phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 04:04:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor: switch to the new default nomic-embed-text-v1.5 embedding model in LS

Browse source
This commit is contained in:
r3v5 2025-08-18 10:34:46 +01:00
parent f1748e2f92
commit 1d0f0a0d8e
No known key found for this signature in database
GPG key ID: C7611ACB4FECAD54
63 changed files with 16170 additions and 186 deletions
Download patch file Download diff file Expand all files Collapse all files

12
tests/integration/inference/test_openai_embeddings.py
View file

@ -104,7 +104,9 @@ def test_openai_embeddings_single_string(compat_client, client_with_models, embe
)
assert response.object == "list"
assert response.model == embedding_model_id
# Handle provider-scoped model identifiers (e.g., sentence-transformers/nomic-ai/nomic-embed-text-v1.5)
assert response.model == embedding_model_id or response.model.endswith(f"/{embedding_model_id}")
assert len(response.data) == 1
assert response.data[0].object == "embedding"
assert response.data[0].index == 0
@ -126,7 +128,9 @@ def test_openai_embeddings_multiple_strings(compat_client, client_with_models, e
)
assert response.object == "list"
assert response.model == embedding_model_id
# Handle provider-scoped model identifiers (e.g., sentence-transformers/nomic-ai/nomic-embed-text-v1.5)
assert response.model == embedding_model_id or response.model.endswith(f"/{embedding_model_id}")
assert len(response.data) == len(input_texts)
for i, embedding_data in enumerate(response.data):
@ -293,7 +297,9 @@ def test_openai_embeddings_base64_batch_processing(compat_client, client_with_mo
)
# Validate response structure
assert response.object == "list"
assert response.model == embedding_model_id
# Handle provider-scoped model identifiers (e.g., sentence-transformers/nomic-ai/nomic-embed-text-v1.5)
assert response.model == embedding_model_id or response.model.endswith(f"/{embedding_model_id}")
assert len(response.data) == len(input_texts)
# Validate each embedding in the batch