-
Notifications
You must be signed in to change notification settings - Fork 25
GUM Platform Enhancement: Unified AI Client, Faster Video Processing #9
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
base: main
Are you sure you want to change the base?
Conversation
|
@oshaikh13 Raised micro pr for unified ai client integration. |
Implement observation batching system to reduce API costs
…r_upgrade Move all processing of observations at a batch-level
|
Hi @oshaikh13 please review this PR when you get a chance |
|
Hi @oshaikh13 just a gentle reminder to review this PR when you get time. Thanks! |
|
Hi @oshaikh13, gentle reminder on this PR. I understand you may be busy, but if you could share even a quick initial review, it would help me proceed. |
|
Hi @oshaikh13, Whenever you get a chance, please review my PR and let me know if any changes are needed — I’ll be happy to update it. I’m excited to work on this project and have a few ideas to explore further. Getting this initial PR reviewed and merged will help me understand how to proceed. |
GUM Platform Enhancement: Unified AI Client, Faster Video Processing, and Web Interface
This PR adds new features to the GUM system, bringing support for multiple AI providers, parallel video analysis.
Key Updates
Unified AI Client
GUM now supports multiple AI providers — Azure OpenAI, OpenAI, and OpenRouter — through a unified client interface. You can switch between providers using environment variables.
Parallel Video Processing
Video uploads and analysis now done in parallel.
Performance highlights:
Other Improvements
Retry logic was added for calls to vision and text AI models to automatically retry requests if they fail.
Handling of large video files was improved to support uploads and processing of videos over 1GB.
A separate vision model was added to handle image data extraction.
Environment Configuration
If you prefer to set up environment variables manually, create a
.envfile in the root directory with the following structure: