I was asked to give one of the Machine Learning talks at DevFest Singapore 2023 - a large event, at which I was happy to be speaking in the main Everest venue.
My talk was titled "PaLM API: No-code Prototyping with Flowise", and included several ambitious live demonstrations of using the Flowise UI (which I had contributed PaLM API 'nodes' to, as part of Google's earlier MakerSuite Sprint):
Now that the PaLM API makes it possible for anyone to access Google's bison-level models easily, the next step in automation is to integrate it into larger processes. Flowise is a GUI front-end for langchain, which enables the orchestration of API calls, so that larger systems (with, for instance, retrieval over documents) or smarter agents (which can act semi-autonomously) can be built. This talk will show how the Flowise no-code tool can be used to prototype these use cases.
Fortunately, the following live demos of Flowise worked flawlessly!
- First steps with PaLM API (simple question input);
- Converting a formatted question in to a REST API without programming; and
- Building a RAG system to answer questions about Singapore (from documents hosted on GitHub)
Many thanks to the Singapore GDG for inviting me!
And the slides for my talk are here :
If there are any questions about the presentation please ask below, or contact me using the details given on the slides themselves.