github/OpenHands
1
0
Fork 0
mirror of https://github.com/OpenHands/OpenHands.git synced 2026-03-22 13:47:19 +08:00
Code Issues Packages Projects Releases Wiki Activity

Remove evaluation directory and benchmarking dependencies (#12666)

Browse Source 
Co-authored-by: openhands <openhands@all-hands.dev>
This commit is contained in:
Graham Neubig
2026-02-01 11:39:29 -08:00
committed by GitHub
parent e688fba761
commit afa0417608
336 changed files with 149 additions and 58718 deletions
Download Patch File Download Diff File Expand all files Collapse all files

77
pyproject.toml
View File

@@ -139,40 +139,6 @@ runtime = [
"jupyterlab",
"notebook",
]
evaluation = [
"boto3-stubs[s3]>=1.37.19",
"browsergym==0.13.3",
"browsergym-miniwob==0.13.3",
"browsergym-visualwebarena==0.13.3",
"browsergym-webarena==0.13.3",
"commit0",
"datasets",
"evaluate",
"func-timeout",
"gdown",
"joblib",
"matplotlib",
"multi-swe-bench==0.1.2",
"pandas",
"pyarrow==21",
"retry",
"seaborn",
"streamlit",
"swebench",
"swegym",
"sympy",
"tabulate",
"visualswebench",
"whatthepatch",
]
testgeneval = [
"fuzzywuzzy>=0.18",
"python-levenshtein>=0.26.1,<0.28",
"rouge>=1.0.1",
"tree-sitter-python>=0.23.6",
]
# UV source configuration for git dependencies in evaluation group
[tool.poetry]
name = "openhands-ai"
@@ -328,44 +294,6 @@ jupyterlab = "*"
notebook = "*"
flake8 = "*"
[tool.poetry.group.evaluation]
optional = true
[tool.poetry.group.evaluation.dependencies]
streamlit = "*"
whatthepatch = "*"
retry = "*"
evaluate = "*"
visualswebench = { git = "https://github.com/luolin101/Visual-SWE-bench.git" }
swegym = { git = "https://github.com/SWE-Gym/SWE-Bench-Package.git" }
commit0 = "*"
func_timeout = "*"
sympy = "*"
gdown = "*"
matplotlib = "*"
seaborn = "*"
tabulate = "*"
browsergym = "0.13.3"
browsergym-webarena = "0.13.3"
browsergym-miniwob = "0.13.3"
browsergym-visualwebarena = "0.13.3"
boto3-stubs = { extras = [ "s3" ], version = "^1.37.19" }
# transitive dependency, pinned here to avoid conflicts
pyarrow = "21.0.0"
datasets = "*"
joblib = "*"
swebench = { git = "https://github.com/ryanhoangt/SWE-bench.git", rev = "fix-modal-patch-eval" }
multi-swe-bench = "0.1.2"
pandas = "*"
# tau-bench = { git = "https://github.com/sierra-research/tau-bench.git" }
# bfcl-eval = "*" # TODO: Verify exact package name/source
[tool.poetry.group.testgeneval.dependencies]
fuzzywuzzy = "^0.18.0"
rouge = "^1.0.1"
python-levenshtein = ">=0.26.1,<0.28.0"
tree-sitter-python = "^0.23.6"
[tool.poetry-dynamic-versioning]
enable = true
style = "semver"
@@ -388,8 +316,3 @@ lint.pydocstyle.convention = "google"
concurrency = [ "gevent" ]
relative_files = true
omit = [ "enterprise/tests/*", "**/test_*" ]
[tool.uv.sources]
visualswebench = { git = "https://github.com/luolin101/Visual-SWE-bench.git" }
swegym = { git = "https://github.com/SWE-Gym/SWE-Bench-Package.git" }
swebench = { git = "https://github.com/ryanhoangt/SWE-bench.git", rev = "fix-modal-patch-eval" }