cua-computer 0.1.23__tar.gz → 0.1.25__tar.gz

{cua_computer-0.1.23 → cua_computer-0.1.25}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cua-computer
-Version: 0.1.23
+Version: 0.1.25
 Summary: Computer-Use Interface (CUI) framework powering Cua
 Author-Email: TryCua <gh@trycua.com>
 Requires-Python: >=3.10
@@ -44,7 +44,7 @@ Description-Content-Type: text/markdown
 ```python
 from computer import Computer
 
-computer = Computer(os="macos", display="1024x768", memory="8GB", cpu="4")
+computer = Computer(os_type="macos", display="1024x768", memory="8GB", cpu="4")
 try:
     await computer.run()
     
@@ -85,30 +85,78 @@ Refer to this notebook for a step-by-step guide on how to use the Computer-Use I
 
 ## Using the Gradio Computer UI
 
-The computer module includes a Gradio UI for creating and sharing demonstration data. The UI provides built-in integration with Hugging Face Datasets for sharing demonstrations and incorporating them into CUA ML pipelines.
+The computer module includes a Gradio UI for creating and sharing demonstration data. We make it easy for people to build community datasets for better computer use models with an upload to Huggingface feature.
 
 ```bash
 # Install with UI support
 pip install "cua-computer[ui]"
 ```
 
+> **Note:** For precise control of the computer, we recommend using VNC or Screen Sharing instead of the Computer Gradio UI.
 
-<details open>
-<summary>View demonstration video</summary>
-<video src="https://github.com/user-attachments/assets/7c683b58-f04d-4e8c-b63f-6ef36e9637d5" controls width="600"></video>
-</details>
+### Building and Sharing Demonstrations with Huggingface
 
-> **Note:** For precise control of the computer, we recommend using VNC or Screen Sharing instead of the Computer Gradio UI.
+Follow these steps to contribute your own demonstrations:
+
+#### 1. Set up Huggingface Access
 
+Set your HF_TOKEN in a .env file or in your environment variables:
+
+```bash
+# In .env file
+HF_TOKEN=your_huggingface_token
+```
 
-### Launch the UI
+#### 2. Launch the Computer UI
 
 ```python
 # launch_ui.py
 from computer.ui.gradio.app import create_gradio_ui
+from dotenv import load_dotenv
+load_dotenv('.env')
 
 app = create_gradio_ui()
 app.launch(share=False)
 ```
 
 For examples, see [Computer UI Examples](../../examples/computer_ui_examples.py)
+
+#### 3. Record Your Tasks
+
+<details open>
+<summary>View demonstration video</summary>
+<video src="https://github.com/user-attachments/assets/de3c3477-62fe-413c-998d-4063e48de176" controls width="600"></video>
+</details>
+
+Record yourself performing various computer tasks using the UI.
+
+#### 4. Save Your Demonstrations
+
+<details open>
+<summary>View demonstration video</summary>
+<video src="https://github.com/user-attachments/assets/5ad1df37-026a-457f-8b49-922ae805faef" controls width="600"></video>
+</details>
+
+Save each task by picking a descriptive name and adding relevant tags (e.g., "office", "web-browsing", "coding").
+
+#### 5. Record Additional Demonstrations
+
+Repeat steps 3 and 4 until you have a good amount of demonstrations covering different tasks and scenarios.
+
+#### 6. Upload to Huggingface
+
+<details open>
+<summary>View demonstration video</summary>
+<video src="https://github.com/user-attachments/assets/c586d460-3877-4b5f-a736-3248886d2134" controls width="600"></video>
+</details>
+
+Upload your dataset to Huggingface by:
+- Naming it as `{your_username}/{dataset_name}`
+- Choosing public or private visibility
+- Optionally selecting specific tags to upload only tasks with certain tags
+
+#### Examples and Resources
+
+- Example Dataset: [ddupont/test-dataset](https://huggingface.co/datasets/ddupont/test-dataset)
+- Find Community Datasets: 🔍 [Browse CUA Datasets on Huggingface](https://huggingface.co/datasets?other=cua)
+

{cua_computer-0.1.23 → cua_computer-0.1.25}/README.md

@@ -26,7 +26,7 @@
 ```python
 from computer import Computer
 
-computer = Computer(os="macos", display="1024x768", memory="8GB", cpu="4")
+computer = Computer(os_type="macos", display="1024x768", memory="8GB", cpu="4")
 try:
     await computer.run()
     
@@ -67,30 +67,78 @@ Refer to this notebook for a step-by-step guide on how to use the Computer-Use I
 
 ## Using the Gradio Computer UI
 
-The computer module includes a Gradio UI for creating and sharing demonstration data. The UI provides built-in integration with Hugging Face Datasets for sharing demonstrations and incorporating them into CUA ML pipelines.
+The computer module includes a Gradio UI for creating and sharing demonstration data. We make it easy for people to build community datasets for better computer use models with an upload to Huggingface feature.
 
 ```bash
 # Install with UI support
 pip install "cua-computer[ui]"
 ```
 
+> **Note:** For precise control of the computer, we recommend using VNC or Screen Sharing instead of the Computer Gradio UI.
 
-<details open>
-<summary>View demonstration video</summary>
-<video src="https://github.com/user-attachments/assets/7c683b58-f04d-4e8c-b63f-6ef36e9637d5" controls width="600"></video>
-</details>
+### Building and Sharing Demonstrations with Huggingface
 
-> **Note:** For precise control of the computer, we recommend using VNC or Screen Sharing instead of the Computer Gradio UI.
+Follow these steps to contribute your own demonstrations:
+
+#### 1. Set up Huggingface Access
 
+Set your HF_TOKEN in a .env file or in your environment variables:
+
+```bash
+# In .env file
+HF_TOKEN=your_huggingface_token
+```
 
-### Launch the UI
+#### 2. Launch the Computer UI
 
 ```python
 # launch_ui.py
 from computer.ui.gradio.app import create_gradio_ui
+from dotenv import load_dotenv
+load_dotenv('.env')
 
 app = create_gradio_ui()
 app.launch(share=False)
 ```
 
 For examples, see [Computer UI Examples](../../examples/computer_ui_examples.py)
+
+#### 3. Record Your Tasks
+
+<details open>
+<summary>View demonstration video</summary>
+<video src="https://github.com/user-attachments/assets/de3c3477-62fe-413c-998d-4063e48de176" controls width="600"></video>
+</details>
+
+Record yourself performing various computer tasks using the UI.
+
+#### 4. Save Your Demonstrations
+
+<details open>
+<summary>View demonstration video</summary>
+<video src="https://github.com/user-attachments/assets/5ad1df37-026a-457f-8b49-922ae805faef" controls width="600"></video>
+</details>
+
+Save each task by picking a descriptive name and adding relevant tags (e.g., "office", "web-browsing", "coding").
+
+#### 5. Record Additional Demonstrations
+
+Repeat steps 3 and 4 until you have a good amount of demonstrations covering different tasks and scenarios.
+
+#### 6. Upload to Huggingface
+
+<details open>
+<summary>View demonstration video</summary>
+<video src="https://github.com/user-attachments/assets/c586d460-3877-4b5f-a736-3248886d2134" controls width="600"></video>
+</details>
+
+Upload your dataset to Huggingface by:
+- Naming it as `{your_username}/{dataset_name}`
+- Choosing public or private visibility
+- Optionally selecting specific tags to upload only tasks with certain tags
+
+#### Examples and Resources
+
+- Example Dataset: [ddupont/test-dataset](https://huggingface.co/datasets/ddupont/test-dataset)
+- Find Community Datasets: 🔍 [Browse CUA Datasets on Huggingface](https://huggingface.co/datasets?other=cua)
+

{cua_computer-0.1.23 → cua_computer-0.1.25}/computer/computer.py

@@ -29,7 +29,7 @@ class Computer:
         display: Union[Display, Dict[str, int], str] = "1024x768",
         memory: str = "8GB",
         cpu: str = "4",
-        os: OSType = "macos",
+        os_type: OSType = "macos",
         name: str = "",
         image: str = "macos-sequoia-cua:latest",
         shared_directories: Optional[List[str]] = None,
@@ -68,6 +68,7 @@ class Computer:
         self.image = image
         self.port = port
         self.host = host
+        self.os_type = os_type
 
         # Store telemetry preference
         self._telemetry_enabled = telemetry_enabled
@@ -129,8 +130,8 @@ class Computer:
         self.shared_paths = []
         if shared_directories:
             for path in shared_directories:
-                abs_path = os.path.abspath(os.path.expanduser(path))  # type: ignore[attr-defined]
-                if not os.path.exists(abs_path):  # type: ignore[attr-defined]
+                abs_path = os.path.abspath(os.path.expanduser(path))
+                if not os.path.exists(abs_path):
                     raise ValueError(f"Shared directory does not exist: {path}")
                 self.shared_paths.append(abs_path)
         self._pylume_context = None
@@ -188,7 +189,7 @@ class Computer:
                 self._interface = cast(
                     BaseComputerInterface,
                     InterfaceFactory.create_interface_for_os(
-                        os=self.os, ip_address=ip_address  # type: ignore[arg-type]
+                        os=self.os_type, ip_address=ip_address  # type: ignore[arg-type]
                     ),
                 )
 
@@ -288,13 +289,13 @@ class Computer:
 
         try:
             # Initialize the interface using the factory with the specified OS
-            self.logger.info(f"Initializing interface for {self.os} at {ip_address}")
+            self.logger.info(f"Initializing interface for {self.os_type} at {ip_address}")
             from .interface.base import BaseComputerInterface
 
             self._interface = cast(
                 BaseComputerInterface,
                 InterfaceFactory.create_interface_for_os(
-                    os=self.os, ip_address=ip_address  # type: ignore[arg-type]
+                    os=self.os_type, ip_address=ip_address  # type: ignore[arg-type]
                 ),
             )
 

{cua_computer-0.1.23 → cua_computer-0.1.25}/computer/interface/base.py

@@ -79,6 +79,17 @@ class BaseComputerInterface(ABC):
         """
         pass
 
+    @abstractmethod
+    async def drag(self, path: List[Tuple[int, int]], button: str = "left", duration: float = 0.5) -> None:
+        """Drag the cursor along a path of coordinates.
+
+        Args:
+            path: List of (x, y) coordinate tuples defining the drag path
+            button: The mouse button to use ('left', 'middle', 'right')
+            duration: Total time in seconds that the drag operation should take
+        """
+        pass
+
     # Keyboard Actions
     @abstractmethod
     async def type_text(self, text: str) -> None:

{cua_computer-0.1.23 → cua_computer-0.1.25}/computer/interface/macos.py

@@ -328,6 +328,11 @@ class MacOSComputerInterface(BaseComputerInterface):
             "drag_to", {"x": x, "y": y, "button": button, "duration": duration}
         )
 
+    async def drag(self, path: List[Tuple[int, int]], button: str = "left", duration: float = 0.5) -> None:
+        await self._send_command(
+            "drag", {"path": path, "button": button, "duration": duration}
+        )
+
     # Keyboard Actions
     async def type_text(self, text: str) -> None:
         await self._send_command("type_text", {"text": text})

{cua_computer-0.1.23 → cua_computer-0.1.25}/computer/interface/models.py

@@ -7,6 +7,9 @@ NavigationKey = Literal['pagedown', 'pageup', 'home', 'end', 'left', 'right', 'u
 # Special key literals
 SpecialKey = Literal['enter', 'esc', 'tab', 'space', 'backspace', 'del']
 
+# Modifier key literals
+ModifierKey = Literal['ctrl', 'alt', 'shift', 'win', 'command', 'option']
+
 # Function key literals
 FunctionKey = Literal['f1', 'f2', 'f3', 'f4', 'f5', 'f6', 'f7', 'f8', 'f9', 'f10', 'f11', 'f12']
 
@@ -35,6 +38,14 @@ class Key(Enum):
     BACKSPACE = 'backspace'
     DELETE = 'del'
     
+    # Modifier keys
+    ALT = 'alt'
+    CTRL = 'ctrl'
+    SHIFT = 'shift'
+    WIN = 'win'
+    COMMAND = 'command'
+    OPTION = 'option'
+    
     # Function keys
     F1 = 'f1'
     F2 = 'f2'
@@ -73,14 +84,27 @@ class Key(Enum):
             'escape': cls.ESCAPE,
             'esc': cls.ESC,
             'delete': cls.DELETE,
-            'del': cls.DELETE
+            'del': cls.DELETE,
+            # Modifier key mappings
+            'alt': cls.ALT,
+            'ctrl': cls.CTRL,
+            'control': cls.CTRL,
+            'shift': cls.SHIFT,
+            'win': cls.WIN,
+            'windows': cls.WIN,
+            'super': cls.WIN,
+            'command': cls.COMMAND,
+            'cmd': cls.COMMAND,
+            '⌘': cls.COMMAND,
+            'option': cls.OPTION,
+            '⌥': cls.OPTION,
         }
         
         normalized = key.lower().strip()
         return key_mapping.get(normalized, key)
 
 # Combined key type
-KeyType = Union[Key, NavigationKey, SpecialKey, FunctionKey, str]
+KeyType = Union[Key, NavigationKey, SpecialKey, ModifierKey, FunctionKey, str]
 
 class AccessibilityWindow(TypedDict):
     """Information about a window in the accessibility tree."""

{cua_computer-0.1.23 → cua_computer-0.1.25}/computer/ui/gradio/app.py

@@ -532,7 +532,7 @@ async def handle_init_computer():
     """Initialize the computer instance and tools"""
     global computer, tool_call_logs, tools
     
-    computer = Computer(os="macos", display="1024x768", memory="8GB", cpu="4")
+    computer = Computer(os_type="macos", display="1024x768", memory="8GB", cpu="4")
     await computer.run()
     
     # Log computer initialization as a tool call

{cua_computer-0.1.23 → cua_computer-0.1.25}/pyproject.toml

@@ -6,7 +6,7 @@ build-backend = "pdm.backend"
 
 [project]
 name = "cua-computer"
-version = "0.1.23"
+version = "0.1.25"
 description = "Computer-Use Interface (CUI) framework powering Cua"
 readme = "README.md"
 authors = [
@@ -50,7 +50,7 @@ target-version = [
 
 [tool.ruff]
 line-length = 100
-target-version = "0.1.23"
+target-version = "0.1.25"
 select = [
     "E",
     "F",
@@ -64,7 +64,7 @@ docstring-code-format = true
 
 [tool.mypy]
 strict = true
-python_version = "0.1.23"
+python_version = "0.1.25"
 ignore_missing_imports = true
 disallow_untyped_defs = true
 check_untyped_defs = true