Vector Podcast

Dmitry Kan
undefined
Nov 12, 2026 • 48min

Vishakha Gupta - ApertureData, Hybrid Search Across Knowledge Graph, Vector And Unstructured Data

Vishakha Gupta is the co-founder and CEO of ApertureData (https://www.aperturedata.io). In this episode we talk about hybrid search that combines a knowledge graph, vector search and storage for text, documents, images, video and audio, all in one query, forming the foundation for Agentic memory & cognition.Episode on YouTube: https://www.youtube.com/watch?v=U6Wq_WXe0ooTimecodes:00:15 Introducing Vishakha Gupta, CEO of ApertureData03:13 Beyond vector search: The multimodal vision05:54 Making the leap from researcher to founder08:30 Why build a graph database?15:11 Unifying metadata, embeddings, and media16:24 Why ApertureDB chose JSON queries18:38 SQL, MCP, and document search20:31 Learning to think like your users26:04 Multimodal data, agent memory, and cognition28:45 Product positioning and proving ROI30:35 Personalization with graph and vector search33:28 Finding video clips: Brad Pitt eating a sandwich35:52 E-commerce search and expanding customer use cases38:29 The data and memory layer for AI39:26 Inside ApertureDB: Architecture and deployment40:53 Aperture Nexus and the agent memory stack41:50 What’s next for ApertureData?43:03 AI’s unsolved data problem and bigger ambitions45:14 Try Aperture Nexus and join the community
undefined
Aug 3, 2026 • 29min

Berlin Buzzwords 2026 - Charlie Hull on role of Search in AI era

This episode was recorded LIVE during Berlin Buzzwords 2026Charlie's site and blog: https://thesearchjuggler.com/LinkedIn: https://www.linkedin.com/in/charliehullsearch/Search Relevance Slack (7000 search professionals): https://join.slack.com/t/relevancy/shared_invite/zt-42nhd2z7n-c8QAsDCYU8hFi8c2pRrXKgCharlie's panel at bbuzz, featuring yours truly among a group of distinguished search and ML people: https://www.youtube.com/watch?v=StaPk0k-52YTime codes00:00 Intro00:42 Charlie's take on this year's Berlin Buzzwords01:55 Based on the panel: Charlie's first encounter of AI04:55 Is preserving search still a question?5:48 Charlie's "old" search technique to improve quality of search7:58 Explainability gap9:03 Did LLMs change Charlie's life12:07 Query Understanding is still a complex topic13:14 Vector search or not17:28 Meetups and places to learn with Charlie19:25 Charlie's message to the search makers23:00 What is fundamentally missing in our space26:03 Where to follow Charlie's workShow notes:- Upcoming Vespa conference: http://www.vespaai.live/- Where find Charlie? On meetups: http://www.searchmeetups.com/- http://www.thesearchjuggler.com/- https://searchmeetups.com/- A neat trick for protecting numbers when using fuzzy search: https://www.youtube.com/watch?v=s34afYwYqyM
undefined
Aug 3, 2026 • 25min

Berlin Buzzwords 2026 - Julien Nioche on Greenops and new open source project SPRUCE

This is a LIVE discussion with Julien Nioche, the creator of SPRUCE, open source greenops framework. We recorded LIVE at Berlin Buzzwords 2026.Cameraman is Zoom's AI and it goes a little crazy at times zooming on Julien and zooming back out. As usual, audio version will be available. Go to https://www.vectorpodcast.com/He gave a talk about SPRUCE at the conference: https://2026.berlinbuzzwords.de/session/spruce-it-up-open-source-greenops-at-scale/Timcodes:00:00 Intro00:16 Julien's background01:36 What is SPRUCE2:51 Greenops vs FinOps6:09 Reasons cloud providers won't go deeper on greenops7:09 Ways to deploy SPRUCE15:06 Cultural shift needed for Greenops17:39 How to measure impact of AI agents and LLMsShownotes:- SPRUCE and green ops: https://opensourcegreenops.cloud/latest/- SPRUCE on GitHub: https://github.com/digitalpebble/spruce- Julien's company: https://digitalpebble.com/- Apache StormCrawler: https://stormcrawler.apache.org/ and GitHub: https://github.com/apache/stormcrawler- SPRUCE is based on Apache Spark: https://spark.apache.org/- "AI is here - time to throw away our search engines?" panel hosted by Charlie Hull at Berlin Buzzwords 2026: https://www.youtube.com/watch?v=StaPk0k-52Y- Estimate and track the environmental footprint of GenAI models at inference. Ecologits: https://ecologits.ai/latest/- Evaluate the environmental impact of digital technologies across organizations. Boavizta: https://boavizta.org/en
undefined
Jun 21, 2026 • 39min

Berlin Buzzwords 2026 - Trey Grainger & Doug Turnbull, Role of Search in modern AI and new course

This episode was recorded LIVE at the Berlin Buzzwords 2026YouTube version: https://youtu.be/acOGVynTVpMThe cameraman is pure Zoom's AI ;)The Course: "AI-Powered Search: Modern Retrieval for Humans & Agents"aipoweredsearch.com/live-course?promoCode=vector-podcastDiscount Code for course (20% off): "vector-podcast"AI-Powered Search (Book, Content, Community): https://aipoweredsearch.com/Timecodes00:00 Intro00:30 Doug's and Trey's impression of the conference01:16 How modern AI changed search (if any)05:48 How to bring AI techniques into existing search engines on a budget10:44 What the AI-Powered Search course includes18:02 Staying hands-on18:47 Guest's favourite topic that keeps them up at night27:40 Message to the builders of search tech32:55 Search continues to be challenging and excitingShownotes:- Upcoming course in detail (grab promo code above to save 20%): https://aipoweredsearch.com/articles/the-frontier-of-ai-search-ai-powered-search-modern-retrieval-for-humans-agents/- Doug's blog on search, agents, RAG, LLM as a judge and more: https://softwaredoug.com/- AI-Powered Search: https://aipoweredsearch.com/- Berlin Buzzwords:- MICES: https://mices.co/- Future of Search conference: https://berlinsearchweek.com/future-of-search/- Women of Search: https://www.women-of-search.org/- "AI is here - time to throw away our search engines?" panel hosted by Charlie Hull at Berlin Buzzwords 2026: https://www.youtube.com/watch?v=StaPk0k-52Y- Dmitry's prototype of Wormhole vectors idea with OpenSearch: https://aiven.io/blog/beyond-hybrid-search-traversing-vector-spaces-with-wormhole-vectors- Dmitry's blog on Medium: https://dmitry-kan.medium.com/- Dmitry's Tech Stories on Substack: https://substack.com/@dmitrykan- Follow me on LinkedIn for Search updates: https://www.linkedin.com/in/dmitrykan/
undefined
Jun 15, 2026 • 57min

Beyond Hyperspace - Ohad Levi on Hardware Accelerated Search and Agentic Memory

In this episode we sat down with Ohad Levi, co-founder and CEO of Hyperspace, to discuss the harware-accelerated search product he has built to address the search latency problem.Ohad also shares his thoughts on Agentic memory and what keeps him at night these days.Podcast design by https://www.linkedin.com/in/srbhr/Timecodes:00:00 Intro01:35 Ohad's background03:30 How idea was born: what was missing in the search landscape06:52 Top 3 issues with existing search solutions10:52 The importance of search latency13:41 Ohad's solution for latency19:22 Was Hyperspace up for the challenge?22:12 New approaches to handling massive scale26:12 Does latency matter for new agentic AI?32:12 Agentic AI vs SaaS35:03 Ohad's learnings from Hyperspace38:37 Friction points for the hardware-accelerated search 42:40 Product-led growth way47:43 What keeps Ohad excited about the AI / search field51:43 Ohad's message to the Search communityShownotes:Ohad Levi on LinkedIn: https://www.linkedin.com/in/ohad-levi/Hyperspace: https://www.hyper-space.io/Dmitry's blog on Medium: https://dmitry-kan.medium.com/Dmitry on LinkedIn: https://www.linkedin.com/in/dmitrykan/
undefined
Apr 10, 2026 • 1h 18min

AI Webinar - Building an AI-Ready Data Backbone

Webinar I gave with AI Camp and Aiven on AI-ready data backbone, and specifically how OpenSearch unlocks AI-powered search and log analytics: https://www.aicamp.ai/event/eventdetails/W2026032610Blog post: https://dmitry-kan.medium.com/webinar-building-an-ai-ready-data-backbone-with-aiven-google-cloud-4629f97f69bdLLM/RAG/AI Agents course: https://dmitry-kan.medium.com/course-large-language-models-and-generative-ai-for-nlp-2025-98e31780de30Free tier OpenSearch: https://aiven.io/free-opensearchTime codes:1:01 Dima's intro + Vector Podcast4:56 About Aiven7:06 Why best? - Question from the audience10:22 Free Tier OpenSearch!11:57 Aiven's unifed platform12:58 OpenSearch: What and Why17:00 Why OpenSearch is AI-Ready?18:26 What Aiven's OpenSearch gives you20:44 Lexical vs semantic search22:51 Technical use cases of OpenSearch 24:17 Reference Architecture with Kafka as event processor, and OpenSearch as storage and search layer25:37 Aiven's case studies for OpenSearch26:27 When to choose OpenSearch?28:21 Demo of OpenSearch query UI32:12 Is there any advantage in using Qdrant over OpenSearch? - Question from the audience34:30 What is the vector lenght (in this demo)? - Question from the audience36:27 What are the main advantages of Aiven's OpenSearch compared to Elasticsearch? - Question from the audience32:11 Demo of Search Relevancy Workbench: visual way of searchingShow notes:- User Behaviour Insights: https://www.ubisearch.dev/- Webinar's demo code part 1: Episode download / transcribe / index: https://github.com/dimakan-dev/conduit-transcripts/blob/main/DATA_PROCESSING_GUIDE.md- Webinar's demo code part 2: Main UI and quality dashboards: https://github.com/dimakan-dev/preparing-data-for-opensearch-and-rag/blob/main/workshop/STREAMLIT_README.md
undefined
15 snips
Nov 7, 2025 • 1h 19min

Trey Grainger - Wormhole Vectors

Trey Grainger, lead author of "AI Powered Search" and founder of Search Kernel, dives into the cutting-edge concept of Wormhole Vectors. He explains how these vectors interconnect various types of data spaces, enhancing hybrid search capabilities. Trey simplifies complex ideas, detailing behavioral embeddings derived from user interactions and the roles of semantic knowledge graphs. He shares practical applications and innovative methods to combine dense and sparse vectors, all while emphasizing the transformative potential of wormholes in search technology.
undefined
10 snips
Sep 19, 2025 • 1h 15min

Economical way of serving vector search workloads with Simon Eskildsen, CEO Turbopuffer

Simon Eskildsen, CEO and co-founder of Turbopuffer, has a rich background as an infrastructure engineer at Shopify. In this discussion, he reveals how Turbopuffer offers cost-effective solutions for vector search workloads, highlighting their innovative use of S3-native storage. Simon dives into the importance of latency optimization and the architectural advantages that result from their unique design. He also shares insights on the challenges of multi-tenancy, the significance of recall monitoring, and how LLM tools impact coding practices.
undefined
Mar 21, 2025 • 1h 3min

Adding ML layer to Search: Hybrid Search Optimizer with Daniel Wrigley and Eric Pugh

Vector Podcast website: https://vectorpodcast.comHaystack US 2025: https://haystackconf.com/2025/Federated search, Keyword & Neural Search, ML Optimisation, Pros and Cons of Hybrid searchIt is fascinating and funny how things develop, but also turn around. In 2022-23 everyone was buzzing about hybrid search. In 2024 the conversation shifted to RAG, RAG, RAG. And now we are in 2025 and back to hybrid search - on a different level: finally there are strides and contributions towards making hybrid search parameters learnt with ML. How cool is that?Design: Saurabh Rai, https://www.linkedin.com/in/srbhr/The design of this episode is inspired by a scene in Blade Runner 2049. There's a clear path leading towards where people want to go to, yet they're searching for something.00:00 Intro00:54 Eric's intro and Daniel's background02:50 Importance of Hybrid search: Daniel's take07:26 Eric's take10:57 Dmitry's take11:41 Eric's predictions13:47 Doug's blog on RRF is not enough16:18 How to not fall short of the blind picking in RRF: score normalization, combinations and weights25:03 The role of query understanding: feature groups35:11 Lesson 1 from Daniel: Simple models might be all you need36:30 Lesson 2: query features might be all you need38:30 Reasoning capabilities in search40:02 Question from Eric: how is this different from Learning To Rank?42:46 Carrying the past in Learning To Rank / any rank44:21 Demo!51:52 How to consume this in OpenSearch55:15 What's next58:44 Haystack US 2025YouTube: https://www.youtube.com/watch?v=quY769om1EY
undefined
Mar 2, 2025 • 20min

Vector Databases: The Rise, Fall and Future - by NotebookLM

https://www.vectorpodcast.com/I had fun interacting with NotebookLM - mostly for self-educational purposes. I think this tool can help by bringing an additional perspective over a textual content. It ties to what RAG (Retrieval Augmented Generation) can do to content generation in another modality. In this case, text is used to augment the generation of a podcast episode.This episode is based on my blog post: https://dmitry-kan.medium.com/the-rise-fall-and-future-of-vector-databases-how-to-pick-the-one-that-lasts-6b9fbb43bbbeTime codes:00:00 Intro to the topic1:11 Dmitry's knowledge in the space1:54 Unpacking the Rise & Fall idea3:14 How attention got back to Vector DBs for a bit4:18 Getting practical: Dmitry's guide for choosing the right Vector Database4:39 FAISS5:34 What if you need fine-grained keyword search? Look at Apache Lucene-based engines6:41 Exception to the rule: Late-interaction models8:30 Latency and QPS: GSI APU, Vespa, Hyperspace9:28 Strategic approach9:55 Cloud solutions: CosmosDB, Vertex AI, Pinecone, Weaviate Cloud10:14 Community voice: pgvector10:48 Picture of the fascinating future of the field12:23 Question to the audience12:44 Taking a step back: key points13:45 Don't get caught up in trendy shiny new techYouTube: https://www.youtube.com/watch?v=403rxbWZK9Y

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app