UnleashGPT: Mastering the Implementation of Large Language Models
summary
Demonstrates building LLM-powered apps using Azure OpenAI, LangChain and Semantic Kernel with concrete demos: Whisper-based transcription, GPT-4 vision, function-calling plugins (OpenAPI) that detect a zip, generate Python, and call a get_route(a,b) function, and a co‑pilot wired to Microsoft Graph. Covers embeddings (1536 dims) stored in vector databases for retrieval-augmented generation, discusses token costs, temperature/top-p, LoRA adapters, and shows what works and where hallucination, streaming and content-filter evasion remain practical problems.
AI-written summary · about
chapters (12)
- 0:00UnleashGPT introduction
- 4:02Human-computer interaction evolution
- 10:33Tokens and Transformer basics
- 16:20Training LLMs and GPT fundamentals
- 20:56Prompts with Azure OpenAI
- 27:56Function calling and tools
- 34:00Embeddings and custom data
- 40:50Semantic Kernel systems
- 47:15Embeddings and semantic analysis
- 50:05LLM risks and attacks
- 54:04Summary and future of LLMs
- 55:05Q&A
related talks
01h 50mChatGPT & LLMs: A Practical Starter's Guide to Language Chains
56mLarge Language Models for Python Specialists
45mHow to use GPT in your projects: A Case Study
21mChatGPT, LLMs, and LangChains - A Beginner's Guide
59mOrchestrate your AI with Semantic Kernel
30mLarge Language Models and Prompt Engineering for Developers
25mLangChain with Azure AI: Building LLM powered Applications
01h 34mA Practical Starter's Guide to building LLM based projects