phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-13 06:07:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(api)!: support extra_body to embeddings and vector_stores APIs (#3794)
Some checks failed
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 0s
Details
Python Package Build Test / build (3.12) (push) Failing after 1s
Details
Unit Tests / unit-tests (3.13) (push) Failing after 4s
Details
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 0s
Details
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 0s
Details
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Details
Python Package Build Test / build (3.13) (push) Failing after 1s
Details
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 3s
Details
Vector IO Integration Tests / test-matrix (push) Failing after 5s
Details
Test External API and Providers / test-external (venv) (push) Failing after 5s
Details
Unit Tests / unit-tests (3.12) (push) Failing after 4s
Details
API Conformance Tests / check-schema-compatibility (push) Successful in 10s
Details
UI Tests / ui-tests (22) (push) Successful in 40s
Details
Pre-commit / pre-commit (push) Successful in 1m23s
Details

Browse source 
Applies the same pattern from
https://github.com/llamastack/llama-stack/pull/3777 to embeddings and
vector_stores.create() endpoints.

This should _not_ be a breaking change since (a) our tests were already
using the `extra_body` parameter when passing in to the backend (b) but
the backend probably wasn't extracting the parameters correctly. This PR
will fix that.

Updated APIs: `openai_embeddings(), openai_create_vector_store(),
openai_create_vector_store_file_batch()`
This commit is contained in:
Ashwin Bharambe 2025-10-12 19:01:52 -07:00 • committed by GitHub
parent 3bb6ef351b
commit ecc8a554d2
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
26 changed files with 451 additions and 426 deletions
Download patch file Download diff file Expand all files Collapse all files

42
tests/unit/providers/vector_io/test_vector_io_openai_vector_stores.py
View file

@ -15,6 +15,7 @@ from llama_stack.apis.common.errors import VectorStoreNotFoundError
from llama_stack.apis.vector_dbs import VectorDB
from llama_stack.apis.vector_io import (
Chunk,
OpenAICreateVectorStoreFileBatchRequestWithExtraBody,
QueryChunksResponse,
VectorStoreChunkingStrategyAuto,
VectorStoreFileObject,
@ -326,8 +327,7 @@ async def test_create_vector_store_file_batch(vector_io_adapter):
vector_io_adapter._process_file_batch_async = AsyncMock()
batch = await vector_io_adapter.openai_create_vector_store_file_batch(
vector_store_id=store_id,
file_ids=file_ids,
vector_store_id=store_id, params=OpenAICreateVectorStoreFileBatchRequestWithExtraBody(file_ids=file_ids)
)
assert batch.vector_store_id == store_id
@ -354,8 +354,7 @@ async def test_retrieve_vector_store_file_batch(vector_io_adapter):
# Create batch first
created_batch = await vector_io_adapter.openai_create_vector_store_file_batch(
vector_store_id=store_id,
file_ids=file_ids,
vector_store_id=store_id, params=OpenAICreateVectorStoreFileBatchRequestWithExtraBody(file_ids=file_ids)
)
# Retrieve batch
@ -388,8 +387,7 @@ async def test_cancel_vector_store_file_batch(vector_io_adapter):
# Create batch
batch = await vector_io_adapter.openai_create_vector_store_file_batch(
vector_store_id=store_id,
file_ids=file_ids,
vector_store_id=store_id, params=OpenAICreateVectorStoreFileBatchRequestWithExtraBody(file_ids=file_ids)
)
# Cancel batch
@ -434,8 +432,7 @@ async def test_list_files_in_vector_store_file_batch(vector_io_adapter):
# Create batch
batch = await vector_io_adapter.openai_create_vector_store_file_batch(
vector_store_id=store_id,
file_ids=file_ids,
vector_store_id=store_id, params=OpenAICreateVectorStoreFileBatchRequestWithExtraBody(file_ids=file_ids)
)
# List files
@ -455,7 +452,7 @@ async def test_file_batch_validation_errors(vector_io_adapter):
with pytest.raises(VectorStoreNotFoundError):
await vector_io_adapter.openai_create_vector_store_file_batch(
vector_store_id="nonexistent",
file_ids=["file_1"],
params=OpenAICreateVectorStoreFileBatchRequestWithExtraBody(file_ids=["file_1"]),
)
# Setup store for remaining tests
@ -472,8 +469,7 @@ async def test_file_batch_validation_errors(vector_io_adapter):
# Test wrong vector store for batch
vector_io_adapter.openai_attach_file_to_vector_store = AsyncMock()
batch = await vector_io_adapter.openai_create_vector_store_file_batch(
vector_store_id=store_id,
file_ids=["file_1"],
vector_store_id=store_id, params=OpenAICreateVectorStoreFileBatchRequestWithExtraBody(file_ids=["file_1"])
)
# Create wrong_store so it exists but the batch doesn't belong to it
@ -520,8 +516,7 @@ async def test_file_batch_pagination(vector_io_adapter):
# Create batch
batch = await vector_io_adapter.openai_create_vector_store_file_batch(
vector_store_id=store_id,
file_ids=file_ids,
vector_store_id=store_id, params=OpenAICreateVectorStoreFileBatchRequestWithExtraBody(file_ids=file_ids)
)
# Test pagination with limit
@ -593,8 +588,7 @@ async def test_file_batch_status_filtering(vector_io_adapter):
# Create batch
batch = await vector_io_adapter.openai_create_vector_store_file_batch(
vector_store_id=store_id,
file_ids=file_ids,
vector_store_id=store_id, params=OpenAICreateVectorStoreFileBatchRequestWithExtraBody(file_ids=file_ids)
)
# Test filtering by completed status
@ -636,8 +630,7 @@ async def test_cancel_completed_batch_fails(vector_io_adapter):
# Create batch
batch = await vector_io_adapter.openai_create_vector_store_file_batch(
vector_store_id=store_id,
file_ids=file_ids,
vector_store_id=store_id, params=OpenAICreateVectorStoreFileBatchRequestWithExtraBody(file_ids=file_ids)
)
# Manually update status to completed
@ -671,8 +664,7 @@ async def test_file_batch_persistence_across_restarts(vector_io_adapter):
# Create batch
batch = await vector_io_adapter.openai_create_vector_store_file_batch(
vector_store_id=store_id,
file_ids=file_ids,
vector_store_id=store_id, params=OpenAICreateVectorStoreFileBatchRequestWithExtraBody(file_ids=file_ids)
)
batch_id = batch.id
@ -727,8 +719,7 @@ async def test_cancelled_batch_persists_in_storage(vector_io_adapter):
# Create batch
batch = await vector_io_adapter.openai_create_vector_store_file_batch(
vector_store_id=store_id,
file_ids=file_ids,
vector_store_id=store_id, params=OpenAICreateVectorStoreFileBatchRequestWithExtraBody(file_ids=file_ids)
)
batch_id = batch.id
@ -775,10 +766,10 @@ async def test_only_in_progress_batches_resumed(vector_io_adapter):
# Create multiple batches
batch1 = await vector_io_adapter.openai_create_vector_store_file_batch(
vector_store_id=store_id, file_ids=["file_1"]
vector_store_id=store_id, params=OpenAICreateVectorStoreFileBatchRequestWithExtraBody(file_ids=["file_1"])
)
batch2 = await vector_io_adapter.openai_create_vector_store_file_batch(
vector_store_id=store_id, file_ids=["file_2"]
vector_store_id=store_id, params=OpenAICreateVectorStoreFileBatchRequestWithExtraBody(file_ids=["file_2"])
)
# Complete one batch (should persist with completed status)
@ -791,7 +782,7 @@ async def test_only_in_progress_batches_resumed(vector_io_adapter):
# Create a third batch that stays in progress
batch3 = await vector_io_adapter.openai_create_vector_store_file_batch(
vector_store_id=store_id, file_ids=["file_3"]
vector_store_id=store_id, params=OpenAICreateVectorStoreFileBatchRequestWithExtraBody(file_ids=["file_3"])
)
# Simulate restart - clear memory and reload from persistence
@ -952,8 +943,7 @@ async def test_max_concurrent_files_per_batch(vector_io_adapter):
file_ids = [f"file_{i}" for i in range(8)] # 8 files, but limit should be 5
batch = await vector_io_adapter.openai_create_vector_store_file_batch(
vector_store_id=store_id,
file_ids=file_ids,
vector_store_id=store_id, params=OpenAICreateVectorStoreFileBatchRequestWithExtraBody(file_ids=file_ids)
)
# Give time for the semaphore logic to start processing files