Explore a comprehensive podcast featuring ML Consultant Nirant Kasliwal, specializing in RAG with a focus on Language and Search. Gain valuable insights into the evolution of AI, challenges in defining modern AI, and the potential improvements in language model planning capabilities. Discover the impact of large language models on search and the importance of vector databases. Delve into the differences between typical RAG solutions and production-ready implementations, and understand the challenges of search evaluation. Learn about designing retrieval and ranking systems, optimizing search systems, and the tech stack for building them. Benefit from Kasliwal's expertise on providing value as a consultant, staying updated in the field, and receive advice for fresh graduates entering the AI industry.
Overview
Syllabus
Trailer
Introduction and Background
The Evolution of AI and the Challenges of Defining AI Today
The Potential for Improvement in Planning Capabilities of Language Models
The Impact of Large Language Models on Search and Importance of Vector DB
Differences Between Typical RAG Solutions and Production-Ready Implementations
Challenges of Search Evaluation and the Need for Better Evaluations Methods
Designing a Retrieval and Ranking System
Optimizing a Search System
Understanding Retrieval and Ranking
Tech Stack for Building a Search System
Providing Value as a Consultant
Staying Updated in the Field
Advice for Fresh Graduates
Taught by
1littlecoder
Related Courses
-
Knowledge Graphs for RAG
-
Generative AI Architecture and Application Development
-
Introduction to Retrieval Augmented Generation (RAG) and Implementation with Databricks
-
Retrieval Augmented Generation Explained for Beginners - RAG in LLMs
-
Getting Started with Retrieval Augmented Generation (RAG) in Java and Spring AI
-
Retrieval Augmented Generation - Boosting LLM Performance with External Knowledge
