mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-10 07:35:59 +00:00
This adds the missing `text` parameter to the Responses API that is how users control structured outputs. All we do with that parameter is map it to the corresponding chat completion response_format. The unit tests exercise the various permutations allowed for this property, while a couple of new verification tests actually use it for real to verify the model outputs are following the format as expected. Signed-off-by: Ben Browning <bbrownin@redhat.com> |
||
---|---|---|
.. | ||
css | ||
js | ||
providers/vector_io | ||
llama-stack-logo.png | ||
llama-stack-spec.html | ||
llama-stack-spec.yaml | ||
llama-stack.png | ||
remote_or_local.gif | ||
safety_system.webp |