phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 18:09:51 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Testing - Memory provider fakes

Browse source 
Summary:
Implementing Memory provider fakes as discussed in this draft https://github.com/meta-llama/llama-stack/pull/490#issuecomment-2492877393.

High level changes:
* Fake provider is specified via the "fake" mark
* Test config will setup a fake fixture for the run of the test
* Test resolver checks fixtures and upon finding a fake provider it injects InlineProviderSpec for fake provider
* Fake provider gets resolved through path/naming convention
* Fake provider implementaion is contained to the tests/ directory and implements stubs and method fakes with minimal functionality to simulate real provider

Instructins to creating a fake
* Create the "fakes" module inside the provider test directory
* Inside the module implement `get_provider_impl` that will return fake implementation object
* Name the fake implementation class to match the fake provider id (e.g. memory_fake -> MemoryFakeImpl)
  * Same rule for the config (e.g. memory_fake -> MemoryFakeConfig)
* Add fake fixture (in the fixtures.py) and setup methods stubs there

Test Plan:
Run memory tests
```
pytest llama_stack/providers/tests/memory/test_memory.py -m "fake" -v -s --tb=short

====================================================================================================== test session starts ======================================================================================================
platform darwin -- Python 3.11.10, pytest-8.3.3, pluggy-1.5.0 -- /opt/homebrew/Caskroom/miniconda/base/envs/llama-stack/bin/python
cachedir: .pytest_cache
rootdir: /Users/vivic/Code/llama-stack
configfile: pyproject.toml
plugins: asyncio-0.24.0, anyio-4.6.2.post1
asyncio: mode=Mode.STRICT, default_loop_scope=None
collected 18 items / 15 deselected / 3 selected

llama_stack/providers/tests/memory/test_memory.py::TestMemory::test_banks_list[fake] PASSED
llama_stack/providers/tests/memory/test_memory.py::TestMemory::test_banks_register[fake] PASSED
llama_stack/providers/tests/memory/test_memory.py::TestMemory::test_query_documents[fake] The scores are: [0.5]
PASSED

========================================================================================= 3 passed, 15 deselected, 10 warnings in 0.46s =========================================================================================

```
This commit is contained in:
Vladimir Ivic 2024-11-25 10:24:52 -08:00
parent 4e6c984c26
commit e2d1b712e2
3 changed files with 189 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

45
llama_stack/providers/tests/memory/fixtures.py
View file

@ -10,6 +10,7 @@ import tempfile
import pytest
import pytest_asyncio
from llama_stack.apis.memory import * # noqa: F403
from llama_stack.distribution.datatypes import Api, Provider, RemoteProviderConfig
from llama_stack.providers.inline.memory.faiss import FaissImplConfig
from llama_stack.providers.remote.memory.pgvector import PGVectorConfig
@ -18,6 +19,48 @@ from llama_stack.providers.tests.resolver import construct_stack_for_test
from llama_stack.providers.utils.kvstore import SqliteKVStoreConfig
from ..conftest import ProviderFixture, remote_stack_fixture
from ..env import get_env_or_fail
from .fakes import InlineMemoryFakeImpl
@pytest.fixture(scope="session")
def memory_fake() -> ProviderFixture:
InlineMemoryFakeImpl.stub_method(
method_name="query_documents",
return_value_matchers={
"programming language": QueryDocumentsResponse(
chunks=[Chunk(content="Python", token_count=1, document_id="")],
scores=[0.1],
),
"AI and brain-inspired computing": QueryDocumentsResponse(
chunks=[
Chunk(content="neural networks", token_count=2, document_id="")
],
scores=[0.1],
),
"computer": QueryDocumentsResponse(
chunks=[
Chunk(content="test-chunk-1", token_count=1, document_id=""),
Chunk(content="test-chunk-2", token_count=1, document_id=""),
],
scores=[0.1, 0.5],
),
"quantum computing": QueryDocumentsResponse(
chunks=[Chunk(content="Python", token_count=1, document_id="")],
scores=[0.5],
),
},
)
fixture = ProviderFixture(
providers=[
Provider(
provider_id="inline_memory_fake",
provider_type="test::fake",
config={},
)
],
)
return fixture
@pytest.fixture(scope="session")
@ -93,7 +136,7 @@ def memory_chroma() -> ProviderFixture:
)
MEMORY_FIXTURES = ["faiss", "pgvector", "weaviate", "remote", "chroma"]
MEMORY_FIXTURES = ["fake", "faiss", "pgvector", "weaviate", "remote", "chroma"]
@pytest_asyncio.fixture(scope="session")