Ship Reliable RAG: Evals That Grow with Your Retrieval Complexity

Name: Ship Reliable RAG: Evals That Grow with Your Retrieval Complexity
Uploaded: 2026-09-04T01:10:28.000Z
Duration: 30 min 28 s
Channel: Ravi Vats
Description: Ravi Vats presents a structured framework for building and evaluating Retrieval Augmented Generation (RAG) systems in Python, emphasizing scalable evaluation…

Ravi Vats

PyCon AU·Ravi Vats

30:28

Notebook

Type below to lock the video timestamp, or press S to capture a slide.

Ship Reliable RAG: Evals That Grow with Your Retrieval Complexity

Ravi Vats PyCon AU

30:28·2026·graduate·Conference Talk

Ravi Vats presents a structured framework for building and evaluating Retrieval Augmented Generation (RAG) systems in Python, emphasizing scalable evaluation strategies for increasing retrieval complexity.

(Ravi Vats) RAG applications come in many shapes. Some start as simple keyword searches over historical records. Others layer on semantic embeddings, hybrid retrieval (semantic + keyword/lexical searches), reranking, and increasingly sophisticated prompting. But regardless of where your system sits on that spectrum, the question is the same: how do you know it actually works?

AI & ML Systems & CS Language Models & NLP Natural Language Processing Retrieval Augmented Generation Machine Learning Engineering Evaluation Metrics

About the lecturer

Speaker directory →

Ravi Vats

Speaker at PyCon AU

Ravi Vats is a speaker at PyCon AU, focusing on practical applications of machine learning and reliable RAG systems.

1 lecture in archiveView profile

Discussion

Share a seminar note, question, or timestamped reference (e.g. 14:20)...Sign in

Related lectures

5