Skip to content

chore: add custom system prompt capability to judge #294

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
GangGreenTemperTatum wants to merge 1 commit into
base: main
Choose a base branch
from
Open

chore: add custom system prompt capability to judge #294

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
13 changes: 12 additions & 1 deletion dreadnode/scorers/judge.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,6 +46,7 @@ def llm_judge(
min_score: float | None = None,
max_score: float | None = None,
name: str = "llm_judge",
system_prompt: str | None = None,
) -> "Scorer[t.Any]":
"""
Score the output of a task using an LLM to judge it against a rubric.
Expand All @@ -60,6 +61,7 @@ def llm_judge(
min_score: Optional minimum score for the judgement - if provided, the score will be clamped to this value.
max_score: Optional maximum score for the judgement - if provided, the score will be clamped to this value.
name: The name of the scorer.
system_prompt: Optional custom system prompt for the judge. If None, uses default.
"""

async def evaluate(
Expand Down Expand Up @@ -97,7 +99,16 @@ async def evaluate(
rubric=rubric,
)

judgement = await judge.bind(generator)(input_data)
if system_prompt:
completion = (
await generator.chat(system_prompt)
.add(input_data.model_dump_json())
.until_parsed_as(Judgement)
.run()
)
judgement = completion.last.parse(Judgement)
else:
judgement = await judge.bind(generator)(input_data)

if min_score is not None:
judgement.score = max(min_score, judgement.score)
Expand Down
Loading