A built version of SeeAct GPT-4V(ision) is a Generalist Web Agent, if Grounded
2.6K
The SeeAct tool enables running web agents on live websites through PlayWright, serving as an interface between an agent and a web browser. It efficiently tunnels inputs from the browser to the agent, and translates predicted actions of the agent into browser events for execution. This tool can be used for running web agent demos and evaluating their performance on live websites.
More details can be found here: https://osu-nlp-group.github.io/SeeAct/
Content type
Image
Digest
sha256:4b58ab2f3…
Size
3.5 GB
Last updated
over 2 years ago
docker pull integrail/seeact