Mastering Hybrid Search: Blending Classic Ranking with Vector Search - Haystack EU 2023
Offered By: OpenSource Connections via YouTube
Course Description
Overview
Explore the cutting-edge world of hybrid search systems in this 37-minute conference talk from Haystack EU 2023. Dive into the integration of classic ranking algorithms like BM25 with modern vector search techniques to enhance search relevancy and overcome limitations of traditional methods. Learn how to leverage unstructured data, including images and text, for fuzzy searching and improved results. Discover best practices for pre/post metadata filtering and hybrid ranking strategies that combine BM25 scores with vector-based algorithms such as HNSW. Gain insights into the challenges of transitioning from research to production, achieving real-time scalability, and balancing performance with accuracy. Join Ohad Levi, co-founder and CEO of Hyperspace, as he shares his expertise in optimizing search systems and pushing the boundaries of real-time search capabilities.
Syllabus
Haystack EU 2023 - Ohad Levi: Mastering Hybrid Search: Blending Classic Ranking with Vector Search
Taught by
OpenSource Connections
Related Courses
SPLADE - The First Search Model to Beat BM25James Briggs via YouTube Supercharge eCommerce Search - OpenAI's CLIP, BM25, and Python
James Briggs via YouTube Vector-Based Methods for Similarity Search - TF-IDF, BM25, SBERT
James Briggs via YouTube RAG with Verified Citations - Advanced Inference Techniques
Trelis Research via YouTube Mastering Retrieval for LLMs - BM25, Fine-tuned Embeddings, and Re-Rankers
Trelis Research via YouTube