I thing there is a question a lot of people using LaVague asks themselves: how can I speed up my webagent scrapping ? It is very very slow.
How can I speed up the webagent scrapper?
Where are the time bottlenecks? What does take time?
Is running the agent on a better machine will increase the speed or is it constrained by inference time on the LLM-provider-side?
We will release an optimized version soon, just need to wait a bit more! We focused on AI capability first but we are now good enough to focus on latency
hello community,
I thing there is a question a lot of people using LaVague asks themselves: how can I speed up my webagent scrapping ? It is very very slow.
How can I speed up the webagent scrapper? Where are the time bottlenecks? What does take time? Is running the agent on a better machine will increase the speed or is it constrained by inference time on the LLM-provider-side?
Thank you for your reply, Best, Paul