github/AutoGPT
1
1
Fork 0
mirror of https://github.com/Significant-Gravitas/AutoGPT.git synced 2026-01-09 15:17:59 -05:00
Code Issues Packages Projects Releases Wiki Activity

Add eval_id and sync Skill Tree with Frontend(#5287)

Browse Source 
Add eval_id to skill tree

Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
This commit is contained in:
merwanehamadi
2023-09-21 13:36:17 -07:00
committed by GitHub
parent 295787c948
commit f4e7b1c61c
63 changed files with 2010 additions and 792 deletions
Download Patch File Download Diff File Expand all files Collapse all files

43
.github/workflows/benchmark-ci.yml vendored
View File

@@ -102,10 +102,9 @@ jobs:
sh run &
sleep 20
set +e # Ignore non-zero exit codes and continue execution
echo "Running the following command: ${prefix}agbenchmark --maintain --mock"
prefix="poetry run "
echo "Running the following command: poetry run agbenchmark --maintain --mock"
${prefix}agbenchmark --maintain --mock
poetry run agbenchmark --maintain --mock
EXIT_CODE=$?
set -e # Stop ignoring non-zero exit codes
# Check if the exit code was 5, and if so, exit with 0 instead
@@ -113,23 +112,37 @@ jobs:
echo "regression_tests.json is empty."
fi
echo "Running the following command: ${prefix}agbenchmark --mock"
${prefix}agbenchmark --mock
echo "Running the following command: poetry run agbenchmark --mock"
poetry run agbenchmark --mock
echo "Running the following command: ${prefix}agbenchmark --mock --category=retrieval"
${prefix}agbenchmark --mock --category=retrieval
echo "Running the following command: poetry run agbenchmark --mock --category=retrieval"
poetry run agbenchmark --mock --category=retrieval
echo "Running the following command: ${prefix}agbenchmark --mock --category=interface"
${prefix}agbenchmark --mock --category=interface
echo "Running the following command: poetry run agbenchmark --mock --category=interface"
poetry run agbenchmark --mock --category=interface
echo "Running the following command: ${prefix}agbenchmark --mock --category=coding"
${prefix}agbenchmark --mock --category=coding
echo "Running the following command: poetry run agbenchmark --mock --category=coding"
poetry run agbenchmark --mock --category=coding
echo "Running the following command: ${prefix}agbenchmark --test=WriteFile"
${prefix}agbenchmark --test=WriteFile
sh run_benchmark &
echo "Running the following command: poetry run agbenchmark --test=WriteFile"
poetry run agbenchmark --test=WriteFile
sh run_benchmark serve &
sleep 10
cd ../../benchmark
poetry install
poetry run pytest tests
echo "Adding the BUILD_SKILL_TREE environment variable. This will attempt to add new elements in the skill tree. If new elements are added, the CI fails because they should have been pushed"
export BUILD_SKILL_TREE=true
poetry run agbenchmark --mock
poetry run pytest -vv -s tests
CHANGED=$(git diff --name-only | grep -E '(agbenchmark/challenges)|(../frontend/assets)') || echo "No diffs"
if [ ! -z "$CHANGED" ]; then
echo "There are unstaged changes please run agbenchmark and commit those changes since they are needed."
echo "$CHANGED"
exit 1
else
echo "No unstaged changes."
fi
env:
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}