Published on

DSPy - Gemini and Gemma


Sam Witteveen and I started the Machine Learning Singapore Group (or MLSG for short) on MeetUp in February 2017 (it was previously named "TensorFlow and Deep Learning Singapore"), and held our Official fiftieth MeetUp on 14-March-2024. This MeetUp marked the fiftieth MLSG event at which we've both spoken, and the point at which the MeetUp surpassed 6000 members...

The overall event was themed "Orchestration : LLMs and Agents".

My talk was titled "DSPy using Gemini and Gemma", and looked at the following topics:

  • DSPy : Basics
  • DSPy use-cases :
    • Hello-world with Gemini
      • Adding Gemma+oLLaMa
    • Choosing Examples
    • Optimisation
      • including PromptBreeder as being a key motivation for the entire talk
    • Structured Output; Data Generation & Fine-tuning

Sam talked about frameworks that can be used for orchestrating Agents (such as CrewAI, LangGraph and AutoGen), and also gave some tip and tricks for building Agent-based systems.

We also were pleased to have Praveen Govindaraj giving a talk titled "LLM Agents - B2C Use-cases & Evaluation" which included:

  • Use-cases for LLM Agents in B2C businesses
    • improving customer experience
    • optimizing network operations in Telecom

Many thanks to the Google team, who not only allowed us to use Google's Developer Space, and put out the extra chairs required for our larger-than-expected attendence, but were also kind enough to provide Pizza for the attendees!

The slides for my talk, which contain links to all of the reference materials and sources, are here :

Presentation Screenshot

If there are any questions about the presentation please ask below, or contact me using the details given on the slides themselves.

Presentation Content Example