base on AI agent using GPT-4V(ision) capable of using a mouse/keyboard to interact with web UI # GPT-4V-Act: Chromium Copilot
> 🔥 **Update (September 14, 2024)**: Check out [Windows Agent Arena (WAA)](https://github.com/microsoft/windowsagentarena)! This project incorporates all the features previously planned for GPT-4V-Act, including AI labeling to enable set-of-marks prompting in desktop UI environments.
GPT-4V-Act serves as an eloquent multimodal AI assistant that harmoniously combines GPT-4V(ision) with a web browser. It's designed to mirror the input and output of a human operator—primarily screen feedback and low-level mouse/keyboard interaction. The objective is to foster a smooth transition between human-computer operations, facilitating the creation of tools that considerably boost the accessibility of any user interface (UI), aid workflow automation, and enable automated UI testing.
## How it works
GPT-4V-Act leverages both [GPT-4V(ision)](https://openai.com/research/gpt-4v-system-card) and [Set-of-Mark Prompting](https://arxiv.org/abs/2310.11441), together with a tailored auto-labeler. This auto-labeler assigns a unique numerical ID to each interactable UI element.
By incorporating a task and a screenshot as input, GPT-4V-Act can deduce the subsequent action required to accomplish a task. For mouse/keyboard output, it can refer to the numerical labels for exact pixel coordinates.
**Get Started!**
```bash
# Clone the repo
git clone https://github.com/ddupont808/GPT-4V-Act ai-browser
# Navigate to the repo directory
cd ai-browser
# Install the required packages
npm install
# Start the demo
npm start
```
## Features
- 🔄 Vision (Partial)
- ✅ JS DOM auto-labeler (w/ COCO export)
- ❌ AI auto-labeler
- ✅ Clicking
- 🔄 Typing (Partial)
- ✅ Typing characters (letters, numbers, strings)
- ❌ Typing special keycodes (enter, pgup, pgdown)
- ❌ Scrolling
- ❌ Prompting user for more information
- ❌ Remembering information relevant to task
If you have ideas, feedback, or want to contribute, feel free to create an Issue or reach out to
[email protected]
## Demonstration Prompt
Below is an example of using the user-interface to instruct the agent to "play a random song for me"
This is the prompt seen by GPT-4V and the corresponding output
### User
```markdown
task: play a random song for me
type ClickAction = { action: "click", element: number }
type TypeAction = { action: "type", element: number, text: string }
type ScrollAction = { action: "scroll", direction: "up" | "down" }
type RequestInfoFromUser = { action: "request-info", prompt: string }
type RememberInfoFromSite = { action: "remember-info", info: string }
type Done = { action: "done" }
## response format
{
briefExplanation: string,
nextAction: ClickAction | TypeAction | ScrollAction | RequestInfoFromUser | RememberInfoFromSite | Done
}
## instructions
# observe the screenshot, and think about the next action
# output your response in a json markdown code block
```
### Assistant
```json
{
"briefExplanation": "I'll type 'random song' into the search bar to find a song for you.",
"nextAction": { "action": "type", "element": 7, "text": "random song" }
}
```
", Assign "at most 3 tags" to the expected json: {"id":"4432","tags":[]} "only from the tags list I provide: [{"id":77,"name":"3d"},{"id":89,"name":"agent"},{"id":17,"name":"ai"},{"id":54,"name":"algorithm"},{"id":24,"name":"api"},{"id":44,"name":"authentication"},{"id":3,"name":"aws"},{"id":27,"name":"backend"},{"id":60,"name":"benchmark"},{"id":72,"name":"best-practices"},{"id":39,"name":"bitcoin"},{"id":37,"name":"blockchain"},{"id":1,"name":"blog"},{"id":45,"name":"bundler"},{"id":58,"name":"cache"},{"id":21,"name":"chat"},{"id":49,"name":"cicd"},{"id":4,"name":"cli"},{"id":64,"name":"cloud-native"},{"id":48,"name":"cms"},{"id":61,"name":"compiler"},{"id":68,"name":"containerization"},{"id":92,"name":"crm"},{"id":34,"name":"data"},{"id":47,"name":"database"},{"id":8,"name":"declarative-gui "},{"id":9,"name":"deploy-tool"},{"id":53,"name":"desktop-app"},{"id":6,"name":"dev-exp-lib"},{"id":59,"name":"dev-tool"},{"id":13,"name":"ecommerce"},{"id":26,"name":"editor"},{"id":66,"name":"emulator"},{"id":62,"name":"filesystem"},{"id":80,"name":"finance"},{"id":15,"name":"firmware"},{"id":73,"name":"for-fun"},{"id":2,"name":"framework"},{"id":11,"name":"frontend"},{"id":22,"name":"game"},{"id":81,"name":"game-engine "},{"id":23,"name":"graphql"},{"id":84,"name":"gui"},{"id":91,"name":"http"},{"id":5,"name":"http-client"},{"id":51,"name":"iac"},{"id":30,"name":"ide"},{"id":78,"name":"iot"},{"id":40,"name":"json"},{"id":83,"name":"julian"},{"id":38,"name":"k8s"},{"id":31,"name":"language"},{"id":10,"name":"learning-resource"},{"id":33,"name":"lib"},{"id":41,"name":"linter"},{"id":28,"name":"lms"},{"id":16,"name":"logging"},{"id":76,"name":"low-code"},{"id":90,"name":"message-queue"},{"id":42,"name":"mobile-app"},{"id":18,"name":"monitoring"},{"id":36,"name":"networking"},{"id":7,"name":"node-version"},{"id":55,"name":"nosql"},{"id":57,"name":"observability"},{"id":46,"name":"orm"},{"id":52,"name":"os"},{"id":14,"name":"parser"},{"id":74,"name":"react"},{"id":82,"name":"real-time"},{"id":56,"name":"robot"},{"id":65,"name":"runtime"},{"id":32,"name":"sdk"},{"id":71,"name":"search"},{"id":63,"name":"secrets"},{"id":25,"name":"security"},{"id":85,"name":"server"},{"id":86,"name":"serverless"},{"id":70,"name":"storage"},{"id":75,"name":"system-design"},{"id":79,"name":"terminal"},{"id":29,"name":"testing"},{"id":12,"name":"ui"},{"id":50,"name":"ux"},{"id":88,"name":"video"},{"id":20,"name":"web-app"},{"id":35,"name":"web-server"},{"id":43,"name":"webassembly"},{"id":69,"name":"workflow"},{"id":87,"name":"yaml"}]" returns me the "expected json"