|
#!/bin/bash
|
|
set -eo pipefail
|
|
|
|
source "evaluation/utils/version_control.sh"
|
|
|
|
MODEL_CONFIG=$1
|
|
COMMIT_HASH=$2
|
|
USE_KNOWLEDGE=$3
|
|
AGENT=$4
|
|
EVAL_LIMIT=$5
|
|
NUM_WORKERS=$6
|
|
|
|
if [ -z "$NUM_WORKERS" ]; then
|
|
NUM_WORKERS=1
|
|
echo "Number of workers not specified, use default $NUM_WORKERS"
|
|
fi
|
|
checkout_eval_branch
|
|
|
|
if [ -z "$AGENT" ]; then
|
|
echo "Agent not specified, use default CodeActAgent"
|
|
AGENT="CodeActAgent"
|
|
fi
|
|
|
|
if [ -z "$USE_KNOWLEDGE" ]; then
|
|
echo "Use knowledge not specified, use default False"
|
|
USE_KNOWLEDGE=false
|
|
fi
|
|
|
|
get_openhands_version
|
|
|
|
echo "AGENT: $AGENT"
|
|
echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
|
|
echo "MODEL_CONFIG: $MODEL_CONFIG"
|
|
|
|
COMMAND="poetry run python evaluation/benchmarks/scienceagentbench/run_infer.py \
|
|
--agent-cls $AGENT \
|
|
--llm-config $MODEL_CONFIG \
|
|
--use-knowledge $USE_KNOWLEDGE \
|
|
--max-iterations 30 \
|
|
--eval-num-workers $NUM_WORKERS \
|
|
--eval-note $OPENHANDS_VERSION" \
|
|
|
|
if [ -n "$EVAL_LIMIT" ]; then
|
|
echo "EVAL_LIMIT: $EVAL_LIMIT"
|
|
COMMAND="$COMMAND --eval-n-limit $EVAL_LIMIT"
|
|
fi
|
|
|
|
|
|
eval $COMMAND
|
|
|
