llama-stack-mirror/llama_stack/providers/utils
Ben Browning a4b573d750 Fix OpenAI API response format handling
This fixes the schema of OpenAI API chat completion response formats,
including how those response formats (and other nested parameters in
the chat completion request) get translated into paramters for calls
to the backend OpenAI-compatible providers.

Signed-off-by: Ben Browning <bbrownin@redhat.com>
2025-04-13 13:39:56 -04:00
..
bedrock Fix precommit check after moving to ruff (#927) 2025-02-02 06:46:45 -08:00
common feat: [new open benchmark] BFCL_v3 (#1578) 2025-03-14 12:50:49 -07:00
datasetio refactor: extract pagination logic into shared helper function (#1770) 2025-03-31 13:08:29 -07:00
inference Fix OpenAI API response format handling 2025-04-13 13:39:56 -04:00
kvstore chore: made inbuilt tools blocking calls into async non blocking calls (#1509) 2025-03-09 16:59:24 -07:00
memory fix(deps): move chardet and pypdf imports inline where used (#1434) 2025-03-06 17:09:14 -08:00
scoring feat: [New Eval Benchamark] IfEval (#1708) 2025-03-19 16:39:59 -07:00
telemetry feat: use same trace ids in stack and otel (#1759) 2025-03-21 15:41:26 -07:00
__init__.py API Updates (#73) 2024-09-17 19:51:35 -07:00