← Back to context Comment by jmalicki 1 day ago One trick I learned for this was to use csv for LLM I/I and translate json <-> csv at the boundary layer 2 comments jmalicki Reply fumeux_fume 1 day ago Oh neat. So have the llm output csv instead of JSON and then convert it? How would handle nested structures? jmalicki 1 day ago Depending on how it's nested, you could denormalize, think of how you could denormalize a one-to-many SQL relationshipSo if you have a user that has many automobiles, maybe instead of Autos: [...] you could do Auto1Make Auto2Make etc.
fumeux_fume 1 day ago Oh neat. So have the llm output csv instead of JSON and then convert it? How would handle nested structures? jmalicki 1 day ago Depending on how it's nested, you could denormalize, think of how you could denormalize a one-to-many SQL relationshipSo if you have a user that has many automobiles, maybe instead of Autos: [...] you could do Auto1Make Auto2Make etc.
jmalicki 1 day ago Depending on how it's nested, you could denormalize, think of how you could denormalize a one-to-many SQL relationshipSo if you have a user that has many automobiles, maybe instead of Autos: [...] you could do Auto1Make Auto2Make etc.
Oh neat. So have the llm output csv instead of JSON and then convert it? How would handle nested structures?
Depending on how it's nested, you could denormalize, think of how you could denormalize a one-to-many SQL relationship
So if you have a user that has many automobiles, maybe instead of Autos: [...] you could do Auto1Make Auto2Make etc.