mirror of
https://github.com/browser-use/browser-use.git
synced 2026-09-14 19:59:47 +08:00
reformedot
7e9bf5c0d7
- Updated the extract method to support a new raw mode, allowing users to retrieve structured content directly without LLM processing. - Modified the ExtractAction model to include a raw parameter for toggling between raw content and LLM-interpreted extraction. - Improved documentation for the extraction process, clarifying usage scenarios and parameters. - Added memory handling for raw mode to optimize content storage and retrieval.
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