phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-11 19:56:03 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

Add rerank API for NVIDIA Inference Provider

Browse source
This commit is contained in:
Jiayi 2025-10-16 17:27:38 -07:00
parent b7dd3f5c56
commit 7ad4b47286
8 changed files with 622 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

5
tests/integration/conftest.py
View file

@ -171,6 +171,10 @@ def pytest_addoption(parser):
"--embedding-model",
help="comma-separated list of embedding models. Fixture name: embedding_model_id",
)
parser.addoption(
"--rerank-model",
help="comma-separated list of rerank models. Fixture name: rerank_model_id",
)
parser.addoption(
"--safety-shield",
help="comma-separated list of safety shields. Fixture name: shield_id",
@ -249,6 +253,7 @@ def pytest_generate_tests(metafunc):
"shield_id": ("--safety-shield", "shield"),
"judge_model_id": ("--judge-model", "judge"),
"embedding_dimension": ("--embedding-dimension", "dim"),
"rerank_model_id": ("--rerank-model", "rerank"),
}
# Collect all parameters and their values