@gUddlmZddlmZmZmZddlmZddlZddl 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/ddgZ0GddeZ1GddeZ2GddZ3GddZ4GddZ5GddZ6dS) ) 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) ChatModel) Assistant)AssistantDeleted)AssistantToolParam)"AssistantResponseFormatOptionParam AssistantsAsyncAssistantsceZdZed6dZed7dZeeeeeeeeeddded d8d"Zddded#d9d&Zeeeeeeeeeeddded'd:d*Z eeeeddded+d;d3Z ddded#d Body | Noner?'float | httpx.Timeout | None | NotGivenrcddi| pi} |dt||||||||| | d tjt | | | |t S) 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. Keys can be a maximum of 64 characters long and values can be a maximum of 512 characters long. name: The name of the assistant. The maximum length is 256 characters. 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 r@r3r4r5r6r7r8r9r:r;r<r=r>r?bodyoptionscast_to)_postrrAssistantCreateParamsrrr*r@r3r4r5r6r7r8r9r:r;r<r=r>r?s r+createzAssistants.create7st'QMr?s r+retrievezAssistants.retrieves. mk[gkkll l&QMr?str | NotGiven:Optional[assistant_update_params.ToolResources] | NotGivenc|std|ddi| pi} |d|t|||||||| | | d tjt | | ||t S)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. Keys can be a maximum of 64 characters long and values can be a maximum of 512 characters long. 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. 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_rNrOr` r3r4r5r@r6r7r8r9r:r;rRrS)rcrWrrAssistantUpdateParamsrrr*r[r3r4r5r@r6r7r8r9r:r;r<r=r>r?s r+updatezAssistants.updatesx mk[gkkll l&QMr?rqrrrsint | NotGivenrt!Literal['asc', 'desc'] | NotGivenSyncCursorPage[Assistant]cddi|pi}|dttt||||t ||||dt jtSaReturns 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 rNrOrP)rqrrrsrt)r<r=r>r?query)pagerUr@) _get_api_listrrrrrAssistantListParams r*rqrrrsrtr<r=r>r?s r+listzAssistants.listAsV'QMrJr?rKr%r r[r\r<rHr=rIr>rJr?rKr%r r[r\r3rBr4rBr5rCr@rhr6rBr7rDr8rEr9rir:rGr;rEr<rHr=rIr>rJr?rKr%r)rqrhrrrhrsrurtrvr<rHr=rIr>rJr?rKr%rw r[r\r<rHr=rIr>rJr?rKr%r __name__ __module__ __qualname__rr,r1r rZrfrorrr-r+r"r"#s///_/555_51:1:09)2S\2;U^9B,5)-$("&;D%p p p p p p p)-$("&;D       L1:1:09 ))2S\2;U^9B,5)-$("&;D't t t t t t r!*!* )3<)-$("&;D? ? ? ? ? ? N)-$("&;D         r-ceZdZed6dZed7dZeeeeeeeeeddded d8d"Zddded#d9d&Zeeeeeeeeeeddded'd:d*Z eeeeddded+d;d3Z ddded#drJr?rKrcKddi| pi} |dt||||||||| | d tjd{Vt | | | |t d{VS)rMrNrOrPrQNrRrS)rWrrrXrrrYs r+rZzAsyncAssistants.createst'QMrJr?rKr%rrrrr-r+r#r#s444_4:::_:1:1:09)2S\2;U^9B,5)-$("&;D%p p p p p p p)-$("&;D       L1:1:09 ))2S\2;U^9B,5)-$("&;D't t t t t t r!*!* )3<)-$("&;D? ? ? ? ? ? N)-$("&;D         r-ceZdZddZdS)r& assistantsr"r%Nonec@||_tj|j|_tj|j|_tj|j|_tj|j|_tj|j|_dSN) _assistantsr to_raw_response_wrapperrZrfrorrr*rs r+__init__z"AssistantsWithRawResponse.__init__(s%&>     )@     '>     %< O   '>     r-Nrr"r%rrrrrrr-r+r&r&'(      r-r&ceZdZddZdS)rrr#r%rc@||_tj|j|_tj|j|_tj|j|_tj|j|_tj|j|_dSr)rr async_to_raw_response_wrapperrZrfrorrrs r+rz'AsyncAssistantsWithRawResponse.__init__=s%&D     )F     'D     %B O   'D     r-Nrr#r%rrrr-r+rr<rr-rceZdZddZdS)r.rr"r%rc||_t|j|_t|j|_t|j|_t|j|_t|j|_dSr)rrrZrfrorrrs r+rz(AssistantsWithStreamingResponse.__init__Rs%2     5     3     1 O   3     r-Nrrrr-r+r.r.Qrr-r.ceZdZddZdS)rrr#r%rc||_t|j|_t|j|_t|j|_t|j|_t|j|_dSr)rrrZrfrorrrs r+rz-AsyncAssistantsWithStreamingResponse.__init__gs%8     ;     9     7 O   9     r-Nrrrr-r+rrfrr-r)7 __future__rtypingrrrtyping_extensionsrhttpxr _typesr r r r r_utilsrr_compatr _resourcerr _responserr paginationrr types.betarrr _base_clientrrtypes.chat_modelrtypes.beta.assistantrtypes.beta.assistant_deletedrtypes.beta.assistant_tool_paramr 1types.beta.assistant_response_format_option_paramr!__all__r"r#r&rr.rrr-r+rs#""""",,,,,,,,,,%%%%%% ??????????????'&&&&&::::::::YYYYYYYY99999999 A@@@@@@@))))))------<<<<<<AAAAAAcccccc * +        D      &   D         *        *        *          r-