phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-10 05:24:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into prompt-api

Browse source
This commit is contained in:
Francisco Arceo 2025-09-06 21:53:34 -06:00 • committed by GitHub
commit 60361b910c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
8 changed files with 112 additions and 138 deletions
Download patch file Download diff file Expand all files Collapse all files

10
tests/integration/inference/test_openai_completion.py
View file

@ -37,6 +37,10 @@ def skip_if_model_doesnt_support_openai_completion(client_with_models, model_id)
"remote::sambanova",
"remote::tgi",
"remote::vertexai",
# {"error":{"message":"Unknown request URL: GET /openai/v1/completions. Please check the URL for typos,
# or see the docs at https://console.groq.com/docs/","type":"invalid_request_error","code":"unknown_url"}}
"remote::groq",
"remote::gemini", # https://generativelanguage.googleapis.com/v1beta/openai/completions -> 404
):
pytest.skip(f"Model {model_id} hosted by {provider.provider_type} doesn't support OpenAI completions.")
@ -63,6 +67,12 @@ def skip_if_doesnt_support_n(client_with_models, model_id):
if provider.provider_type in (
"remote::sambanova",
"remote::ollama",
# https://console.groq.com/docs/openai#currently-unsupported-openai-features
# -> Error code: 400 - {'error': {'message': "'n' : number must be at most 1", 'type': 'invalid_request_error'}}
"remote::groq",
# Error code: 400 - [{'error': {'code': 400, 'message': 'Only one candidate can be specified in the
# current model', 'status': 'INVALID_ARGUMENT'}}]
"remote::gemini",
):
pytest.skip(f"Model {model_id} hosted by {provider.provider_type} doesn't support n param.")

3
tests/unit/providers/inference/test_inference_client_caching.py
View file

@ -33,8 +33,7 @@ def test_groq_provider_openai_client_caching():
with request_provider_data_context(
{"x-llamastack-provider-data": json.dumps({inference_adapter.provider_data_api_key_field: api_key})}
):
openai_client = inference_adapter._get_openai_client()
assert openai_client.api_key == api_key
assert inference_adapter.client.api_key == api_key
def test_openai_provider_openai_client_caching():