U ܟj@sddlmZddlmZmZmZddlmZddlZddl m Z ddl m Z m Z mZmZmZddlmZmZdd lmZdd lmZmZdd lmZmZdd lmZmZdd lm Z m!Z!m"Z"ddl#m$Z$m%Z%ddl&m'Z'ddl(m)Z)ddl*m+Z+ddl,m-Z-ddl.m/Z/ddl0m1Z1ddl2m3Z3ddgZ4GdddeZ5GdddeZ6GdddZ7GdddZ8GdddZ9Gd d!d!Z:dS)") annotations)UnionIterableOptional)LiteralN)_legacy_response) NOT_GIVENBodyQueryHeadersNotGiven)maybe_transformasync_maybe_transform)cached_property)SyncAPIResourceAsyncAPIResource)to_streamed_response_wrapper"async_to_streamed_response_wrapper)SyncCursorPageAsyncCursorPage)assistant_list_paramsassistant_create_paramsassistant_update_params)AsyncPaginatormake_request_options) Assistant) ChatModel)AssistantDeleted)Metadata)ReasoningEffort)AssistantToolParam)"AssistantResponseFormatOptionParam AssistantsAsyncAssistantsc@sFeZdZeddddZeddddZeeeeeeeeeeddded d d d d d d dddddddddddddZdddeddddddddddZeeeeeeeeeeedddeddd d d d d d ddd!dddddddd"d#d$Z eeeeddded%d&d&d'd(ddddd)d* d+d,Z dddeddddddd-dd.d/Z dS)0r#AssistantsWithRawResponsereturncCst|Sa This property can be used as a prefix for any HTTP method call to return the raw response object instead of the parsed content. For more information, see https://www.github.com/openai/openai-python#accessing-raw-response-data-eg-headers )r%selfr+D/tmp/pip-unpacked-wheel-2qj3ofc_/openai/resources/beta/assistants.pywith_raw_response&szAssistants.with_raw_responseAssistantsWithStreamingResponsecCst|Sz An alternative to `.with_raw_response` that doesn't eagerly read the response body. For more information, see https://www.github.com/openai/openai-python#with_streaming_response )r.r)r+r+r,with_streaming_response0sz"Assistants.with_streaming_responseN description instructionsmetadatanamereasoning_effortresponse_format temperaturetool_resourcestoolstop_p extra_headers extra_query extra_bodytimeoutUnion[str, ChatModel]Optional[str] | NotGivenOptional[Metadata] | NotGiven$Optional[ReasoningEffort] | NotGiven7Optional[AssistantResponseFormatOptionParam] | NotGivenOptional[float] | NotGiven:Optional[assistant_create_params.ToolResources] | NotGiven'Iterable[AssistantToolParam] | NotGivenHeaders | None Query | None Body | None'float | httpx.Timeout | None | NotGivenrmodelr2r3r4r5r6r7r8r9r:r;r<r=r>r?r'cCsNddi| p i} |jdt||||||||| | | d tjt| | ||dtdS) 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: **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 OpenAI-Beta assistants=v2 /assistants rMr2r3r4r5r6r7r8r9r:r;r<r=r>r?bodyoptionscast_to)_postrrAssistantCreateParamsrrr*rMr2r3r4r5r6r7r8r9r:r;r<r=r>r?r+r+r,create9s4d zAssistants.createrSstr assistant_idr<r=r>r?r'cCsD|std|ddi|pi}|jd|t||||dtdS)K 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 ;Expected a non-empty value for `assistant_id` but received rOrP /assistants/rSrVrW ValueError_getrrr*r^r<r=r>r?r+r+r,retrieveszAssistants.retriever2r3r4rMr5r6r7r8r9r:r;r<r=r>r?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:Optional[assistant_update_params.ToolResources] | NotGivenr^r2r3r4rMr5r6r7r8r9r:r;r<r=r>r?r'cCsf|std|ddi| pi} |jd|t|||||||| | | | d tjt| |||dtdS)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 r`rOrPra r2r3r4rMr5r6r7r8r9r:r;rSrT)rdrXrrAssistantUpdateParamsrrr*r^r2r3r4rMr5r6r7r8r9r:r;r<r=r>r?r+r+r,updates: zAssistants.updateafterbeforelimitorderr<r=r>r?str | NotGivenint | NotGiven#Literal[('asc', 'desc')] | NotGivenzSyncCursorPage[Assistant] rrrsrtrur<r=r>r?r'c CsFddi|p i}|jdttt||||t||||dtjdtdSaReturns 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 rOrPrQ)rrrsrtru)r<r=r>r?query)pagerVrM) _get_api_listrrrrrAssistantListParams r*rrrsrtrur<r=r>r?r+r+r,lists(+zAssistants.listrcCsD|std|ddi|pi}|jd|t||||dtdS)H 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 r`rOrPrarSrbrd_deleterrrfr+r+r,deleteszAssistants.delete __name__ __module__ __qualname__rr-r0r r[rgrprrr+r+r+r,r#%sp  0&*2."Gc@sFeZdZeddddZeddddZeeeeeeeeeeddded d d d d d d dddddddddddddZdddeddddddddddZeeeeeeeeeeedddeddd d d d d d ddd!dddddddd"d#d$Z eeeeddded%d&d&d'd(ddddd)d* d+d,Z dddeddddddd-dd.d/Z dS)0r$AsyncAssistantsWithRawResponser&cCst|Sr()rr)r+r+r,r-sz!AsyncAssistants.with_raw_response$AsyncAssistantsWithStreamingResponsecCst|Sr/)rr)r+r+r,r0sz'AsyncAssistants.with_streaming_responseNr1r@rArBrCrDrErFrGrHrIrJrKrrLcsZddi| p i} |jdt||||||||| | | d tjIdHt| | ||dtdIdHS)rNrOrPrQrRNrSrT)rXrrrYrrrZr+r+r,r[s4d zAsyncAssistants.createrSr\r]csJ|std|ddi|pi}|jd|t||||dtdIdHS)r_r`rOrPrarSrbNrcrfr+r+r,rgwszAsyncAssistants.retrieverhrirjrkcsr|std|ddi| pi} |jd|t|||||||| | | | d tjIdHt| |||dtdIdHS) rlr`rOrPrarmNrSrT)rdrXrrrnrrror+r+r,rps: zAsyncAssistants.updaterqrvrwrxz5AsyncPaginator[Assistant, AsyncCursorPage[Assistant]]ryc CsFddi|p i}|jdttt||||t||||dtjdtdSrz)r}rrrrrr~rr+r+r,rCs(+zAsyncAssistants.listrcsJ|std|ddi|pi}|jd|t||||dtdIdHS)rr`rOrPrarSrbNrrfr+r+r,rszAsyncAssistants.deleterr+r+r+r,r$sp  0&*2."Gc@seZdZdddddZdS)r%r#None assistantsr'cCsP||_t|j|_t|j|_t|j|_t|j|_t|j|_dSN) _assistantsrZto_raw_response_wrapperr[rgrprrr*rr+r+r,__init__s z"AssistantsWithRawResponse.__init__Nrrrrr+r+r+r,r%sr%c@seZdZdddddZdS)rr$rrcCsP||_t|j|_t|j|_t|j|_t|j|_t|j|_dSr)rrZasync_to_raw_response_wrapperr[rgrprrrr+r+r,rs z'AsyncAssistantsWithRawResponse.__init__Nrr+r+r+r,rsrc@seZdZdddddZdS)r.r#rrcCsF||_t|j|_t|j|_t|j|_t|j|_t|j|_dSr)rrr[rgrprrrr+r+r,rs z(AssistantsWithStreamingResponse.__init__Nrr+r+r+r,r.sr.c@seZdZdddddZdS)rr$rrcCsF||_t|j|_t|j|_t|j|_t|j|_t|j|_dSr)rrr[rgrprrrr+r+r,rs z-AsyncAssistantsWithStreamingResponse.__init__Nrr+r+r+r,rsr); __future__rtypingrrrtyping_extensionsrZhttpxr_typesr r r r r _utilsrr_compatrZ _resourcerr _responserrZ paginationrrZ types.betarrrZ _base_clientrrZtypes.beta.assistantrZtypes.shared.chat_modelrZtypes.beta.assistant_deletedrZtypes.shared_params.metadatarZtypes.shared.reasoning_effortr Ztypes.beta.assistant_tool_paramr!Z1types.beta.assistant_response_format_option_paramr"__all__r#r$r%rr.rr+r+r+r,s@           DD