ChatGPT with Laravel & beyond
summary
Shows how to integrate OpenAI APIs into a Laravel app with concrete code: using a Laravel package, differences between chat completion and completion, cost/token management, and implementing token-by-token streaming via Server-Sent Events. Demonstrates Livewire to handle streams, builds an embeddings + cosine-similarity pipeline for retrieval from documentation, and gives real examples (copyba.se, a ChatGPT UI plugin, PR automations). Covers function calling to fetch external data and argues that fine-tuning can reduce prompt tokens, with warnings about cost, latency, and hallucinations.
AI-written summary · about
chapters (18)
- 0:00ChatGPT with Laravel intro
- 1:06OpenAI for developers
- 2:28GPT API token costs
- 4:15Laravel ChatGPT package
- 5:40Key request parameters
- 7:25Effective GPT prompts
- 8:31Response times streaming
- 11:47GPT response limits sources
- 12:30Context bending techniques
- 15:38Fine-tuning GPT models
- 18:48Fine-tuning use cases
- 20:36Function Call integration
- 23:49Function Call limits
- 24:31Laravel GPT apps
- 25:16Real Laravel GPT integrations
- 28:51AI integration risks
- 30:37Future of AI for devs
- 32:26Q&A
related talks
51mChatGPT as a developer's personal servant
25mChatGPT Unleashed: From Code Wizards To Silly Shenanigans!
21mChatGPT, LLMs, and LangChains - A Beginner's Guide
01h 09mChatGPT and OpenAI API solutions: 👑 My Favourite Implementations
01h 16mChatGPT - and How we Can Benefit from it
49mBuilding AI Enabled Web Apps
01h 00mGoing beyond ChatGPT: introduction to prompt engineering & LLMs
01h 01mHow ChatGPT Works