wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

scripts(evals): improve prompts

Browse Source
This commit is contained in:
Aleix Conchillo Flaqué
2025-12-16 17:26:50 -08:00
parent 5f7dbfe775
commit 5b30f1b1ef
2 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
scripts/evals/eval.py
View File

@@ -290,9 +290,9 @@ async def run_eval_pipeline(
"Ignore greetings, comments, non-answers, or requests for clarification."
)
if eval_config.eval_speaks_first:
system_prompt = f"You are an evaluation agent, be extremly brief. You will start the conversation by saying: '{example_prompt}'. {common_system_prompt}"
system_prompt = f"You are an evaluation agent, be extremly brief. Numerical word answers are allowed. You will start the conversation by saying: '{example_prompt}'. {common_system_prompt}"
else:
system_prompt = f"You are an evaluation agent, be extremly brief. First, ask one question: {example_prompt}. {common_system_prompt}"
system_prompt = f"You are an evaluation agent, be extremly brief. Numerical word answers are allowed. First, ask one question: {example_prompt}. {common_system_prompt}"
messages = [
{

2
scripts/evals/run-release-evals.py
View File

@@ -30,7 +30,7 @@ EVAL_SIMPLE_MATH = EvalConfig(
)
EVAL_WEATHER = EvalConfig(
prompt="What's the weather in San Francisco? Temperature should be in any unit, just pick one.",
prompt="What's the weather in San Francisco? Temperature should be in fahrenheits.",
eval="The user talks about the weather in San Francisco, including the degrees.",
)