Documentation

The detailed API documentation for gpCAM can be found here:

fvGP and HGDL are support packages upstream of gpCAM. Knowing about these packages in detail is optional but beneficial for advanced use cases. 

• gpCAM Documentation

• fvGP Documentation

• HGDL Documentation

Bayesian Optimization, Gaussian process uncertainty quantification, and  Autonomous experimentation can be complicated endeavors employing user-defined acquisition functions, cost functions, training procedures, and optimization algorithms. Make sure to test your setup a few weeks before a high-stakes application, and please feel free to reach out if you encounter difficulties.

gpCAM ships with a set of Claude Code (compatible with other AI models) skills that guide an AI assistant through designing autonomous experiments — custom kernels, acquisition functions, noise models, and the full ask/tell/train loop. Experimentalists who want smart, autonomous data acquisition without deep knowledge of GP math or the gpCAM API can use these skills to design autonomous experiments.

The codes for the three packages can be found here:

• https://github.com/lbl-camera/gpCAM

• https://github.com/lbl-camera/fvGP

• https://github.com/lbl-camera/HGDL

Install all of them as part of the gpCAM package via: pip install gpcam

More installation information can be found here.