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

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

13
tests/integration/fixtures/common.py
View file

@ -124,6 +124,7 @@ def client_with_models(
vision_model_id,
embedding_model_id,
judge_model_id,
rerank_model_id,
):
client = llama_stack_client
@ -141,6 +142,9 @@ def client_with_models(
if embedding_model_id and embedding_model_id not in model_ids:
raise ValueError(f"embedding_model_id {embedding_model_id} not found")
if rerank_model_id and rerank_model_id not in model_ids:
raise ValueError(f"rerank_model_id {rerank_model_id} not found")
return client
@ -156,7 +160,14 @@ def model_providers(llama_stack_client):
@pytest.fixture(autouse=True)
def skip_if_no_model(request):
model_fixtures = ["text_model_id", "vision_model_id", "embedding_model_id", "judge_model_id", "shield_id"]
model_fixtures = [
"text_model_id",
"vision_model_id",
"embedding_model_id",
"judge_model_id",
"shield_id",
"rerank_model_id",
]
test_func = request.node.function
actual_params = inspect.signature(test_func).parameters.keys()