mirror/computer
1
0
Fork 0
mirror of https://github.com/trycua/computer.git synced 2026-05-19 15:38:48 -05:00
Code Issues Packages Projects Releases Wiki Activity

Add link to HUD integration documentation

Browse Source
This commit is contained in:
James Murdza
2025-09-12 21:41:09 -04:00
parent d41fd91d9a
commit 4ec4bbc888
1 changed files with 7 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
notebooks/hud_hackathon.ipynb
+7 -6
View File
@@ -239,16 +239,17 @@
"from pprint import pprint\n",
"from agent.integrations.hud import run_full_dataset\n",
"\n",
"# Full dataset evaluation (runs via HUD's run_dataset under the hood)\n",
"job_name = f\"osworld-test-{str(uuid.uuid4())[:4]}\"\n",
"\n",
"# Full dataset evaluation (runs via HUD's run_dataset under the hood)\n",
"# See the documentation here: https://docs.trycua.com/docs/agent-sdk/integrations/hud#running-a-full-dataset\n",
"results = await run_full_dataset(\n",
" dataset=\"ddupont/OSWorld-Tiny-Public\", # You can also pass a Dataset or a list[dict]\n",
" job_name=job_name, # Optional; defaults to a timestamp for custom datasets\n",
" dataset=\"ddupont/OSWorld-Tiny-Public\",\n",
" job_name=job_name,\n",
" **agent_config,\n",
" max_concurrent=20, # Tune to your infra\n",
" max_steps=50, # Safety cap per task\n",
" #split=\"train[:5]\" # Limit to just 5 tasks\n",
" max_concurrent=20,\n",
" max_steps=50,\n",
" #split=\"train[:5]\"\n",
")\n",
"\n",
"# results is a list from hud.datasets.run_dataset; inspect/aggregate as needed\n",