Hacker News Reader

Remember that you still need to include an instruction to produce a CSV to get the prompt into the right context to generate a CSV that makes sense. Otherwise, you may get output that is technically in the CSV format but doesn't make any sense because the model was actually trying to write a paragraph response and the token sampler just selected really low-probability tokens that the model didn't really want to say.

View on HN

It seems ollama only supports JSON Schema.

Interestingly, JSON Schema has much less of this problem than say CSV - when the model is forced to produce `{"first_key":` it will generally understand it's supposed to continue in JSON. It still helps to tell it the schema though, especially due to weird tokenization issues you can get otherwise.

> It seems ollama only supports JSON Schema.

"Encoding" CSV as JSON is trivial though, so make it output JSON then parse the array-of-arrays into CSV :)

Reply on news.ycombinator.com