o i@sddlmZddlmZmZmZmZddlmZddl Z ddl m Z ddl m Z mZmZmZmZmZmZddlmZmZmZdd lmZd d lmZmZmZmZmZm Z dd l!m"Z"m#Z#dd l$m%Z%m&Z&ddl'm(Z(m)Z)ddl*m+Z+m,Z,ddl-m.Z.m/Z/m0Z0ddl1m2Z2ddl3m4Z4ddl5m6Z6ddgZ7Gddde"Z8Gddde#Z9GdddZ:GdddZ;GdddZZd d d e d*dEd?d@Zd S)Hr*IManage fine-tuning jobs to tailor a model to your specific training data.returnrcC t|jSr-)r_clientselfr4`/home/kim/smarthome/.venv/lib/python3.10/site-packages/openai/resources/fine_tuning/jobs/jobs.py checkpoints( zJobs.checkpointsJobsWithRawResponsecCt|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 )r8r2r4r4r5with_raw_response-zJobs.with_raw_responseJobsWithStreamingResponsecCr9z 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=r2r4r4r5with_streaming_response7zJobs.with_streaming_responseN hyperparameters integrationsmetadatamethodseedsuffixvalidation_file extra_headers extra_query extra_bodytimeoutmodelQUnion[str, Literal['babbage-002', 'davinci-002', 'gpt-3.5-turbo', 'gpt-4o-mini']] training_filestrrB(job_create_params.Hyperparameters | OmitrC8Optional[Iterable[job_create_params.Integration]] | OmitrDOptional[Metadata] | OmitrEjob_create_params.Method | OmitrFOptional[int] | OmitrGOptional[str] | OmitrHrIHeaders | NonerJ Query | NonerK Body | NonerL'float | httpx.Timeout | None | NotGivenr(c  Cs:|jdt||||||||| d tjt| | | | dtdS) Creates a fine-tuning job which begins the process of creating a new model from a given dataset. Response includes details of the enqueued job including job status and the name of the fine-tuned models once complete. [Learn more about fine-tuning](https://platform.openai.com/docs/guides/model-optimization) Args: model: The name of the model to fine-tune. You can select one of the [supported models](https://platform.openai.com/docs/guides/fine-tuning#which-models-can-be-fine-tuned). training_file: The ID of an uploaded file that contains training data. See [upload file](https://platform.openai.com/docs/api-reference/files/create) for how to upload a file. Your dataset must be formatted as a JSONL file. Additionally, you must upload your file with the purpose `fine-tune`. The contents of the file should differ depending on if the model uses the [chat](https://platform.openai.com/docs/api-reference/fine-tuning/chat-input), [completions](https://platform.openai.com/docs/api-reference/fine-tuning/completions-input) format, or if the fine-tuning method uses the [preference](https://platform.openai.com/docs/api-reference/fine-tuning/preference-input) format. See the [fine-tuning guide](https://platform.openai.com/docs/guides/model-optimization) for more details. hyperparameters: The hyperparameters used for the fine-tuning job. This value is now deprecated in favor of `method`, and should be passed in under the `method` parameter. integrations: A list of integrations to enable for your fine-tuning job. 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. method: The method used for fine-tuning. seed: The seed controls the reproducibility of the job. Passing in the same seed and job parameters should produce the same results, but may differ in rare cases. If a seed is not specified, one will be generated for you. suffix: A string of up to 64 characters that will be added to your fine-tuned model name. For example, a `suffix` of "custom-model-name" would produce a model name like `ft:gpt-4o-mini:openai:custom-model-name:7p4lURel`. validation_file: The ID of an uploaded file that contains validation data. If you provide this file, the data is used to generate validation metrics periodically during fine-tuning. These metrics can be viewed in the fine-tuning results file. The same data should not be present in both train and validation files. Your dataset must be formatted as a JSONL file. You must upload your file with the purpose `fine-tune`. See the [fine-tuning guide](https://platform.openai.com/docs/guides/model-optimization) for more details. 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 /fine_tuning/jobs rMrOrBrCrDrErFrGrHrIrJrKrLbodyoptionscast_to)_postrr%JobCreateParamsr#r(r3rMrOrBrCrDrErFrGrHrIrJrKrLr4r4r5create@s(a z Jobs.creater^fine_tuning_job_idcC6|s td||jtd|dt||||dtdS) Get info about a fine-tuning job. [Learn more about fine-tuning](https://platform.openai.com/docs/guides/model-optimization) 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 AExpected a non-empty value for `fine_tuning_job_id` but received &/fine_tuning/jobs/{fine_tuning_job_id}rgr^rarb ValueError_getrr#r(r3rgrIrJrKrLr4r4r5retrieves z Jobs.retrieveafterlimitrDrIrJrKrLrt str | Omitru int | OmitOptional[Dict[str, str]] | OmitSyncCursorPage[FineTuningJob]c C4|jdttt||||t|||dtjdtdSa List your organization's fine-tuning jobs Args: after: Identifier for the last job from the previous pagination request. limit: Number of fine-tuning jobs to retrieve. metadata: Optional metadata filter. To filter, use the syntax `metadata[k]=v`. Alternatively, set `metadata=null` to indicate no metadata. 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\)rtrurDrIrJrKrLquerypagerarM) _get_api_listr r(r#rr$ JobListParamsr3rtrurDrIrJrKrLr4r4r5list$ z Jobs.listcCrh)W Immediately cancel a fine-tune job. 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 rj-/fine_tuning/jobs/{fine_tuning_job_id}/cancelrlr^rmrorcrr#r(rqr4r4r5cancel z Jobs.cancelrtrurIrJrKrL"SyncCursorPage[FineTuningJobEvent]c CL|s td||jtd|dttt||||t||dtjdtdSa Get status updates for a fine-tuning job. Args: after: Identifier for the last event from the previous pagination request. limit: Number of events to retrieve. 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 rjz-/fine_tuning/jobs/{fine_tuning_job_id}/eventsrl)rtrur|r~) rorrr r)r#rr&JobListEventsParamsr3rgrtrurIrJrKrLr4r4r5 list_events/&  zJobs.list_eventscCrh)J Pause a fine-tune job. 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 rj,/fine_tuning/jobs/{fine_tuning_job_id}/pauserlr^rmrrqr4r4r5pausearz Jobs.pausecCrh)K Resume a fine-tune job. 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 rj-/fine_tuning/jobs/{fine_tuning_job_id}/resumerlr^rmrrqr4r4r5resumerz Jobs.resume)r.r)r.r8)r.r=rMrNrOrPrBrQrCrRrDrSrErTrFrUrGrVrHrVrIrWrJrXrKrYrLrZr.r( rgrPrIrWrJrXrKrYrLrZr.r()rtrvrurwrDrxrIrWrJrXrKrYrLrZr.ry)rgrPrtrvrurwrIrWrJrXrKrYrLrZr.r__name__ __module__ __qualname____doc__rr6r;r?rrrfrrrrrrrr4r4r4r5r*%n    }&:%8'c @r,)Hr+r-r.rcCr/r0)rr1r2r4r4r5r6r7zAsyncJobs.checkpointsAsyncJobsWithRawResponsecCr9r:)rr2r4r4r5r;r<zAsyncJobs.with_raw_responseAsyncJobsWithStreamingResponsecCr9r>)rr2r4r4r5r?r@z!AsyncJobs.with_streaming_responseNrArMrNrOrPrBrQrCrRrDrSrErTrFrUrGrVrHrIrWrJrXrKrYrLrZr(c  sH|jdt||||||||| d tjIdHt| | | | dtdIdHS)r[r\r]Nr^r_)rcrr%rdr#r(rer4r4r5rfs*a  zAsyncJobs.creater^rgc>|s td||jtd|dt||||dtdIdHS)rirjrkrlr^rmNrnrqr4r4r5rr6s  zAsyncJobs.retrieversrtrvrurwrx=AsyncPaginator[FineTuningJob, AsyncCursorPage[FineTuningJob]]c Crzr{)rr!r(r#rr$rrr4r4r5rYrzAsyncJobs.listcr)rrjrrlr^rmNrrqr4r4r5r  zAsyncJobs.cancelrGAsyncPaginator[FineTuningJobEvent, AsyncCursorPage[FineTuningJobEvent]]c Crr) rorrr!r)r#rr&rrr4r4r5rrzAsyncJobs.list_eventscr)rrjrrlr^rmNrrqr4r4r5rrzAsyncJobs.pausecr)rrjrrlr^rmNrrqr4r4r5rrzAsyncJobs.resume)r.r)r.r)r.rrr)rtrvrurwrDrxrIrWrJrXrKrYrLrZr.r)rgrPrtrvrurwrIrWrJrXrKrYrLrZr.rrr4r4r4r5r+rc@$eZdZd ddZed dd Zd S) r8jobsr*r.NonecCl||_t|j|_t|j|_t|j|_t|j|_t|j|_t|j|_t|j |_ dSN) _jobsr Zto_raw_response_wrapperrfrrrrrrrr3rr4r4r5__init__$, zJobsWithRawResponse.__init__rcC t|jjSr0)rrr6r2r4r4r5r6= zJobsWithRawResponse.checkpointsNrr*r.r)r.rrrrrrr6r4r4r4r5r8# r8c@r) rrr+r.rcCrr) rr Zasync_to_raw_response_wrapperrfrrrrrrrrr4r4r5rDrz!AsyncJobsWithRawResponse.__init__rcCrr0)rrr6r2r4r4r5r6]rz$AsyncJobsWithRawResponse.checkpointsNrr+r.r)r.rrr4r4r4r5rCrrc@r) r=rr*r.rcC^||_t|j|_t|j|_t|j|_t|j|_t|j|_t|j|_t|j|_dSr) rrrfrrrrrrrrr4r4r5rd, z"JobsWithStreamingResponse.__init__rcCrr0)rrr6r2r4r4r5r6}rz%JobsWithStreamingResponse.checkpointsNr)r.rrr4r4r4r5r=crr=c@r) rrr+r.rcCrr) rrrfrrrrrrrrr4r4r5rrz'AsyncJobsWithStreamingResponse.__init__rcCrr0)rrr6r2r4r4r5r6rz*AsyncJobsWithStreamingResponse.checkpointsNr)r.rrr4r4r4r5rrr)> __future__rtypingrrrrZtyping_extensionsrZhttpxr _typesr r r r rrrZ_utilsrrrZ_compatrr6rrrrrrZ _resourcerr _responserrZ paginationr r!Z _base_clientr"r#Ztypes.fine_tuningr$r%r&Ztypes.shared_params.metadatar'Z!types.fine_tuning.fine_tuning_jobr(Z'types.fine_tuning.fine_tuning_job_eventr)__all__r*r+r8rr=rr4r4r4r5s<   $