Yep. A lot more on our roadmap, but a lot already in place!
It's been cool seeing how different pieces add up together and how gov/enterprise teams push us. While there are some surprising implementation details, a lot has been following up on what they need with foundational implementations and reusing them. The result is a lot is obvious in retrospect and well-done pieces carry it far.
Ex: We added a secure python sandbox last quarter so analysts can drive richer data wrangling on query results. Except now we are launching a GPU version, both so the wrangling can be ML/AI (ex: auto feature engineering), users can wrangle bigger results (GPU dataframes), and we will move our own built-in agents to it as well (ex: GPU-accelerated dashboard panels). Most individual PRs here are surprisingly small, but opens a lot!
Those are pretty normal needs for us and our users. A big reason louie.ai exists is to make easier all the years of Graphistry helping enterprise & gov teams use python notebooks, streamlit/databricks/plotly python dashboards, and overall python GPU+graph data science. Think pandas, pytorch, huggingface, Nvidia RAPIDS, our own pygraphistry, etc.
While we can't those years of our lives back, we can make the next ones a lot better!
It's been cool seeing how different pieces add up together and how gov/enterprise teams push us. While there are some surprising implementation details, a lot has been following up on what they need with foundational implementations and reusing them. The result is a lot is obvious in retrospect and well-done pieces carry it far.
Ex: We added a secure python sandbox last quarter so analysts can drive richer data wrangling on query results. Except now we are launching a GPU version, both so the wrangling can be ML/AI (ex: auto feature engineering), users can wrangle bigger results (GPU dataframes), and we will move our own built-in agents to it as well (ex: GPU-accelerated dashboard panels). Most individual PRs here are surprisingly small, but opens a lot!