Redefining internet surfing by transforming natural language instructions into seamless browser interactions.
Here's an examples to show how LaVague can execute natural lanaguge instructions on a browser to automate interactions with a website:
LaVague interacting with Hugging Face's website.
Want to test out LaVague without any local set-up? You can try our hosted HuggingFace Gradio!
To get started locally or in a Google Colab, see our quick-tour which will walk you through how to get set-up and launch LaVague with our CLI tool.
We would love your help in making La Vague a reality.
Please check out our contributing guide to see how you can get involved!
If you are interested by this project, want to ask questions, contribute, or have proposals, please come on our Discord to chat!
LaVague is an open-source project designed to automate menial tasks on behalf of its users. Many of these tasks are repetitive, time-consuming, and require little to no cognitive effort. By automating these tasks, LaVague aims to free up time for more meaningful endeavors, allowing users to focus on what truly matters to them.
By providing an engine turning natural language queries into Selenium code, LaVague is designed to make it easy for users or other AIs to automate easily express web workflows and execute them on a browser.
One of the key usages we see is to automate tasks that are personal to users and require them to be logged in, for instance automating the process of paying bills, filling out forms or pulling data from specific websites.
- Natural Language Processing: Understands instructions in natural language to perform browser interactions.
- Selenium Integration: Seamlessly integrates with Selenium for automating web browsers.
- Open-Source: Built on open-source projects such as transformers and llama-index, and compatible with open-source models, either locally or remote, to ensure the transparency of the agent and ensures that it is aligned with users' interests.
- Local models for privacy and control: Supports local models like
Gemma-7bso that users can fully control their AI assistant and have privacy guarantees. - Advanced AI techniques: Uses a local embedding (
bge-small-en-v1.5) first to perform RAG to extract the most relevant HTML pieces to feed the LLM answering the query. Then leverages Few-shot learning and Chain of Thought to elicit the most relevant Selenium code to perform the action without having to finetune the LLM for code generation.
This is an early project but could grow to democratize transparent and aligned AI models to undertake actions for the sake of users on the internet.
Keep up to date with our project backlog here.
This project executes LLM-generated code using exec. This is not considered a safe practice. We therefore recommend taking extra care when using LaVague (such as running LaVague in a sandboxed environment)!