mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-15 22:47:59 +00:00
chore: Auto-detect Provider ID when only 1 Vector Store Provider avai… (#3802)
Some checks failed
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 0s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 0s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Python Package Build Test / build (3.13) (push) Failing after 1s
Python Package Build Test / build (3.12) (push) Failing after 1s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 4s
Test External API and Providers / test-external (venv) (push) Failing after 4s
Unit Tests / unit-tests (3.12) (push) Failing after 4s
Unit Tests / unit-tests (3.13) (push) Failing after 4s
Vector IO Integration Tests / test-matrix (push) Failing after 8s
API Conformance Tests / check-schema-compatibility (push) Successful in 18s
UI Tests / ui-tests (22) (push) Successful in 29s
Pre-commit / pre-commit (push) Successful in 1m24s
Some checks failed
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 0s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 0s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Python Package Build Test / build (3.13) (push) Failing after 1s
Python Package Build Test / build (3.12) (push) Failing after 1s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 4s
Test External API and Providers / test-external (venv) (push) Failing after 4s
Unit Tests / unit-tests (3.12) (push) Failing after 4s
Unit Tests / unit-tests (3.13) (push) Failing after 4s
Vector IO Integration Tests / test-matrix (push) Failing after 8s
API Conformance Tests / check-schema-compatibility (push) Successful in 18s
UI Tests / ui-tests (22) (push) Successful in 29s
Pre-commit / pre-commit (push) Successful in 1m24s
# What does this PR do?
2 main changes:
1. Remove `provider_id` requirement in call to vector stores and
2. Removes "register first embedding model" logic
- Now forces embedding model id as required on Vector Store creation
Simplifies the UX for OpenAI to:
```python
vs = client.vector_stores.create(
name="my_citations_db",
extra_body={
"embedding_model": "ollama/nomic-embed-text:latest",
}
)
```
<!-- If resolving an issue, uncomment and update the line below -->
<!-- Closes #[issue-number] -->
## Test Plan
<!-- Describe the tests you ran to verify your changes with result
summaries. *Provide clear instructions so the plan can be easily
re-executed.* -->
---------
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
This commit is contained in:
Francisco Arceo
GitHub
parent
642126e13b
commit
968c364a3e
5 changed files with 123 additions and 115 deletions
|
|
@ -146,8 +146,6 @@ def test_openai_create_vector_store(
|
|||
metadata={"purpose": "testing", "environment": "integration"},
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -175,8 +173,6 @@ def test_openai_list_vector_stores(
|
|||
metadata={"type": "test"},
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
store2 = client.vector_stores.create(
|
||||
|
|
@ -184,8 +180,6 @@ def test_openai_list_vector_stores(
|
|||
metadata={"type": "test"},
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -220,8 +214,6 @@ def test_openai_retrieve_vector_store(
|
|||
metadata={"purpose": "retrieval_test"},
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -249,8 +241,6 @@ def test_openai_update_vector_store(
|
|||
metadata={"version": "1.0"},
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
time.sleep(1)
|
||||
|
|
@ -282,8 +272,6 @@ def test_openai_delete_vector_store(
|
|||
metadata={"purpose": "deletion_test"},
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -314,8 +302,6 @@ def test_openai_vector_store_search_empty(
|
|||
metadata={"purpose": "search_testing"},
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -346,8 +332,6 @@ def test_openai_vector_store_with_chunks(
|
|||
metadata={"purpose": "chunks_testing"},
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -412,8 +396,6 @@ def test_openai_vector_store_search_relevance(
|
|||
metadata={"purpose": "relevance_testing"},
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -457,8 +439,6 @@ def test_openai_vector_store_search_with_ranking_options(
|
|||
metadata={"purpose": "ranking_testing"},
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -500,8 +480,6 @@ def test_openai_vector_store_search_with_high_score_filter(
|
|||
metadata={"purpose": "high_score_filtering"},
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -561,8 +539,6 @@ def test_openai_vector_store_search_with_max_num_results(
|
|||
metadata={"purpose": "max_num_results_testing"},
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -596,8 +572,6 @@ def test_openai_vector_store_attach_file(
|
|||
name="test_store",
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -666,8 +640,6 @@ def test_openai_vector_store_attach_files_on_creation(
|
|||
file_ids=file_ids,
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -713,8 +685,6 @@ def test_openai_vector_store_list_files(
|
|||
name="test_store",
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -799,8 +769,6 @@ def test_openai_vector_store_retrieve_file_contents(
|
|||
name="test_store",
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -819,8 +787,6 @@ def test_openai_vector_store_retrieve_file_contents(
|
|||
attributes=attributes,
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -857,8 +823,6 @@ def test_openai_vector_store_delete_file(
|
|||
name="test_store",
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -918,8 +882,6 @@ def test_openai_vector_store_delete_file_removes_from_vector_store(
|
|||
name="test_store",
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -965,8 +927,6 @@ def test_openai_vector_store_update_file(
|
|||
name="test_store",
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -1026,8 +986,6 @@ def test_create_vector_store_files_duplicate_vector_store_name(
|
|||
name="test_store_with_files",
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
assert vector_store.file_counts.completed == 0
|
||||
|
|
@ -1040,8 +998,6 @@ def test_create_vector_store_files_duplicate_vector_store_name(
|
|||
name="test_store_with_files",
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -1053,8 +1009,6 @@ def test_create_vector_store_files_duplicate_vector_store_name(
|
|||
file_id=file_ids[0],
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
assert created_file.status == "completed"
|
||||
|
|
@ -1065,8 +1019,6 @@ def test_create_vector_store_files_duplicate_vector_store_name(
|
|||
file_id=file_ids[1],
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
assert created_file_from_non_deleted_vector_store.status == "completed"
|
||||
|
|
@ -1087,8 +1039,6 @@ def test_openai_vector_store_search_modes(
|
|||
metadata={"purpose": "search_mode_testing"},
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -1120,8 +1070,6 @@ def test_openai_vector_store_file_batch_create_and_retrieve(
|
|||
name="batch_test_store",
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -1139,8 +1087,6 @@ def test_openai_vector_store_file_batch_create_and_retrieve(
|
|||
file_ids=file_ids,
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -1187,8 +1133,6 @@ def test_openai_vector_store_file_batch_list_files(
|
|||
name="batch_list_test_store",
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -1206,8 +1150,6 @@ def test_openai_vector_store_file_batch_list_files(
|
|||
file_ids=file_ids,
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -1284,8 +1226,6 @@ def test_openai_vector_store_file_batch_cancel(
|
|||
name="batch_cancel_test_store",
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -1303,8 +1243,6 @@ def test_openai_vector_store_file_batch_cancel(
|
|||
file_ids=file_ids,
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -1343,8 +1281,6 @@ def test_openai_vector_store_file_batch_retrieve_contents(
|
|||
name="batch_contents_test_store",
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -1367,8 +1303,6 @@ def test_openai_vector_store_file_batch_retrieve_contents(
|
|||
file_ids=file_ids,
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -1420,8 +1354,6 @@ def test_openai_vector_store_file_batch_error_handling(
|
|||
name="batch_error_test_store",
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -1433,8 +1365,6 @@ def test_openai_vector_store_file_batch_error_handling(
|
|||
file_ids=file_ids,
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
|
|||
|
|
@ -52,8 +52,6 @@ def test_vector_db_retrieve(client_with_empty_registry, embedding_model_id, embe
|
|||
name=vector_db_name,
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -73,8 +71,6 @@ def test_vector_db_register(client_with_empty_registry, embedding_model_id, embe
|
|||
name=vector_db_name,
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -110,8 +106,6 @@ def test_insert_chunks(client_with_empty_registry, embedding_model_id, embedding
|
|||
name=vector_db_name,
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -152,8 +146,6 @@ def test_insert_chunks_with_precomputed_embeddings(client_with_empty_registry, e
|
|||
name=vector_db_name,
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -202,8 +194,6 @@ def test_query_returns_valid_object_when_identical_to_embedding_in_vdb(
|
|||
name=vector_db_name,
|
||||
extra_body={
|
||||
"embedding_model": embedding_model_id,
|
||||
"embedding_dimension": embedding_dimension,
|
||||
"provider_id": "my_provider",
|
||||
},
|
||||
)
|
||||
|
||||
|
|
@ -234,3 +224,35 @@ def test_query_returns_valid_object_when_identical_to_embedding_in_vdb(
|
|||
assert len(response.chunks) > 0
|
||||
assert response.chunks[0].metadata["document_id"] == "doc1"
|
||||
assert response.chunks[0].metadata["source"] == "precomputed"
|
||||
|
||||
|
||||
def test_auto_extract_embedding_dimension(client_with_empty_registry, embedding_model_id):
|
||||
vs = client_with_empty_registry.vector_stores.create(
|
||||
name="test_auto_extract", extra_body={"embedding_model": embedding_model_id}
|
||||
)
|
||||
assert vs.id is not None
|
||||
|
||||
|
||||
def test_provider_auto_selection_single_provider(client_with_empty_registry, embedding_model_id):
|
||||
providers = [p for p in client_with_empty_registry.providers.list() if p.api == "vector_io"]
|
||||
if len(providers) != 1:
|
||||
pytest.skip(f"Test requires exactly one vector_io provider, found {len(providers)}")
|
||||
|
||||
vs = client_with_empty_registry.vector_stores.create(
|
||||
name="test_auto_provider", extra_body={"embedding_model": embedding_model_id}
|
||||
)
|
||||
assert vs.id is not None
|
||||
|
||||
|
||||
def test_provider_id_override(client_with_empty_registry, embedding_model_id):
|
||||
providers = [p for p in client_with_empty_registry.providers.list() if p.api == "vector_io"]
|
||||
if len(providers) != 1:
|
||||
pytest.skip(f"Test requires exactly one vector_io provider, found {len(providers)}")
|
||||
|
||||
provider_id = providers[0].provider_id
|
||||
|
||||
vs = client_with_empty_registry.vector_stores.create(
|
||||
name="test_provider_override", extra_body={"embedding_model": embedding_model_id, "provider_id": provider_id}
|
||||
)
|
||||
assert vs.id is not None
|
||||
assert vs.metadata.get("provider_id") == provider_id
|
||||
|
|
|
|||
57
tests/unit/core/routers/test_vector_io.py
Normal file
57
tests/unit/core/routers/test_vector_io.py
Normal file
|
|
@ -0,0 +1,57 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
from unittest.mock import AsyncMock, Mock
|
||||
|
||||
import pytest
|
||||
|
||||
from llama_stack.apis.vector_io import OpenAICreateVectorStoreRequestWithExtraBody
|
||||
from llama_stack.core.routers.vector_io import VectorIORouter
|
||||
|
||||
|
||||
async def test_single_provider_auto_selection():
|
||||
# provider_id automatically selected during vector store create() when only one provider available
|
||||
mock_routing_table = Mock()
|
||||
mock_routing_table.impls_by_provider_id = {"inline::faiss": "mock_provider"}
|
||||
mock_routing_table.get_all_with_type = AsyncMock(
|
||||
return_value=[
|
||||
Mock(identifier="all-MiniLM-L6-v2", model_type="embedding", metadata={"embedding_dimension": 384})
|
||||
]
|
||||
)
|
||||
mock_routing_table.register_vector_db = AsyncMock(
|
||||
return_value=Mock(identifier="vs_123", provider_id="inline::faiss", provider_resource_id="vs_123")
|
||||
)
|
||||
mock_routing_table.get_provider_impl = AsyncMock(
|
||||
return_value=Mock(openai_create_vector_store=AsyncMock(return_value=Mock(id="vs_123")))
|
||||
)
|
||||
router = VectorIORouter(mock_routing_table)
|
||||
request = OpenAICreateVectorStoreRequestWithExtraBody.model_validate(
|
||||
{"name": "test_store", "embedding_model": "all-MiniLM-L6-v2"}
|
||||
)
|
||||
|
||||
result = await router.openai_create_vector_store(request)
|
||||
assert result.id == "vs_123"
|
||||
|
||||
|
||||
async def test_create_vector_stores_multiple_providers_missing_provider_id_error():
|
||||
# if multiple providers are available, vector store create will error without provider_id
|
||||
mock_routing_table = Mock()
|
||||
mock_routing_table.impls_by_provider_id = {
|
||||
"inline::faiss": "mock_provider_1",
|
||||
"inline::sqlite-vec": "mock_provider_2",
|
||||
}
|
||||
mock_routing_table.get_all_with_type = AsyncMock(
|
||||
return_value=[
|
||||
Mock(identifier="all-MiniLM-L6-v2", model_type="embedding", metadata={"embedding_dimension": 384})
|
||||
]
|
||||
)
|
||||
router = VectorIORouter(mock_routing_table)
|
||||
request = OpenAICreateVectorStoreRequestWithExtraBody.model_validate(
|
||||
{"name": "test_store", "embedding_model": "all-MiniLM-L6-v2"}
|
||||
)
|
||||
|
||||
with pytest.raises(ValueError, match="Multiple vector_io providers available"):
|
||||
await router.openai_create_vector_store(request)
|
||||
Loading…
Add table
Add a link
Reference in a new issue