Skip to content

armgit / cua

Public Imported from GitHub
0

Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation.

Add link to HUD integration documentation

James Murdza4ec4bbc888c7
diff --git a/notebooks/hud_hackathon.ipynb b/notebooks/hud_hackathon.ipynb
index b0e6e84cb4..7192b00045 100644
--- a/notebooks/hud_hackathon.ipynb
+++ b/notebooks/hud_hackathon.ipynb
@@ -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",