About this episode

Radu Gheorghe discusses the limitations of vector similarity in search systems and the advantages of tensor-based retrieval in AI applications.

Vector search has risen to become a foundational tool in modern search and retrieval systems, including the RAG pipelines that power many AI applications. However, the demands on retrieval systems are growing more sophisticated, which is revealing the limits of relying on a single vector similarity score. Vespa is a popular open source search and data serving engine. Central to Vespa’s architecture is tensor-based retrieval, which is an approach that represents data as tensors rather than simple vectors. Tensor-based retrieval enables richer mathematical operations and more flexible ranking functions that can surmount the limitations of a single vector similarity score. Radu Gheorghe is a software engineer at Vespa with a background spanning nearly 12 years of consulting and training on Elasticsearch and Solr. In this episode, Radu joins Sean Falconer to discuss why vector similarity alone falls short in production, how tensor-based retrieval generalizes to support richer ranking functions, the trade-offs in chunking and multi-stage re-ranking architectures, and where AI search is headed next. Full Disclosure: This episode is sponsored by Vespa. Sean’s been an academic, startup…

People in this episode

Host: Sean Falconer

Guest: Radu Gheorghe

Topics covered

• vector search
• tensor-based retrieval
• AI applications
• ranking functions
• search systems
• RAG pipelines

Keywords

• vector similarity
• tensor-based retrieval
• search and retrieval
• AI search
• ranking functions
• Vespa
• RAG pipelines

Sponsors

Vespa

Mentioned in this episode

Organizations: Elasticsearch, Solr, Confluent

More episodes of Software Engineering Daily

• Web Native Game Development · June 4, 2026 · 52 min
• The Hardware Bottleneck AI Can’t Fix · June 2, 2026 · 51 min
• Autonomous Drone Delivery at Scale · May 28, 2026 · 50 min
• The European Startup Scene · May 26, 2026 · 47 min
• React Native at Scale · May 21, 2026 · 47 min
• Formal Methods as Agent Guardrails · May 19, 2026 · 50 min

Explore listener stats, chart rankings, contacts and more on the Software Engineering Daily podcast page.