> Markdown version of [/events/world-congress-2026-europe/sessions/976-the-r-in-rag-why](https://www.wearedevelopers.com/events/world-congress-2026-europe/sessions/976-the-r-in-rag-why). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# The R in RAG: Why retrieval is often the weakest link (and how to fix it)


- **Date:** Thursday, Jul 9, 2026
- **Time:** 10:10–10:40 (30 min)
- **Room:** Stage 1
- **Event:** World Congress 2026 Europe

## Recording

[Watch recording](https://www.wearedevelopers.com/videos/100005-the-r-in-rag-why-retrieval-is-often-the-weakest-link-and-how-to-fix-it)

## Description

RAG is one of the most popular ways to build LLM-powered applications - combining document retrieval with text generation. In demos and carefully prepared tests, these systems work great. In production, they often disappoint. Why? Because your documents are full of domain-specific terminology, internal jargon, and acronyms that off-the-shelf embedding models simply don't understand. If retrieval returns the wrong documents, even the best LLM can't save you.
In this session, I'll show how to fine-tune an embedding model for your specific domain. We'll walk through preparing training data, running the training process, and evaluating results. You don't need thousands of examples or expensive infrastructure - in the case I'll present, 50+ training samples were enough to dramatically improve retrieval quality.
You'll leave with a practical understanding of when and how to fine-tune embedding models, and what pitfalls to watch out for along the way.

## Speaker

### [Tomek Porożyński](https://www.wearedevelopers.com/@tomek-porozynski)

Staff ML Engineer at deepsense.ai


## Related talks at this congress

- [From Vector Search to Better Understanding: How Hybrid RAG Improves Answers, Not Just Matches](https://www.wearedevelopers.com/events/world-congress-2026-europe/sessions/968-from-vector-search) — David vonThenen
- [Scaling GraphRAG: Efficient Knowledge Retrieval for AI](https://www.wearedevelopers.com/events/world-congress-2026-europe/sessions/1005-scaling-graphrag) — Gal Shubeli
- [OLAP for AI Applications and why you should care](https://www.wearedevelopers.com/events/world-congress-2026-europe/sessions/1245-olap-for-ai) — Andrey Abramov
- [Outclassing Frontier LLMs at Extracting Information](https://www.wearedevelopers.com/events/world-congress-2026-europe/sessions/1216-outclassing-frontier) — Etienne Bernard