We were using OpenAI's codex model with a bunch of few shot examples for natural language queries over blockchain data coupled with a finetuned completions model for plot the results when we were working on makerdojo.io.

Without the ability to fine tune Codex, we had to employ a bunch of techniques to pick the right set of examples to provide in the context to get good SQL. We have come very far since then and it has been great to see projects projects like sqlcoder and this.

Pieces of the pipeline powering makerdojo eventually became LLMStack (https://github.com/trypromptly/LLMStack). We are looking to integrate one of these SQL generators as processors in LLMStack so we can build higher level applications.