-
Notifications
You must be signed in to change notification settings - Fork 14
OpenAI Action #577
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
OpenAI Action #577
Conversation
|
|
||
| {"name": "render jinja template", "function": "render_jinja_template", "screenshot": "none" }, | ||
| {"name": "download chrome extension", "function": "download_chrome_extension", "screenshot": "none" }, | ||
| {"name": "AI visual reader", "function": "AI_visual_reader", "screenshot": "none" }, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Action name should change to "AI - LLM prompt with files"
| # Load API key from .env file | ||
| try: | ||
| from dotenv import load_dotenv | ||
| framework_dir = os.path.dirname(os.path.dirname(os.path.dirname(__file__))) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I don't think we need to load these ourselves. load_dotenv() is already called when node_cli.py starts. So, if a user specifies and environment variable and starts node, it'll already be available in os.getenv() calls.
| } | ||
|
|
||
| payload = { | ||
| "model": "gpt-4o", |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Users should be able to specify the model name as part of the action parameters.
They should also be able to configure the temperature and any other associated hyperparameters of the model.
|
@Zayadul-huq-afnan please review the requests |
|
PR Type
Feature
PR Checklist
Overview
This action takes image and user prompt as input and return the data according to the user prompt. The user prompt is optional, if no user prompt is given then this action will read the data from the image and return it in a JSON format. This acion uses OpenAI's API. Currently the users will have to use their own API key to use this action. Detailed instruction of how to setup the API key will be mentioned in the documentation and action description as well.
Test Cases