Learn how to make a modern Search experience with us in this 6-weekend instructor-led course+live practice for senior engineers.
This course is no longer available.
Explore other coursesBuilt products for
Course overview
🔥 Live Code Walkthroughs: Engage with code examples and implementations by coding along in real-time
🚀 Expert-led Sessions: Learn from industry veterans with over 2-decades of experience, providing practical knowhow and tricks
📚 Comprehensive Course Content: Gain a deep working knowledge of GenerativeAI technologies and their applications
🏃♀️ Intensive Week-long Case Study Sprint: Dive into practical projects like building your own LM, Customer Support Bot, and more
👨🏫 Guest Lectures: Exlusive lectures by the authors of Llama Index and Ragas
01
Senior Data Scientists, ML Engineers, CTOs, or Technical Leaders looking to improve an existing RAG system MVP
02
Aiming to scale your RAG system for better accuracy and faster response times
03
Ready to build nuanced, effective RAG systems across web, document and image retrieval
Tailoring and Optimizing Search Solutions 🎯
Advanced Techniques and AI Management 🚀
Building Expertise and Community 🌐
Live sessions
Learn directly from your instructors in a real-time, interactive format.
Lifetime access
Go back to course content and recordings whenever you need to.
Community of peers
Stay accountable and share insights with like-minded professionals.
Certificate of completion
Share your new skills with your employer or on LinkedIn.
Maven Guarantee
This course is backed by the Maven Guarantee. Students are eligible for a full refund up until the halfway point of the course.
RAG Evals: Ragas - Metrics, Synthetic Testset Generation
Clustering for Inspecting data
Defining Categories
Query Rewriting
Query Decomposition & Expansion
Testset Generation
LLM as a Judge with Ragas
Baseline RAG Evaluation Submission
Chunking
Parsing
Metadata Design and Schema
Selecting, Improving Embedding Model
Combining Embedding Types
Example Web App with Logging and Monitoring
Improving Latency
Gateways: Routing, Guardraisl and Caching
Vector Quantization
LLM Quantization
Re-rankers and Signal Combinations
Do I even need a VectorDB?
Differing Vector Indexing Types
Multi Modal RAG Basics
Late Interaction e.g. ColiPali
No module content yet
No module content yet
Dr. Pratik Desai
Ravi Theja
Nirant Kasliwal is a notable AI Engineer with over 7 years of expertise in areas like chatbots, language models, and vector databases. He founded FastEmbed, an embedding library praised for its speed and utilized by companies including NVIDIA.
Recognized by AI luminaries such as Dr. Andrew Ng, Nirant is one of India's leading GenAI scientists. He has significantly contributed to AI education through projects like "Awesome NLP," a resource for engineers learning NLP, and continues to enhance AI accessibility and knowledge sharing.
Jithin James (jjmachan) is the founder of Exploding Gradients and creator of ragas, an open-source tool for evaluating RAG pipelines. He builds tools to help devs building with LLMs, especially those building with RAG pipelines.
His work on ragas has significantly advanced the field of RAG evaluation, providing developers with crucial tools to enhance LLM-based applications. His contributions to open-source projects like BentoML have streamlined ML model deployment processes across the industry.
ragas is used by OpenAI for RAG evals.
Dhruv Anand is the Founder and CEO of AI Northstar Tech, an innovation startup leveraging LLMs, vector embeddings, and databases to enhance Search and Recommendation systems, and build custom RAG applications.
An alumnus of Computer Science departments at Carnegie Mellon and IIT Kanpur, he has worked on ML models for Search products at both Google and Facebook.
As a consultant, Dhruv delivers optimized AI solutions to enterprises, specializing in Search algorithms and LLM fine-tuning. His expertise lies in architecting scalable AI systems that bridge academic research with industry demands.
4-6 hours per week
Saturday & Sunday
9:00pm - 10:30pm PST
Hands-on sessions exploring each phase of the framework and guiding you through implementing enhancements in your RAG application.
Guest Lectures
Coming soon
We'll confirm the guest lecture schedule closer to the course date. We are onboarding e-commerce search and re-ranking veterans.
Capstone Project
2 hours per week
Project-specific, custom-built datasets spanning various industries -- ensuring you develop the targeted expertise required for your unique challenges. You can work on them async.
Active hands-on learning
This course is designed to help you achieve enterprise-readiness in RAG with deep-dives and code walkthroughs.
Interactive and project-based
You’ll get hands-on experience creating next-generation AI solutions, from fine-tuned prompts to multi-modal systems, alongside other AI enthusiasts and data scientists.
Learn with a cohort of peers
Join a community of like-minded people who want to learn and grow alongside you