Skip to content

fix(evaluate): 1.fix evalset parse. 2.fix save_eval_set #291

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

Merged
yaozheng-fang merged 1 commit into from
Nov 7, 2025
Merged

fix(evaluate): 1.fix evalset parse. 2.fix save_eval_set #291

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
25 changes: 24 additions & 1 deletion veadk/evaluation/base_evaluator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -442,7 +442,10 @@ def build_eval_set(
_input = user_content.parts[0].text
_expected_output = invocation.final_response.parts[0].text

if invocation.intermediate_data.tool_uses:
if (
hasattr(invocation.intermediate_data, "tool_uses")
and invocation.intermediate_data.tool_uses
):
for expected_tool_use in invocation.intermediate_data.tool_uses:
_expected_tool.append(
{
Expand All @@ -451,6 +454,26 @@ def build_eval_set(
}
)

elif (
hasattr(invocation.intermediate_data, "invocation_events")
and invocation.intermediate_data.invocation_events
):
for event in invocation.intermediate_data.invocation_events:
if hasattr(event, "content") and hasattr(
event.content, "parts"
):
for part in event.content.parts:
if (
hasattr(part, "function_call")
and part.function_call is not None
):
_expected_tool.append(
{
"name": part.function_call.name,
"args": part.function_call.args,
}
)

eval_case_data.invocations.append(
Invocation(
invocation_id=invocation.invocation_id,
Expand Down
5 changes: 3 additions & 2 deletions veadk/evaluation/eval_set_recorder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,7 @@

import time
from pathlib import Path

import os
from google.adk.cli.utils import evals
from google.adk.evaluation.eval_case import EvalCase, SessionInput
from google.adk.evaluation.local_eval_sets_manager import LocalEvalSetsManager
Expand Down Expand Up @@ -131,7 +131,8 @@ async def dump(
dump_path = self._get_eval_set_file_path(app_name, self.eval_set_id)
Path(dump_path).parent.mkdir(parents=True, exist_ok=True)

self.create_eval_set(app_name=app_name, eval_set_id=self.eval_set_id)
if not os.path.exists(dump_path):
self.create_eval_set(app_name=app_name, eval_set_id=self.eval_set_id)

await self.add_session_to_eval_set(
app_name=app_name,
Expand Down