phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-30 11:50:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix for model in OpenAIEmbeddingsResponse and rebase

Browse source 
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
This commit is contained in:
Francisco Javier Arceo 2025-06-12 22:05:54 -04:00
parent 15042c6c31
commit 179399edf4
2 changed files with 9 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
llama_stack/providers/remote/inference/ollama/ollama.py
View file

@ -419,9 +419,10 @@ class OllamaInferenceAdapter(
prompt_tokens=response.usage.prompt_tokens, prompt_tokens=response.usage.prompt_tokens,
total_tokens=response.usage.total_tokens, total_tokens=response.usage.total_tokens,
) )
# TODO: Investigate why model_obj.identifier is used instead of response.model
return OpenAIEmbeddingsResponse( return OpenAIEmbeddingsResponse(
data=data, data=data,
model=response.model, model=model_obj.identifier,
usage=usage, usage=usage,
) )

7
tests/integration/inference/test_openai_embeddings.py
View file

@ -55,6 +55,12 @@ def skip_if_model_doesnt_support_openai_embeddings(client, model_id):
pytest.skip(f"Model {model_id} hosted by {provider.provider_type} doesn't support OpenAI embeddings.") pytest.skip(f"Model {model_id} hosted by {provider.provider_type} doesn't support OpenAI embeddings.")
def skip_if_client_doesnt_support_base64_encoding(client, model_id):
provider = provider_from_model(client, model_id)
if provider.provider_type in ("remote::ollama",):
pytest.skip(f"Client {client} doesn't support base64 encoding for embeddings.")
@pytest.fixture @pytest.fixture
def openai_client(client_with_models): def openai_client(client_with_models):
base_url = f"{client_with_models.base_url}/v1/openai/v1" base_url = f"{client_with_models.base_url}/v1/openai/v1"
@ -247,6 +253,7 @@ def test_openai_embeddings_with_encoding_format_base64(compat_client, client_wit
def test_openai_embeddings_base64_batch_processing(compat_client, client_with_models, embedding_model_id): def test_openai_embeddings_base64_batch_processing(compat_client, client_with_models, embedding_model_id):
"""Test OpenAI embeddings endpoint with base64 encoding for batch processing.""" """Test OpenAI embeddings endpoint with base64 encoding for batch processing."""
skip_if_model_doesnt_support_openai_embeddings(client_with_models, embedding_model_id) skip_if_model_doesnt_support_openai_embeddings(client_with_models, embedding_model_id)
skip_if_client_doesnt_support_base64_encoding(client_with_models, embedding_model_id)
input_texts = ["First text for base64", "Second text for base64", "Third text for base64"] input_texts = ["First text for base64", "Second text for base64", "Third text for base64"]