Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation.
Rust agentai-agentapplecomputer-usecomputer-use-agentcontainerizationcuadesktop-automationhacktoberfestlumemacosmanusoperatorswiftvirtualizationvirtualization-frameworkwindowswindows-sandbox
updated nb
Dillon DuPont13fc9e2e90b7
diff --git a/notebooks/ollama_nb.ipynb b/notebooks/ollama_nb.ipynbindex 7bb572842b..6a59530bb3 100644--- a/notebooks/ollama_nb.ipynb+++ b/notebooks/ollama_nb.ipynb@@ -25,7 +25,7 @@"\n","The easiest way to get started is by getting set up with the Cua development repository.\n","\n",- "Install [Docker](https://www.docker.com/products/docker-desktop/), [pdm](https://pdm-project.org/en/latest/#recommended-installation-method), and [Ollama](https://ollama.com/) (optional, but recommended for this notebook).\n",+ "Install [Docker](https://www.docker.com/products/docker-desktop/) and [pdm](https://pdm-project.org/en/latest/#recommended-installation-method)\n","\n","Clone the Cua repository:\n","\n",@@ -51,7 +51,7 @@"\n","- `OPENAI_API_KEY` (if composing with OpenAI)\n","- `ANTHROPIC_API_KEY` (if composing with Anthropic)\n",- "- `OLLAMA_HOST` (defaults to `http://localhost:11434`)\n",+ "- `OLLAMA_API_BASE` (defaults to `http://localhost:11434`)\n","\n","Note: For Cua Cloud computers, you would also set `CUA_API_KEY` and `CUA_CONTAINER_NAME`, but this notebook uses Docker for the computer.\n"]@@ -69,7 +69,7 @@"ANTHROPIC_API_KEY=\n","\n","# Ollama endpoint (default shown)\n",- "OLLAMA_HOST=http://localhost:11434\n",+ "OLLAMA_API_BASE=http://localhost:11434\n","\"\"\"\n","\n","from pathlib import Path\n",@@ -93,7 +93,7 @@"load_dotenv(dotenv_path='.env', override=True)\n","print('OPENAI_API_KEY set:', bool(os.getenv('OPENAI_API_KEY')))\n","print('ANTHROPIC_API_KEY set:', bool(os.getenv('ANTHROPIC_API_KEY')))\n",- "print('OLLAMA_HOST:', os.getenv('OLLAMA_HOST', 'http://localhost:11434'))\n"+ "print('OLLAMA_API_BASE:', os.getenv('OLLAMA_API_BASE', 'http://localhost:11434'))\n"]},{@@ -115,7 +115,7 @@"\n","```bash\n","docker exec -it ollama ollama pull gemma3:4b\n",- "docker exec -it ollama ollama pull blaifa/InternVL3_5\n",+ "docker exec -it ollama ollama pull blaifa/InternVL3_5:8b\n","```\n","\n","Make sure your `OLLAMA_HOST` points to `http://localhost:11434`.\n"@@ -177,9 +177,12 @@"import logging\n","from pathlib import Path\n","from agent import ComputerAgent\n",+ "import os\n",+ "\n",+ "os.environ['OLLAMA_API_BASE'] = 'http://localhost:11434'\n","\n","agent_all_in_one = ComputerAgent(\n",- " model=\"ollama/blaifa/InternVL3_5\",\n",+ " model=\"ollama/blaifa/InternVL3_5:8b\",\n"," tools=[computer],\n"," trajectory_dir=str(Path('trajectories')),\n"," only_n_most_recent_images=3,\n",