src/openai/resources/beta/assistants.py [214:358]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - self, assistant_id: str, *, description: Optional[str] | NotGiven = NOT_GIVEN, instructions: Optional[str] | NotGiven = NOT_GIVEN, metadata: Optional[Metadata] | NotGiven = NOT_GIVEN, model: Union[ str, Literal[ "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", ], ] | NotGiven = NOT_GIVEN, name: Optional[str] | NotGiven = NOT_GIVEN, reasoning_effort: Optional[ReasoningEffort] | NotGiven = NOT_GIVEN, response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN, temperature: Optional[float] | NotGiven = NOT_GIVEN, tool_resources: Optional[assistant_update_params.ToolResources] | NotGiven = NOT_GIVEN, tools: Iterable[AssistantToolParam] | NotGiven = NOT_GIVEN, top_p: Optional[float] | 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, ) -> 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: **o-series models only** Constrains effort on reasoning for [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently supported values are `low`, `medium`, and `high`. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. 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 {})} - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - src/openai/resources/beta/assistants.py [663:807]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - self, assistant_id: str, *, description: Optional[str] | NotGiven = NOT_GIVEN, instructions: Optional[str] | NotGiven = NOT_GIVEN, metadata: Optional[Metadata] | NotGiven = NOT_GIVEN, model: Union[ str, Literal[ "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", ], ] | NotGiven = NOT_GIVEN, name: Optional[str] | NotGiven = NOT_GIVEN, reasoning_effort: Optional[ReasoningEffort] | NotGiven = NOT_GIVEN, response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN, temperature: Optional[float] | NotGiven = NOT_GIVEN, tool_resources: Optional[assistant_update_params.ToolResources] | NotGiven = NOT_GIVEN, tools: Iterable[AssistantToolParam] | NotGiven = NOT_GIVEN, top_p: Optional[float] | 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, ) -> 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: **o-series models only** Constrains effort on reasoning for [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently supported values are `low`, `medium`, and `high`. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. 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 {})} - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -