The Weaviate Gorilla project is a collection of research experiments in two core concepts:
(1) Agents and Function Calling with Weaviate
(2) Creating synthetic training and testing data with Generative Feedback Loops
Illustrated below, the Weaviate Gorilla translates natural language commands into Weaviate queries. We separate Weaviate queries into 3 categories of difficulty (simple, moderate, complex) based on how many unique query operators they require.
🎙️ Shishir Patil and Tianjun Zhang on the Weaviate Podcast - link
🎥 Fine-tuning LLMs to use Weaviate's GraphQL APIs on Weaviate Youtube - link
📝 Fine-tuning LLMs to use Weaviate's GraphQL APIs on the Weaviate Blog - link
🎥 Gorilla LLM Explained by Connor Shorten on Weaviate YouTube - link
🎥 SQL-PaLM Explained by Connor Shorten on Weaviate YouTube - link
