OpenAI #Chat: Answer Text Prompt

OpenAI #Chat: Answer Text Prompt

Generates a response to the Text Prompt. By default, it is generated by accessing “gpt-4-1106-preview MODEL” (can be changed to any MODEL). Text prompts for starting a conversation are defined separately for system messages and user messages. Generally, the system message contains the answer rules and the personality of the answering character, and the user message contains the question text.

OpenAI #Images: Generate

OpenAI #Images: Generate

Creates an image given a PROMPT text by the “DALL-E 3 MODEL” via OpenAI API. By default a 1024×1024 image is generated, but 1024×1792 or 1792×1024 are also available. Note that PROMPT must be defined within 4000 characters.

OpenAI #Chat: Answer Prompt with Images

OpenAI #Chat: Answer Prompt with Images

Creates a response for a prompt with images. MODEL (GPT-4 with Vision) takes in images and answers questions related to them, such as what the image represents, what is in the image, and more (eg. ideas for dinner based on what is in fridge).

WordPress.com #Posts: Get

WordPress.com #Posts: Get

Gets an article on WordPress.com service. Specify the article (fixed page/post) by ID or Slug, and store HTML content, excerpt data, etc. You can automate tasks such as backup and transfer operations for website management.

String, Get Number of Characters

String, Get Number of Characters

Gets the number of characters in the text. Consecutive blanks (including tabs and double-byte spaces) are counted as one character. The number of characters that do not count linefeed codes and blanks can also be obtained.

Azure OpenAI Service #Chat: Interact with Parameters

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.

Adobe PDF Services #NonPDF: Create PDF

Adobe PDF Services #Results: Download

Downloads the files (results of PDF OPERATIONS) from PDF Services storage using Polling-URI; Job status URI for polling the results. Note that if the Job is in progress, the FILE type data will be updated as empty, and errors will not occur.

OpenAI #FtJob: List Events

OpenAI #FtJob: List Events

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)

OpenAI #FtJob: Cancel

OpenAI #FtJob: Cancel

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.

Questetra-Model-XML file, Extract Definitions

Questetra-Model-XML file, Extract Definitions

Extracts the step names and the data item names (variable names) of the Workflow App. The Model-XML file is parsed to extract information such as whether it is a human task or an automated task, what the type of data item is, and so on.

OpenAI #FtJob: Retrieve

OpenAI #FtJob: Retrieve

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.

OpenAI #FtJob: Create

OpenAI #FtJob: Create

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.

Converter (File to Base64 String)

Converts file type data to Base 64 encoded string type data. If there are multiple files in File-type data, or if the file size exceeds 10 MB the data will not be converted.