Skip to content

Read-only code review of PR 349 #381

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

Open
google-labs-jules wants to merge 3 commits into from
Open

Read-only code review of PR 349 #381

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
33a73e9
chore: perform read-only code review for PR 349
google-labs-jules[bot] Jul 30, 2026
cccc619
Address PR #349 review comments
google-labs-jules[bot] Jul 30, 2026
21f392f
Address PR #349 review comments
google-labs-jules[bot] Aug 4, 2026
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
9 changes: 3 additions & 6 deletions backend/src/agent/evaluation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,7 @@
from agent.models import GEMINI_PRO

# Module-level cache for the judge model instance
_judge_model_cache: Optional[ChatGoogleGenerativeAI] = None
_judge_model_cache: ChatGoogleGenerativeAI | None = None


def _get_judge_model() -> ChatGoogleGenerativeAI:
Expand Down Expand Up @@ -74,8 +74,7 @@ class GroundednessScore(BaseModel):


def eval_quality(request: str, report: str) -> Dict[str, Any]:
"""
Evaluates the overall quality of a research report.
"""Evaluates the overall quality of a research report.

Args:
request: The original user research request.
Expand Down Expand Up @@ -106,9 +105,7 @@ def eval_quality(request: str, report: str) -> Dict[str, Any]:


def eval_groundedness(report: str, sources: List[str]) -> Dict[str, Any]:
"""
Evaluates how well the report is grounded in the provided sources.
"""
"""Evaluates how well the report is grounded in the provided sources."""
# Simplified placeholder for groundedness logic
# In a real scenario, this would involve extracting claims and checking them against summaries
prompt = ChatPromptTemplate.from_messages(
Expand Down