Define base card JSON Schema + prompts#26
Conversation
System design + Tech Stack update, removing typos
cboiteux2765
left a comment
cboiteux2765
left a comment
There was a problem hiding this comment.
Great work, just making sure can users add/remove fields from the base card once they edit it? I was thinking of editing the fields of a card being like LinkedIn where you can choose what sections of your profile to add and remove, and choose which fields they want to include based on what they care about since it's a lot of fields
| "visualCue": "string" | ||
| }, | ||
|
|
||
| "aiGrounding": { |
There was a problem hiding this comment.
I like the AI grounding technique to make sure the data is legit
| } | ||
| ], | ||
|
|
||
| "coreMeaning": "string", |
There was a problem hiding this comment.
What would be the core meaning vs definition?
There was a problem hiding this comment.
Core meaning is most common meaning and definitions is an array of definition objects with all meanings and contexts
cboiteux2765
left a comment
cboiteux2765
left a comment
There was a problem hiding this comment.
Maybe also include a section that describes how we're gonna handle dynamic JSON depending on what fields the user wants to include in their card
| "normalizedLemma": "string", | ||
|
|
||
| "partOfSpeech": "string", | ||
| "otherForms": [ |
There was a problem hiding this comment.
So just making sure for now we will include basic info of other forms of the word but the user will have to request more information for those? (the LLM can extend on a previously generated card). I think that's good because it doesn't include info not asked for if they only sought to study one form.
3 participants
Description
Created JSON Schema for baseCard and prompts for BaseCard generation and BaseCard Q&A Prompt.
Sprint Ticket
#20