This series gives you an inside look at how we're using generative AI in customer support. Join us as we share our journey in real-time, focusing in this section on tuning RAG search for relevance.

A search problem

Our first approach

Data

Query

Generation

Feedback

Challenges

#1: CVEs (Common Vulnerabilities and Exposures)

#2: Product Versions

A. Inaccurate semantic matching

B. Multiple versions, same articles

C. Wrong versions being returned

Let's replay the question!

Measuring success

Improvements Observed

Before and After – `P@K`

What's next? 🔎

Conclusion

Elastic ELSER: Tuning RAG search for relevance

GenAI for Customer Support — Part 4: Tuning RAG Search for Relevance

Author

Antonio Schönmann

Articles

GenAI for Customer Support — Part 4: Tuning RAG Search for Relevance