Daniel Alvarez 538d601472 Do not send an empty 'tools' param to remote vllm ... Fixes: #1955 Since 0.2.0, the vLLM gets an empty list (vs ``None`` in 0.1.9 and before) when there are no tools configured which causes the issue described in #1955. This patch avoids sending the 'tools' param to the vLLM altogether instead of an empty list. It also adds a small unit test to avoid regressions. Signed-off-by: Daniel Alvarez <dalvarez@redhat.com>		2025-04-15 18:02:21 +02:00
..
agents	test: add unit test to ensure all config types are instantiable (#1601)	2025-03-12 22:29:58 -07:00
datasetio	refactor: extract pagination logic into shared helper function (#1770)	2025-03-31 13:08:29 -07:00
inference	Do not send an empty 'tools' param to remote vllm	2025-04-15 18:02:21 +02:00
post_training	fix: remove extra sft args in NvidiaPostTrainingAdapter (#1939)	2025-04-11 10:17:57 -07:00
safety	feat: Add unit tests for NVIDIA safety (#1897)	2025-04-11 11:49:55 -07:00
tool_runtime	fix(api): don't return list for runtime tools (#1686)	2025-04-01 09:53:11 +02:00
vector_io	chore: Updating Milvus Client calls to be non-blocking (#1830)	2025-03-28 22:14:07 -04:00
__init__.py	impls -> inline, adapters -> remote (#381)	2024-11-06 14:54:05 -08:00