The obvious solution is to find a way to train GPT-3 on the Dagster documentation. We need a way to teach GPT-3 about the technical details of the Dagster GitHub project. With that said, let’s proceed! To fine tune or not to fine tune? There are likely ways that we could improve what we’ve done in this blog post. It is worth noting that I’m not an AI expert. So we set out on a journey to figure out if we could use GPT-3 to build a bot that could answer basic technical questions about Dagster. While OpenAI's ChatGPT itself doesn’t have an API, the underlying technology - GPT-3 - does. When we saw what ChatGPT could do, we wondered if we could create a Slack bot based on the technology that could answer basic questions. Providing a best-in-class support experience is key to the success of our project, but it requires a ton of work from our core team members. We build Dagster, a rapidly growing open-source data orchestration solution with a large community Slack instance.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |