Explore a series of lightning talks from the Haystack US 2024 Search Relevance Conference, covering a wide range of topics in search technology and artificial intelligence. Dive into discussions on information retrieval versus synthesis in RAG, LLM-powered unstructured analytics, and optimized scalar quantization for vector search in Lucene. Learn about best practices in Learning to Rank, strategies for searching over groups instead of multiple indices, and implementing semantic search in startup environments. Discover how to accelerate vector embeddings, explore the SearchArray concept, and get updates on open-source tools like Quepid and Lucille. Gain insights into MICES, Langflow, and the latest ML search capabilities in OpenSearch. Conclude with a demonstration on interacting with technical documentation using generative AI. Presented by OpenSource Connections, this collection of talks offers valuable knowledge for professionals and enthusiasts in the search and AI domains.
Overview
Syllabus
Haystack US 2024 - Lightning Talks
Taught by
OpenSource Connections
Related Courses
-
Vector Search RAG Tutorial – Combine Your Data with LLMs with Advanced Search
-
Learn Embeddings and Vector Databases
-
Haystack - Customizable LLM pipelines for GenAI Applications
-
Generative AI Architectures with LLM, Prompt, RAG, Vector DB
-
Retrieval Optimization: Tokenization to Vector Quantization
-
Multimodal RAG: AI Search & Recommender Systems with GPT-4
