Building a price comparison platform requires solving multiple ML challenges at scale. This talk covers a year-long production project combining LLMs, graph algorithms, and computer vision.

We'll explore:

Orchestrating complex ML workflows with Vertex AI Pipelines Using Gemini to classify products, extract attributes, and generating titles/descriptions Connecting product variants across retailers with graph algorithms Deduplicating images using computer vision

You'll learn practical lessons from deploying these systems in production, including trade-offs and challenges encountered along the way

This talk explores Java code structure analysis using Graphs. It provides an introduction to Graphs and underscores their significance in both Graph Analysis and the field of Graph Data Science. The journey begins with exploring queries to analyze code dependencies and progresses to the application of graph algorithms for tasks such as community detection, centrality, and similarity. Additionally, the talk provides an introduction to node embeddings for machine learning. By the end of this presentation, software professionals will be well-equipped to extract valuable insights from Java code bases effectively.