Building LLM-Powered Web Apps with Client-Side Technology

What changed

Building LLM-Powered Web Apps with Client-Side Technology October 13, 2023 This is a guest blog post by Jacob Lee, JS/TS maintainer at @LangChainAI, formerly co-founder & CTO at @Autocode, engineer on Google photos. The initial version of this blog post was a talk for Google’s internal WebML Summit 2023, which you can check out here: It’s no secret that for a long time machine learning has been mostly a Python game, but the recent surge in popularity of ChatGPT has brought many new developers into the field. A few observations: - Open source models are advancing rapidly - I built the initial version of this app with Llama 2, and Mistral was announced just weeks later.

Why it matters

A concrete addition to Practical AI: Tools, Models & Frameworks: it changes what's available to builders today rather than being general commentary.

How it compares

Related prior coverage to compare against:

• Introducing apps in ChatGPT and the new Apps SDK
• Open-Source Text Generation & LLM Ecosystem at Hugging Face
• The AI context gap: Enterprise AI organizations have a trust problem, not a retrieval problem — and most are still building the fix

• Introducing apps in ChatGPT and the new Apps SDK similarity 0.19
• Open-Source Text Generation & LLM Ecosystem at Hugging Face similarity 0.18
• The AI context gap: Enterprise AI organizations have a trust problem, not a retrieval problem — and most are still building the fix similarity 0.17