Databricks
State-of-the-Art Retrieval Augmented Generation at Scale in Spark NLP
Efficient scaling of RAG systems using Spark NLP: pre-processing, embedding calculation, post-processing, and integration with LangChain and HayStack for production-grade LLM systems.
YouTube33 minutesSelf-pacedFree video
OpenSource Connections
Lightning Talks on Search Relevance and AI - Haystack US 2024
Explore cutting-edge search and AI topics through lightning talks from Haystack US 2024. Gain insights on information retrieval, LLMs, vector search, semantic search, and more from industry experts.
YouTube1 hour 3 minutesSelf-pacedFree video
Data Science Festival
Building RAG Applications from Scratch with NVIDIA NIM Microservices
Dive into building scalable RAG applications using NVIDIA NIM microservices, covering text embedding, reranking, and chatbot integration for high-performance AI deployment.
YouTube43 minutesSelf-pacedFree video