llama-stack-mirror/src/llama_stack
Mustafa Elbehery f94d614631 fix(integration): init AsyncMilvusClient before MilvusIndex
Signed-off-by: Mustafa Elbehery <melbeher@redhat.com>
2025-11-12 23:06:17 +01:00
..
apis feat: allow returning embeddings and metadata from /vector_stores/ methods; disallow changing Provider ID (#4046) 2025-11-12 09:59:48 -08:00
cli fix: print help for list-deps if no args (#4078) 2025-11-05 11:34:08 -08:00
core feat(storage): share sql/kv instances and add upsert support (#4140) 2025-11-12 12:14:26 -08:00
distributions fix: harden storage semantics (#4118) 2025-11-12 10:35:39 -08:00
models refactor: remove dead inference API code and clean up imports (#4093) 2025-11-10 15:29:24 -08:00
providers fix(integration): init AsyncMilvusClient before MilvusIndex 2025-11-12 23:06:17 +01:00
strong_typing fix(mypy): part-03 completely resolve meta reference responses impl typing issues (#3951) 2025-10-29 08:07:15 -07:00
testing fix: update tests for OpenAI-style models endpoint (#4053) 2025-11-03 17:30:08 -08:00
__init__.py chore: Stack server no longer depends on llama-stack-client (#4094) 2025-11-07 09:54:09 -08:00
env.py chore(package): migrate to src/ layout (#3920) 2025-10-27 12:02:21 -07:00
log.py chore(package): migrate to src/ layout (#3920) 2025-10-27 12:02:21 -07:00
schema_utils.py chore(package): migrate to src/ layout (#3920) 2025-10-27 12:02:21 -07:00