🟆🟆🟆🟆🟆🟆🟆🟆🟆🟆🟆🟆🟆Set-Up🟆🟆🟆🟆🟆🟆🟆🟆🟆🟆🟆🟆🟆🟆
We have detailed video tutorials for each of the actions/elements we have in this plugin. Watch them to understand and use it at ease.

🟆🟆🟆🟆🟆🟆🟆🟆🟆🟆Installing the Plugin🟆🟆🟆🟆🟆🟆🟆🟆🟆🟆


✔ Log in to your Bubble account
✔ Go to Plugins
✔ Search for “Open AI by_Ritz7”
✔ Install the plugin


🟆🟆🟆🟆🟆🟆🟆🟆🟆🟆🟆Using the Plugin🟆🟆🟆🟆🟆🟆🟆🟆🟆🟆🟆


🟆🟆 Note: In all the actions, we have a field named "Authorization". This field should be in the following format: Bearer <OPENAI_API_KEY> or just <OPENAI_API_KEY>.🟆🟆


🟆🟆 Actions 🟆🟆

➽ Create Text Completion

✔ Inputs:
 ➻ Authorization: It is the API key
 ➻ Model: ID of the model to use. You can use the List models API to see all of your available models.
 ➻ Prompt: The prompt(s) to generate completions for, encoded as a string, array of strings, array of tokens, or array of token arrays. Ex - "text" or "text1","text2".
 ➻ 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.
 ➻ Max_Tokens : The maximum number of tokens to generate in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length. Most models have a context length of 2048 tokens (except for the newest models, which support 4096).
 ➻ No_of_Completions: How many completions to generate for each prompt.

✔ Outputs:
 ➻ Details of completion with generated texts, model used, total tokens etc.

➸ Watch the video for the above action here: https://www.youtube.com/watch?v=zqBkQRV2CIg


➽ Create chat completions

✔ Inputs:
 ➻ Authorization: It is received from "Get Access Token from Auth Code" or "Get Access Token from Refresh Token" API response.
 ➻ Model: ID of the model to use. Use "gpt-3.5-turbo". See the model endpoint compatibility table for details on which models work with the Chat API.
 ➻ Messages: The messages to generate chat completions. Check the documentation for the message format.
 ➻ 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.
 ➻ n : How many chat completion choices to generate for each input message.

✔ Outputs:
 ➻ List all models with its details such as id, permissions.

➸ Watch the video for the above action here: https://www.youtube.com/watch?v=1F21BntGMa0


➽ Edit Texts

✔ Inputs:
 ➻ Authorization: It is received from "Get Access Token from Auth Code" or "Get Access Token from Refresh Token" API response.
 ➻ Model: ID of the model to use. You can use the text-davinci-edit-001 or code-davinci-edit-001 model with this endpoint.
 ➻ Input: The input text to use as a starting point for the edit.
 ➻ Instruction: The instruction that tells the model how to edit the prompt.
 ➻ 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.
 ➻ n : How many edits to generate for the input and instruction.

✔ Outputs:
 ➻ Details of text edited by Open AI.

➸ Watch the video for the above action here: https://www.youtube.com/watch?v=EJSc-ADWPXs


➽ Generate Images

✔ Inputs:
 ➻ Authorization: It is received from "Get Access Token from Auth Code" or "Get Access Token from Refresh Token" API response.
 ➻ Prompt: A text description of the desired image(s). The maximum length is 1000 characters.
 ➻ Size: The size of the generated images. Must be one of 256x256, 512x512, or 1024x1024.
 ➻ No_of_Images: The number of images to generate. Must be between 1 and 10.
 ➻ Image_Format: The format in which the generated images are returned. Must be one of url or b64_json.

✔ Outputs:
 ➻ URL of images as described in the prompt.

➸ Watch the video for the above action here: https://www.youtube.com/watch?v=gFhNz6C7WNA


➽ Create image variations

✔ Inputs:
 ➻ Authorization: It is received from "Get Access Token from Auth Code" or "Get Access Token from Refresh Token" API response.
 ➻ Image: The image to use as the basis for the variation(s). Must be a valid PNG file, less than 4MB, and square.
 ➻ No_of_Images: The number of images to generate. Must be between 1 and 10.
 ➻ Size: The size of the generated images. Must be one of 256x256, 512x512, or 1024x1024.
 ➻ Image_Format: The format in which the generated images are returned. Must be one of url or b64_json.

✔ Outputs:
 ➻ URL of images as described in the prompt.

➸ Watch the video for the above action here: https://www.youtube.com/watch?v=tSbicE62hOQ


➽ Create transcriptions from audio file

✔ Inputs:
 ➻ Authorization: It is received from "Get Access Token from Auth Code" or "Get Access Token from Refresh Token" API response.
 ➻ File: The audio file to transcribe, in one of these formats: mpeg, mpga, m4a, wav, or webm.
 ➻ Language: The language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency. ISO-639-1 URL - https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes
 ➻ No_of_Images: The number of images to generate. Must be between 1 and 10.
 ➻ Image_Format: The format in which the generated images are returned. Must be one of url or b64_json.

✔ Outputs:
 ➻ Transcript text generated from audio file in the language mentioned in the input.

➸ Watch the video for the above action here: https://www.youtube.com/watch?v=ZoRREo12hT0


➽ Create translations from audio file

✔ Inputs:
 ➻ Authorization: It is received from "Get Access Token from Auth Code" or "Get Access Token from Refresh Token" API response.
 ➻ File: The audio file to transcribe, in one of these formats: mpeg, mpga, m4a, wav, or webm.
 ➻ Prompt: An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language.

✔ Outputs:
 ➻ Translated text generated from audio file.

➸ Watch the video for the above action here: https://www.youtube.com/watch?v=0ML-94MWuAw