search

OSU-NLP-Group / SeeAct

[ICML'24] SeeAct is a system for generalist web agents that autonomously carry out tasks on any given website, with a focus on large multimodal models (LMMs) such as GPT-4V(ision).
https://osu-nlp-group.github.io/SeeAct/
Other
571 stars 69 forks source link

pip package #17

Closed yimothysu closed 3 months ago

yimothysu commented 4 months ago

It would be great if this repository could be packaged via pip and uploaded to PyPI. This would allow users to easily use it in other projects via pip install.

boyuanzheng010 commented 4 months ago

Thanks @yimothysu , for this suggestion. We are organizing the codebase and will wrap it into PyPi in the next update.

boyugou commented 3 months ago

We have released a first version, with many updates.

https://pypi.org/project/seeact/

pip install seeact

An example:

`import asyncio import argparse import toml from seeact.agent import SeeActAgent async def run_agent(): agent = SeeActAgent(default_task="terminate",openai_key="Your API KEY Here") await agent.start() while not agent.complete_flag: prediction_dict = await agent.predict() await agent.execute(prediction_dict) await agent.stop()

if name == "main": asyncio.run(run_agent()) `