I wanted to try ChromaDB and see how easy it is to use and how easily you can plug it into an agent or any other flow to build a RAG.

Much of the world’s data is locked in PDFs, JPEGs, and other documents. Traditional OCR extracts text but loses critical information: the layout of tables with merged cells, the relationship between charts and captions, the reading order of multi-column layouts, etc.

Extracting data from modern websites can be a challenge. Developers typically resort to a few standard tactics:

A couple of weeks ago, while assisting in a workshop at Google DevFest Silicon Valley in Sunnyvale, I discovered a powerful way to supercharge GitHub workflows: combining the Gemini CLI with the Jules extension. This setup works in two powerful ways—first, it transforms your command line into an AI-powered development assistant that can review code, analyze pull requests, automate issue triage, and even create pull requests from issues all without leaving your terminal. Second, it enables GitHub Actions workflows that automatically use Gemini to perform tasks directly in your repository, such as automated issue triage, security scans, and PR reviews, all running automatically without any manual intervention.

I’m a big NBA fan living in Spain, which means I wake up every morning eager to catch up on the previous night’s games. To make this daily ritual more efficient and enjoyable, I decided to build my own AI-powered NBA morning podcast.

“Everyone understands that knowing your customer is key to success. But in the AI era, understanding how your LLM behaves is just as important. And it’s the part most teams neglect.”