Metrics Driven Development (Practical AI #284)

Changelog Master Feed

How do you systematically measure, optimize, and improve the performance of LLM applications (like those powered by RAG or tool use)? Ragas is an open source effort that has been trying to answer this question comprehensively, and they are promoting a “Metrics Driven Development” approach. Shahul from Ragas joins us to discuss Ragas in this episode, and we dig into specific metrics, the difference between benchmarking models and evaluating LLM apps, generating synthetic test data and more.

Join the discussion

Changelog++ members save 5 minutes on this episode because they made the ads disappear. Join today!

Sponsors:

• Assembly AI – Turn voice data into summaries with AssemblyAI’s leading Speech AI models. Built by AI experts, their Speech AI models include accurate speech-to-text for voice data (such as calls, virtual meetings, and podcasts), speaker detection, sentiment analysis, chapter detection, PII redaction, and more.

Featuring:

• Shahul Es – Twitter, GitHub, LinkedIn
• Daniel Whitenack – Twitter, GitHub, Website

Show Notes:

• Ragas

Something missing or broken? PRs welcome!

Chapter

1. Welcome to Practical AI (00:00:00)

2. What is Ragas (00:00:43)

3. General LLM evaluation (00:05:19)

4. Current unit testing workflow (00:10:10)

5. Metrics driven development (00:14:37)

6. Sponsor: Assembly AI (00:17:20)

https://www.assemblyai.com

7. Most used metrics (00:20:59)

8. Data burdens (00:26:27)

9. Exciting things coming (00:35:50)

10. Thanks for joining us! (00:40:49)

11. Outro (00:41:25)