π Home
πββοΈ What is LaVague?
LaVague is an open-source Large Action Model framework for turning natural language into browser actions.
At LaVague's core, we have an Action Engine which uses advanced AI techniques (RAG, Few-shot learning, Chain of Thought) to βcompileβ natural language instructions into browser automation code, by leveraging Selenium or Playwright.
LaVague in Action
Here's an example of LaVague being used to execute natural language instructions on a browser to automate web interactions. This example uses the Gradio interface available with the lavague launch
CLI command:
π Getting Started
Running LaVague in your local env
You can get started with LaVague
in 2 steps:
- Install LaVague & dependencies
wget https://raw.githubusercontent.com/lavague-ai/LaVague/main/setup.sh &&
bash setup.sh
- Run your LaVague command!
lavague --instructions examples/instructions/huggingface.yaml --config examples/configurations/api/openai_api.py build
For a step-by-step guide or to run LaVague 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.
π Playwright integration
If you want to get started with LaVague build using Playwright as your underlying automation tool, see our Playwright integration guide
π Contributing
We would love your help and support on our quest to build a robust and reliable Large Action Model for web automation.
To avoid having multiple people working on the same things & being unable to merge your work, we have outlined the following contribution process:
1) π’ We outline tasks on our backlog
: we recommend you check out issues with the help-wanted
labels & good first issue
labels
2) πββοΈ If you are interested in working on one of these tasks, comment on the issue!
3) π€ We will discuss with you and assign you the task with a community assigned
label
4) π¬ We will then be available to discuss this task with you
5) β¬οΈ You should submit your work as a PR
6) β We will review & merge your code or request changes/give feedback
Please check out our contributing guide
for a more detailed guide.
If you want to ask questions, contribute, or have proposals, please come on our Discord
to chat!
πΊοΈ Roadmap
TO keep up to date with our project backlog here.
Disclaimer
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)!