From d1c63e078c8712748ccfaf4ad3bc193172cd9de4 Mon Sep 17 00:00:00 2001 From: Connor Shorten Date: Mon, 3 Feb 2025 21:43:00 -0500 Subject: [PATCH] Update readme.md Signed-off-by: Connor Shorten --- readme.md | 2 -- 1 file changed, 2 deletions(-) diff --git a/readme.md b/readme.md index 90e4ab0..72eaef2 100644 --- a/readme.md +++ b/readme.md @@ -2,8 +2,6 @@ The capabilities of Large Language Models (LLMs) are rapidly accelerating largely thanks to their integration with external tools. Querying databases is among the most effective of these integrations, enabling LLMs to access private or continually updating data. This repo benchmarks how well Large Language Models can utilize Weaviate's query APIs in the Function Calling framework. The following result table summarizes our most recent experimental results. -![Weaviate Gorilla Leaderboard](./visuals/result-table.png) - ## Natural Language Commands to Weaviate Queries 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.