[Eval] DiscoveryBench OpenHands Integration - #7

Open

Ethan0456 wants to merge 16 commits into

mainfrom

test/discoverybench-openhands-integration

Commits on Oct 30, 2024

init(eval): add baseline DiscoveryBench infer script
Ethan0456
committed
7c9ccaa
feat(eval): implement create_dataset function to clone and prepare dataset
Ethan0456
committed
da61d20
feat(eval): implement process_instance function
Ethan0456
committed
cfe39b6
feat(eval): initialize docker runtime with necessary python libraries
Ethan0456
committed
33071aa
feat(eval): implement complete_runtime function
Ethan0456
committed
a585cee
feat(eval): add response parser for DiscoveryBench evaluation
Ethan0456
committed
98efba4
docs(eval): Add README for discoverybench
suranah
authored
8140aae
docs(eval): Add README for DiscoveryBench eval utils
suranah
authored
477eb84
refactor(eval): integrate DiscoveryBench evaluation and update scripts for linting compliance
Ethan0456
committed
f1bf06c
feat(eval): add run_infer.sh to execute inference
Ethan0456
committed
23a8027
feat(eval): add AgentConfig to disable function calling and enable jupyter and browsing delegate config
Ethan0456
committed
0374351
chore(eval): set execute permission for run_infer.sh
Ethan0456
committed
7d35c51
docs(eval): update README to comply with linting rules
Ethan0456
authored
7f3ab98
Increase share popup duration from 5s to 10s (#4625)

tofarr
and
openhands-agent
authored
75ee54b
Load GitHub users list at startup for improved authentication performance (#4567)

rbren
and
openhands-agent
authored
e21abce
Merge branch 'main' into test/discoverybench-openhands-integration
suranah
authored
adf0b87