Git push get an AI API
summary
Builds a live demo that classifies GitHub issues, summarizes trends, and finds similar items using Hypermode; code compiles AssemblyScript to WebAssembly and exposes an auto-generated GraphQL endpoint. Uses OpenAI GPT-4 for trend summarization, a BERT MNLI classifier from Hugging Face for issue type labels, and MiniLM embeddings for vector search; Hypermode hosts models, auto-embeds uploaded CSVs, logs inference history, and the demo runs on the top 100 repo issues with some misclassifications needing threshold/tuning.
AI-written summary · about
chapters (18)
- 0:00Intro
- 0:22AI platform
- 0:33Getting started
- 0:57Agenda
- 1:29Hyper Categories
- 2:21Game Play
- 2:33Game Start
- 4:58Results
- 7:12Concepts
- 7:49Why AI
- 8:25Documentation
- 9:37GitHub issue triage
- 10:04Connecting to GitHub
- 13:56Using the template
- 25:19Inference History
- 26:04System Logs
- 31:49Hyper Mode
- 39:29Deployment
related talks
01h 01mUnlocking the Potential of AI
32m"How Smart is AI? – Real projects to build real understanding"
34mAI won't take your job but it sure will help you do it better
23mFine Tune Your AI Toolbox with GitHub Copilot, Azure AI Foundry...
21mEverything AI: It's a Multi-Model, Agentic World
38mEthical Artificial Intelligence to Advance Welcoming Communities and Identify Potential Communica...
30mWhat Are the Security Risks Associated with AI-Generated Code? 🤔
36mAI Is Revolutionizing Developer Experience - Are You Ready?