Skip to content

arcwisedata/semantic-layer-llm-benchmarking

 
 

Repository files navigation

About the repo

This repo is an accompaniment to this Roundup article and extends the work done in A Benchmark to Understand the Role of Knowledge Graphs on Large Language Model's Accuracy for Question Answering on Enterprise SQL Databases, a preprint on arxiv.org from the team at data.world.

About the experiment

Using OpenAI's completions API (gpt-4), we provide a few-shot prompt to introduce the LLM to proper dbt SL syntax (which is otherwise not available due to the knowledge cutoff of April 2023) and ask it to generate a SL query to answer a selection of questions from the benchmark.

How to interact with the benchmark and our results

Created by Jason Ganz, Joel Labes and Jordan Stein

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Shell 100.0%