Get it on Google Play

Vespa AI and Surpassing the Limits of Vector Search

Vespa AI and Surpassing the Limits of Vector Search

Author: Software Engineering Daily May 12, 2026 Duration: 38:35
Software Engineering Daily
Technology

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 founder, and Googler. He has published works covering a wide range of topics from AI to quantum computing. Currently, Sean is an AI Entrepreneur in Residence at Confluent where he works on AI strategy and thought leadership. You can connect with Sean on LinkedIn.

Please click here to see the transcript of this episode.

Sponsorship inquiries: sponsor@softwareengineeringdaily.com

The post Vespa AI and Surpassing the Limits of Vector Search appeared first on Software Engineering Daily.


Dive deep into the conversations shaping the future of artificial intelligence with the Machine Learning Archives-Software Engineering Daily. This curated collection pulls from the broader Software Engineering Daily library, focusing entirely on the intricate world of ML engineering. Each episode features a detailed, technical interview with engineers, researchers, and architects who are building the systems behind today's most advanced AI. You'll hear them break down complex topics like model deployment, data pipeline challenges, and the practical trade-offs involved in taking research from a notebook into production. The discussions are grounded in real-world implementation, moving beyond theoretical concepts to explore the tools, failures, and successes that define the field. For developers and technical leaders looking to understand the nuts and bolts of applied machine learning, this podcast offers a valuable archive of knowledge. It's a direct line to the practitioners who are solving hard problems every day, providing insights you can apply to your own work. Tune in to gain a clearer perspective on how machine learning is integrated into modern software, one detailed conversation at a time.
Author: Language: en-us Episodes: 50

Official website RSS
youtubelinkedinspotifyapple_music
Software Engineering Daily
Podcast Episodes
The Hardware Bottleneck AI Can’t Fix [not-audio_url] [/not-audio_url]

Duration: 52:47
Software engineering has developed powerful tools for observability, data management, and continuous testing, but hardware engineering has largely not kept pace. The feedback loops, tooling, and infrastructure that softw…
Autonomous Drone Delivery at Scale [not-audio_url] [/not-audio_url]

Duration: 50:30
Autonomous drone delivery has long been the stuff of science fiction, but ongoing advances have moved the space from experimental to operational. Zipline is one of the leading companies in this space, with drones that ch…
The European Startup Scene [not-audio_url] [/not-audio_url]

Duration: 48:57
Europe’s startup ecosystem is maturing rapidly, with companies like Revolut, Lovable, and Legora demonstrating that world-class technology businesses can be built and scaled on the continent. While the US remains the dom…
React Native at Scale [not-audio_url] [/not-audio_url]

Duration: 45:35
React Native is an open source framework developed by Meta that allows engineers to build mobile applications for both iOS and Android using a single JavaScript codebase. The framework bridges the gap between web develop…
Formal Methods as Agent Guardrails [not-audio_url] [/not-audio_url]

Duration: 48:32
Formal methods are a branch of mathematics and computer science focused on proving the correctness of systems, and they have long promised a more rigorous foundation for software. However, their complexity has kept them…
Open Source Sustainability [not-audio_url] [/not-audio_url]

Duration: 58:43
Open source software underpins nearly every modern application, including frameworks powering the most popular websites, to the libraries securing financial backend systems. However, while open source drives collaboratio…
SmartBear and Multi-Agent QA [not-audio_url] [/not-audio_url]

Duration: 55:15
AI coding tools have dramatically accelerated the pace of development, and the bottleneck in the software development lifecycle has shifted to code validation and testing. However, the conventional tools and workflows th…
The Ethics of Autonomous Weapons Systems [not-audio_url] [/not-audio_url]

Duration: 1:06:40
Artificial intelligence is transforming warfare faster than the legal and ethical frameworks designed to govern it. Militaries around the world are deploying AI-powered decision support systems to identify targets, asses…
Open-Weight AI Models [not-audio_url] [/not-audio_url]

Duration: 50:14
Open-weight models are AI systems whose trained parameters are publicly released, which allows developers to run, fine-tune, and deploy them independently rather than accessing them only through a hosted API. While close…

«12345»