Using Open AI to assess database via Get API

[randal]

Hi,

I’ve been creating a dataset with a Get API, copying the JSON for the get request, and throwing the JSON manually into Chat GPT. I then ask it questions based on the data.

I’m finding this really interesting as it saves time having to manually build a dashboard or figure out what sorts of data views would be interesting for cuts of the database.

I’d like to know if there’s a way to use Xano to take out the manual steps above, i.e. get Open AI to provide analysis of my dataset JSON via a function or something using the Open AI API. I also play with bubble and have been trying to figure out ways to move the API events to Bubble.

I’m open to any ideas people might have / any suggestions on your experience of doing this.

[redvivi]

What you need @randal is “Functions”. I elaborated the different points in that post

Any bubble compatible options for AI querying your data?

@sanastasi @bidlist @saviorabrams I might be missing some context but there is definitely a way to query dynamic data from Bubble to LLM upon user query. This is called “Functions”. Some functions are called when the LLM detects that the requested data from the conversation requires to get data from such functions. At this point, nothing prevent you from feeding back the function results to the LLM which will then answer with the queried data. I have implemented this kind of use-cases using…