2024-11-04 14:29:54 +01:00
2024-11-04 10:24:09 +01:00
2024-11-04 14:29:54 +01:00
2024-11-04 11:59:36 +01:00
2024-11-02 18:43:35 +01:00
2024-10-31 17:00:29 +01:00
2024-11-01 17:07:05 +01:00
2024-11-04 09:40:09 +01:00
2024-10-31 17:00:29 +01:00
2024-11-01 21:39:09 +01:00
2024-11-01 21:39:09 +01:00
2024-11-03 22:24:28 +01:00
2024-11-03 22:24:28 +01:00

Website Use

This repository contains an agent that can plan and execute actions on a website with or without a vision model.

Installation

pip install website-use

Supported models

  • GPT-4o
  • GPT-4o Mini
  • Claude 3.5 Sonnet

Codebase Structure

The code structure inspired by https://github.com/Netflix/dispatch.

Very good structure on how to make a scalable codebase is also in this repo.

Just a brief document about how we should structure our backend codebase.

Code Structure

src/
/<service name>/
models.py
services.py
prompts.py
views.py
utils.py
routers.py

    	/_<subservice name>/

Service.py

Always a single file, except if it becomes too long - more than ~500 lines, split it into _subservices

Views.py

Always split the views into two parts

# All
...

# Requests
...

# Responses
...

If too long → split into multiple files

Prompts.py

Single file; if too long → split into multiple files (one prompt per file or so)

Routers.py

Never split into more than one file

Requirements

uv pip install -r requirements.txt
uv pipreqs --ignore .venv --force
Description
Mirrored from GitHub
Readme MIT 125 MiB
Languages
Python 98%
Shell 1.4%
Dockerfile 0.4%
HTML 0.2%