Releases: py-bots/AutoPyBOT-Browser-UI
Version1
AutoPyBOT-Browser-UI v0.1.0-alpha
This is the first alpha pre-release of AutoPyBOT-Browser-UI, introducing initial functionality for controlling your web browser using AI prompts through a browser-based user interface!
Imagine controlling your browser with prompts like these (Future Potential Examples):
- E-commerce Automation:
Add grocery items to cart and checkout on Walmart.com. - CRM & Lead Management:
Add my latest LinkedIn follower named John Doe to my leads in Salesforce under 'Networking Contacts' category. - Job Searching & Application:
Read my CV document. Find Machine Learning jobs on LinkedIn and Indeed. Save the job links to a file called 'ML_Jobs_to_Apply.txt'. Then, start applying for each job in a new browser tab. If application forms need personalized info beyond my CV, ask me for help. - Document Creation & Automation:
Write a letter in Google Docs to my Papa, thanking him for everything he has done for me, and save the document as a PDF named 'Thank_You_Papa_Letter'.
With AutoPyBOT-Browser-UI, the goal is to make browser automation as simple as describing your task in words! To enable the AI-powered features, you will need to configure an API key.
API Key Configuration Required for AI Features:
- AutoPyBOT-Browser-UI relies on an AI API to understand your text prompts. For this alpha release, Gemini API is recommended and is relatively easy to set up.
- Get a Gemini API Key:
- Go to Google Cloud Platform (GCP): If you don't have one, you may need to create a Google Cloud account.
- Enable the Gemini API: In your GCP project, enable the "Gemini API".
- Create API Credentials: Generate an API key for the Gemini API. You will need to copy this key.
- (Note: While Gemini API offers a free tier, usage may be subject to limits. Please review Gemini API pricing and terms of service on Google Cloud Platform for detailed information.)
- Configure the API Key in AutoPyBOT-Browser-UI:
- (Important: You will need to find the API Key configuration setting within the Browser-UI itself.) Look for a settings panel, configuration page, or similar section within the web interface.
- There should be a field to enter your Gemini API key. Paste your Gemini API key into this field and save the settings.
- (If you cannot find API Key settings in the UI in this Alpha): It's possible API key configuration is not yet implemented in the UI for this very early alpha. In that case, API-powered features may not be functional in this initial release, or configuration might need to be done manually via a configuration file (check for project documentation if available - though unlikely for an alpha).
Key Features in this Alpha Release (Initial Capabilities):
- Browser-Based User Interface (Browser-UI): Access and interact with AutoPyBOT through a web browser for a user-friendly experience.
- Basic Prompt-Based Browser Automation (Requires API Key Configuration): You can now enter text prompts in the web interface to instruct AutoPyBOT to perform actions in your web browser after you have configured a valid API key.
- Initial Supported Actions (Browser Focus - very basic in Alpha - Actual actions will be heavily limited in this Alpha Release - Functionality depends on successful API Key configuration):
- Setup via
AutoPyBOTSetup.exe(if applicable): The providedAutoPyBOTSetup.exeinstaller may handle initial setup tasks.
Known Issues and Limitations (Crucial - Alpha Stage):
- API Key Required for AI Features: Remember that AI-powered prompt understanding will not work until you configure a Gemini API key as described above.
- Very Basic Prompt Parsing (Browser Context): Even with API key configured, the system's AI for browser prompts is in its earliest stage. Prompts need to be extremely simple.
- Highly Limited Browser Action Support: The range of browser actions is extremely narrow, even with API key.
- Website Compatibility: Expect very limited website compatibility, even with API key configured.
- Browser Compatibility (Specify browsers tested): e.g., "Basic testing with Chrome, API key functionality and browser actions on other browsers are untested."
- Focus on Foundational UI and API Integration: This alpha is primarily about setting up the Browser-UI, initial API integration, and very basic prompt handling. Robust browser automation and advanced AI are long-term goals.
Instructions:
- Obtain a Gemini API key following the "API Key Configuration Required for AI Features" section above.
- Download
AutoPyBOTSetup.exe. - Run the installer.
- Launch AutoPyBOT-Browser-UI.
- Open the web interface in your browser.
- Configure your Gemini API key in the Browser-UI settings. (Look for a settings or configuration area in the UI).
- Experiment with extremely simple prompts related to opening URLs or very basic interactions on very simple websites, after configuring your API key. Do not expect complex task execution in this alpha.
- Use the "Execute Task (AI Powered)" button.
Feedback Welcome - Help Shape the Future!
This alpha release is a very early exploration of AI-powered browser automation that requires API key configuration for AI features to function. We are extremely interested in your feedback to guide development, specifically:
- API Key Configuration Experience: Was it easy to obtain and configure a Gemini API key? Were the instructions clear?
- Functionality After API Key Configuration: Once you configured the API key, did you observe any AI-powered behavior (even if basic)?
- Your Expectations (with API Key configured): With the API key set up, what kinds of browser automation tasks are most important to you?
- Browser-UI Usability: Is the web interface easy to use for very basic actions, after API key configuration?
- Prompting Experience (Even with Limitations): Even within the limited functionality and with API key configured, how intuitive is the prompting approach?
- Website Compatibility (Even if Limited): On which very simple websites (if any) does the alpha seem to perform basic actions after API key configuration?
- Challenges and Errors (Especially related to API Key and AI functionality): What issues or errors do you encounter, particularly with API key setup or AI-powered features?
- Desired Features for Future Development: What features, especially related to AI prompt understanding and browser actions, are most crucial for making this a truly useful browser automation tool?
Please report all feedback, no matter how small, in the GitHub issue tracker. Your input is critical to making AutoPyBOT-Browser-UI a valuable project!