Allow Non-Strict mode in generate.json

[lapp0]

Fixes #985

Problem

For generate.json(), Sometimes models exhaust their available token length and generate a sequence which isn't valid JSON or doesn't comply with the provided schema.

Solution

Implement strict mode, which defaults to True (same behavior as main)

If generate.json(..., strict=False) is called, an error dict will be returned rather than an error being raised.

{
    'error': 'Unterminated string starting at: line 1 column 13 (char 12)', 
    'error_type': 'JSONDecodeError', 
    'output': '{"this output obviously is not valid JSON',
}

[rlouf]

Pydantic does offer partial JSON parsing, is that something we'd want to use here?

[lapp0]

Pydantic does offer partial JSON parsing, is that something we'd want to use here?

IMO, users should expect their generation to comply with their schema or an error. Perhaps an allow_partial kwarg should be implemented separately if it fits with someones use case?

[rlouf]

I meant in the "output" field of the error, sorry for not being more specific.