async_to_streamed_response_wrapper(
+            assistants.retrieve,
+        )
+        self.update = async_to_streamed_response_wrapper(
+            assistants.update,
+        )
+        self.list = async_to_streamed_response_wrapper(
+            assistants.list,
+        )
+        self.delete = async_to_streamed_response_wrapper(
+            assistants.delete,
+        )