Faster and More Powerful Full-Text Search with Milvus 3.0
About the Webinar
Milvus has long been known for vector search and has supported full-text search since Milvus 2.5, allowing teams to combine lexical and semantic retrieval in one engine. With Milvus 3.0, full-text search takes another major leap, with compressed BM25 indexes roughly 3× smaller than those in Milvus 2.6 at comparable recall, reducing memory and bandwidth pressure. It also introduces SINDI, a new sparse-retrieval algorithm that delivered roughly 5× to 10× the QPS of MaxScore across four learned-sparse benchmarks and extends the optimized retrieval path to native BM25.Milvus 3.0 also brings sorting, aggregation, and faceting into the engine.
With stronger full-text retrieval added to Milvus’s established vector-search foundation, teams can reconsider whether AI retrieval still requires a separate full-text system, along with the infrastructure, pipelines, and result-fusion logic that come with it. Join Simon Hearne, Solutions Architect at Zilliz, for a customer-backed comparison of Elasticsearch and Milvus, including live side-by-side queries.
What You’ll Learn
- Milvus 3.0 Full-Text Search — Explore BM25, sparse retrieval, index efficiency, server-side sorting, aggregation, and faceted search, with a brief look at planned fuzzy matching, multi-phase reranking, and JSON-field aggregations.
- Elasticsearch vs. Milvus — Compare search capabilities, performance, and operational tradeoffs across the two systems.
- Live Query Demo — Follow the same queries in Elasticsearch and Milvus, with results and latency visible on screen.
- Hybrid Search and Ranking — See how full-text and vector results can be combined through ranking and fusion methods such as RRF.
- Production Customer Evidence — Learn how real teams improve retrieval quality, support growing workloads, and simplify search operations.
- Live AMA — Bring your search patterns and architecture questions to a 20-minute discussion with Simon.
Join the Webinar
Loading...
Meet the Speaker
Join the session for live Q&A with the speaker
Simon Hearne
Solutions Architect
Simon Hearne is a Solutions Architect at Zilliz. He works closely with EMEA-based enterprise customers across verticals including IdV / facial recognition, legal case review, and social matching, enabling the design and implementation of GenAI, semantic search, and retrieval use cases using the Zilliz Cloud Vector Database. He brings experience from Elasticsearch and Akamai, and holds an MEng in Artificial Intelligence and an MSc in Data Science. Simon combines deep technical expertise in vector search with a strong focus on developer enablement, helping teams move from proof of concept to production with Milvus on Zilliz Cloud.