You can use structured outputs, or something like my https://arthurcolle--dynamic-schema.modal.run/
to extract real data from unstructured text (like that producted from an LLM) to make benchmarks slightly easier if you have a schema
to extract real data from unstructured text (like that producted from an LLM) to make benchmarks slightly easier if you have a schema
Dynamic Schema API API is running. See documentation for available endpoints.