Approval Flow, ChatGPT Decision Assistance
Field Name, num, Initial Value Download This archive contains the BPMN icons that are not available in the Basic edition. Notes Capture
Field Name, num, Initial Value Download This archive contains the BPMN icons that are not available in the Basic edition. Notes Capture
This is an approval process where AI reviews the draft content.
The drafters can refine their drafts based on the results of the AI review.
Communicates with Azure OpenAI Service API (ChatGPT running on Microsoft infrastructure). Supports the assignment of advanced parameters. Specifically, sampling temperature, upper % sampling, recurrence prohibition, frequency prohibition and Logit bias can be set.
The process of requesting a translation (English translation) of a specified text.
ChatGPT automatically generates a draft translation of the draft entered by the requester.
The translator completes the translation using the draft translation created by ChatGPT.
Lists status updates for the fine-tuning job. The number of all events and the TSV of all event details can be obtained; created time, event level, event message. (upto 20)
Immediately cancels the Fine Tuning Job (FtJob). FtJob status will be “cancelled”. If logging of fine-tuning events is required, perform a separate operation to obtain a list of events.
Gets info about the Fine-Tune Job (FtJob). FineTune status can be obtained. If the job status is “succeeded”, the MODEL name (ID) can also be obtained. It is typically placed in a flow that is called repeatedly every hour.
Creates a job (FtJob) that fine-tunes a specified MODEL. Stores the job ID. The job will take minutes or hours. The Fine-Tuned MODEL (FtMODEL) will be available after the job is completed. Note that the training file (dataset) must be uploaded in advance.
Gets info about the Fine-Tune Job (FtJob). FineTune event logs can be obtained. If the job status is “succeeded”, the MODEL name (ID) can also be obtained. It is typically placed in a flow that is called repeatedly every hour.
Creates a job (FtJob) that fine-tunes a specified MODEL. Stores the job ID. The job will take minutes or hours. The “Fine-Tuned MODEL” (FtMODEL) will be available after the job is completed. Note that the training file (dataset) must be uploaded in advance.
Deletes a Fine-Tuned Model (FtMODEL). The Owner role in your organization is required. If the specified FtMODEL does not exist, a 404 error will occur.
Lists the various models available in the API including Fine-Tuned Models (FtMODELs). The number of the currently available models and TSV of basic information about each one can be obtained; created time, owner, root MODEL, MODEL ID.
Immediately cancels a Fine Tuning Job (FtJob). FtJob status will be “cancelled”. Fine-tune event logs can be obtained.
Lists all Fine-Tuning Jobs (FtJobs) in your organization. The number of all FtJobs and the TSV of all FtJobs can be obtained; start time, update time, status, Base MODEL, FtJob ID.
Deletes a file on the OpenAI API server. Delete a file by specifying its file ID. The file ID is in the format “file-xxxxxyyyyyyyzzzzzXXXXXXXYYYYY” and can be stored when uploading.
Downloads a file on the OpenAI API server. Files matching the specified ID are stored. The file ID is in the format “file-xxxxxyyyyyyyzzzzzXXXXXXXYYYYY” and can be obtained during upload.
Lists the files on the OpenAI API server. For all files belonging to the user organisation, the four attributes File ID, Purpose, File Size and File Name are stored as TSV text.
Uploads files to the OpenAI API server. File documents are used by various endpoints and functions, such as fine tuning.
This is the process of creating AI art using image-generating AI. The person in charge (Prompter/Arranger) repeatedly uses the OpenAI API (Dall-E 2) to complete the AI art (image file). The reviewer (Reviewer) ensures that the AI art does not (and will not) infringe the copyright of other companies.
The process manages the daily sales report.
At regular intervals, an email is sent requesting the completion of the daily report.
The request email contains a humorous daily message (auto-generated by ChatGPT).
This process centrally manages the process from receipt of queries via web form to response.
After drafting a response, the person in charge can request an improvement review from ChatGPT if necessary.
The response is completed based on the review results, and is then sent back to the enquirer.