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

feat: Add /v1/embeddings endpoint to batches API

Browse source 
This PR extends the Llama Stack Batches API to support the /v1/embeddings endpoint, enabling efficient batch processing of embedding requests alongside the existing /v1/chat/completions and /v1/completions support.

Signed-off-by: Varsha Prasad Narsing <varshaprasad96@gmail.com>
This commit is contained in:
Varsha Prasad Narsing 2025-09-08 16:55:17 -07:00
parent aab22dc759
commit 531b1451dc
3 changed files with 122 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

10
tests/unit/providers/batches/test_reference.py
View file

@ -213,7 +213,6 @@ class TestReferenceBatchesImpl:
@pytest.mark.parametrize(
"endpoint",
[
"/v1/embeddings",
"/v1/invalid/endpoint",
"",
],
@ -765,3 +764,12 @@ class TestReferenceBatchesImpl:
await asyncio.sleep(0.042) # let tasks start
assert active_batches == 2, f"Expected 2 active batches, got {active_batches}"
async def test_create_batch_embeddings_endpoint(self, provider):
"""Test that batch creation succeeds with embeddings endpoint."""
batch = await provider.create_batch(
input_file_id="file_123",
endpoint="/v1/embeddings",
completion_window="24h",
)
assert batch.endpoint == "/v1/embeddings"