Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

rebase eval test w/ tool_runtime fixtures #773

Merged
merged 3 commits into from
Jan 15, 2025
Merged

rebase eval test w/ tool_runtime fixtures #773

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
b7e59ba
fix eval test w/ tools
yanxi0830 Jan 15, 2025
bae2896
rebase eval context extraction with query_memory tool
yanxi0830 Jan 15, 2025
26bcb96
comments
yanxi0830 Jan 15, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 9 additions & 2 deletions llama_stack/providers/inline/eval/meta_reference/eval.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,9 @@
from llama_stack.distribution.datatypes import Api
from llama_stack.providers.datatypes import EvalTasksProtocolPrivate

from llama_stack.providers.inline.agents.meta_reference.agent_instance import (
MEMORY_QUERY_TOOL,
)
from llama_stack.providers.utils.common.data_schema_validator import (
ColumnName,
get_valid_schemas,
Expand Down Expand Up @@ -146,8 +149,12 @@ async def _run_agent_generation(
# check if there's a memory retrieval step and extract the context
memory_rag_context = None
for step in final_event.turn.steps:
if step.step_type == StepType.memory_retrieval.value:
memory_rag_context = " ".join(x.text for x in step.inserted_context)
if step.step_type == StepType.tool_execution.value:
for tool_response in step.tool_responses:
if tool_response.tool_name == MEMORY_QUERY_TOOL:
memory_rag_context = " ".join(
x.text for x in tool_response.content
)

agent_generation = {}
agent_generation[ColumnName.generated_answer.value] = (
Expand Down
5 changes: 5 additions & 0 deletions llama_stack/providers/tests/eval/conftest.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,7 @@
from ..memory.fixtures import MEMORY_FIXTURES
from ..safety.fixtures import SAFETY_FIXTURES
from ..scoring.fixtures import SCORING_FIXTURES
from ..tools.fixtures import TOOL_RUNTIME_FIXTURES
from .fixtures import EVAL_FIXTURES

DEFAULT_PROVIDER_COMBINATIONS = [
Expand All @@ -27,6 +28,7 @@
"agents": "meta_reference",
"safety": "llama_guard",
"memory": "faiss",
"tool_runtime": "memory_and_search",
},
id="meta_reference_eval_fireworks_inference",
marks=pytest.mark.meta_reference_eval_fireworks_inference,
Expand All @@ -40,6 +42,7 @@
"agents": "meta_reference",
"safety": "llama_guard",
"memory": "faiss",
"tool_runtime": "memory_and_search",
},
id="meta_reference_eval_together_inference",
marks=pytest.mark.meta_reference_eval_together_inference,
Expand All @@ -53,6 +56,7 @@
"agents": "meta_reference",
"safety": "llama_guard",
"memory": "faiss",
"tool_runtime": "memory_and_search",
},
id="meta_reference_eval_together_inference_huggingface_datasetio",
marks=pytest.mark.meta_reference_eval_together_inference_huggingface_datasetio,
Expand Down Expand Up @@ -98,6 +102,7 @@ def pytest_generate_tests(metafunc):
"agents": AGENTS_FIXTURES,
"safety": SAFETY_FIXTURES,
"memory": MEMORY_FIXTURES,
"tool_runtime": TOOL_RUNTIME_FIXTURES,
}
combinations = (
get_provider_fixture_overrides(metafunc.config, available_fixtures)
Expand Down
11 changes: 10 additions & 1 deletion llama_stack/providers/tests/eval/fixtures.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,13 @@ def eval_meta_reference() -> ProviderFixture:


@pytest_asyncio.fixture(scope="session")
async def eval_stack(request, inference_model, judge_model):
async def eval_stack(
request,
inference_model,
judge_model,
tool_group_input_memory,
tool_group_input_tavily_search,
):
fixture_dict = request.param

providers = {}
Expand All @@ -48,6 +54,7 @@ async def eval_stack(request, inference_model, judge_model):
"agents",
"safety",
"memory",
"tool_runtime",
]:
fixture = request.getfixturevalue(f"{key}_{fixture_dict[key]}")
providers[key] = fixture.providers
Expand All @@ -63,6 +70,7 @@ async def eval_stack(request, inference_model, judge_model):
Api.agents,
Api.safety,
Api.memory,
Api.tool_runtime,
],
providers,
provider_data,
Expand All @@ -73,6 +81,7 @@ async def eval_stack(request, inference_model, judge_model):
judge_model,
]
],
tool_groups=[tool_group_input_memory, tool_group_input_tavily_search],
)

return test_stack.impls
Loading