Weaviate Podcast Instructor with Jason Liu - Weaviate Podcast #88!
Feb 14, 2024
Jason Liu, creator of Instructor, a leading LLM framework, discusses the benefits of structured output parsing with language models and the future of function calling. The podcast also explores selecting tools, organizing prompts, using Go library for reranking, and the capabilities of modal API for serverless GPU compute. The importance of fine-tuning embedding models for improved performance is emphasized.
Chapters
Transcript
Episode notes
1 2 3 4 5 6 7
Introduction
00:00 • 3min
Passing Data Between Programs and Its Impact on Functionality
02:42 • 5min
Exploring the Power and Future of Function Calling
07:18 • 2min
Selecting Tools and Organizing Prompts
08:49 • 9min
Using Go Library for Reranking and Verifying ID Existence
17:41 • 19min
Modal API and Serverless GPU Compute
37:07 • 4min
Fine-Tuning Embedding Models for Improved Performance
41:19 • 14min