How to use GPT in your projects: A Case Study
summary
Shows concrete systems: a translator and live captions using whisper + GPT pipeline, talk-summary pages, semantic search and Q&A powered by Devoxx Insights embeddings stored in a vector DB, tweet generation, photo/voice clones and an avatar pipeline that actually produces synced audio/video. Describes production tactics: retries, model fallback (GPT‑4 → 3.5 → local llama), Lang chain + FastAPI glue, and a GPT‑generated Python scheduler that runs but fails to scale; transcript errors and acronym hallucinations remain.
AI-written summary · about
chapters (11)
- 0:00Introduction and setup
- 4:13Daily use of GPT
- 7:45Handling rate limits in production
- 9:11Real-time voice cloning demo
- 10:16Low-hanging fruit use cases
- 14:27Attempting schedule generation
- 17:39Code examples and LangChain
- 27:38Frequently asked questions with context
- 30:10GPT plugins overview
- 35:04Productivity and future of LLMs
- 41:31Q&A session
related talks
01h 01mKeynote: Transformers: The Rise of ChatGPT
01h 00mUnleashGPT: Mastering the Implementation of Large Language Models
01h 09mChatGPT and OpenAI API solutions: 👑 My Favourite Implementations
28mGPT or how I learned to stop worrying and love the generative AI
02h 00mChatGPT & Prompt Engineering
38mIntroducing the New Colleague - ChatGPT
48mTestGPT: Generative AI (AutoGPT, ChatGPT & VisualGPT)
01h 01mHow ChatGPT Works