Vector Podcast Dmitry Kan

Topics:
00:00 Intro - how do you like our new design?
00:52 Greets
01:55 Saurabh's background
03:04 Resume Matcher: 4.5K stars, 800 community members, 1.5K forks
04:11 How did you grow the project?
05:42 Target audience and how to use Resume Matcher
09:00 How did you attract so many contributors?
12:47 Architecture aspects
15:10 Cloud or not
16:12 Challenges in maintaining OS projects
17:56 Developer marketing with Swirl AI Connect
21:13 What you (listener) can help with
22:52 What drives you?

Show notes:
- Resume Matcher: https://github.com/srbhr/Resume-Matcher
website: https://resumematcher.fyi/

- Ultimate CV by Martin John Yate: https://www.amazon.com/Ultimate-CV-Cr...

- fastembed: https://github.com/qdrant/fastembed

- Swirl: https://github.com/swirlai/swirl-search

Topics:
00:00 Intro
00:22 Quick demo of SWIRL on the summary transcript of this episode
01:29 Sid’s background
08:50 Enterprise vs Federated search
17:48 How vector search covers for missing folksonomy in enterprise data
26:07 Relevancy from vector search standpoint
31:58 How ChatGPT improves programmer’s productivity
32:57 Demo!
45:23 Google PSE
53:10 Ideal user of SWIRL
57:22 Where SWIRL sits architecturally
1:01:46 How to evolve SWIRL with domain expertise
1:04:59 Reasons to go open source
1:10:54 How SWIRL and Sid interact with ChatGPT
1:23:22 The magical question of WHY
1:27:58 Sid’s announcements to the community
YouTube version: https://www.youtube.com/watch?v=vhQ5LM5pK_Y
Design by Saurabh Rai: https://twitter.com/_srbhr_ Check out his Resume Matcher project: https://www.resumematcher.fyi/

Topics:
00:00 Intro
02:20 Atita’s path into search engineering
09:00 When it’s time to contribute to open source
12:08 Taking management role vs software development
14:36 Knowing what you like (and coming up with a Solr course)
19:16 Read the source code (and cook)
23:32 Open Bistro Innovations Lab and moving to Germany
26:04 Affinity to Search world and working as a Search Relevance Consultant
28:39 Bringing vector search to Chorus and Querqy
34:09 What Atita learnt from Eric Pugh’s approach to improving Quepid
36:53 Making vector search with Solr & Elasticsearch accessible through tooling and documentation
41:09 Demystifying data embedding for clients (and for Java based search engines)
43:10 Shifting away from generic to domain-specific in search+vector saga
46:06 Hybrid search: where it will be useful to combine keyword with semantic search
50:53 Choosing between new vector DBs and “old” keyword engines
58:35 Women of Search
1:14:03 Important (and friendly) People of Open Source
1:22:38 Reinforcement learning applied to our careers
1:26:57 The magical question of WHY
1:29:26 Announcements
See show notes on YouTube: https://www.youtube.com/watch?v=BVM6TUSfn3E

Topics:
00:00 Intro
01:54 Things Connor learnt in the past year that changed his perception of Vector Search
02:42 Is search becoming conversational?
05:46 Connor asks Dmitry: How Large Language Models will change Search?
08:39 Vector Search Pyramid
09:53 Large models, data, Form vs Meaning and octopus underneath the ocean
13:25 Examples of getting help from ChatGPT and how it compares to web search today
18:32 Classical search engines with URLs for verification vs ChatGPT-style answers
20:15 Hybrid search: keywords + semantic retrieval
23:12 Connor asks Dmitry about his experience with sparse retrieval
28:08 SPLADE vectors
34:10 OOD-DiskANN: handling the out-of-distribution queries, and nuances of sparse vs dense indexing and search
39:54 Ways to debug a query case in dense retrieval (spoiler: it is a challenge!)
44:47 Intricacies of teaching ML models to understand your data and re-vectorization
49:23 Local IDF vs global IDF and how dense search can approach this issue
54:00 Realtime index
59:01 Natural language to SQL
1:04:47 Turning text into a causal DAG
1:10:41 Engineering and Research as two highly intelligent disciplines
1:18:34 Podcast search
1:25:24 Ref2Vec for recommender systems
1:29:48 Announcements
For Show Notes, please check out the YouTube episode below.
This episode on YouTube: https://www.youtube.com/watch?v=2Q-7taLZ374
Podcast design: Saurabh Rai: https://twitter.com/srvbhr

Toloka’s support for Academia: grants and educator partnerships
https://toloka.ai/collaboration-with-educators-form
https://toloka.ai/research-grants-form
These are pages leading to them:
https://toloka.ai/academy/education-partnerships
https://toloka.ai/grants
Topics:
00:00 Intro
01:25 Jenny’s path from graduating in ML to a Data Advocate role
07:50 What goes into the labeling process with Toloka
11:27 How to prepare data for labeling and design tasks
16:01 Jenny’s take on why Relevancy needs more data in addition to clicks in Search
18:23 Dmitry plays the Devil’s Advocate for a moment
22:41 Implicit signals vs user behavior and offline A/B testing
26:54 Dmitry goes back to advocating for good search practices
27:42 Flower search as a concrete example of labeling for relevancy
39:12 NDCG, ERR as ranking quality metrics
44:27 Cross-annotator agreement, perfect list for NDCG and Aggregations
47:17 On measuring and ensuring the quality of annotators with honeypots
54:48 Deep-dive into aggregations
59:55 Bias in data, SERP, labeling and A/B tests
1:16:10 Is unbiased data attainable?
1:23:20 Announcements
This episode on YouTube: https://youtu.be/Xsw9vPFqGf4
Podcast design: Saurabh Rai: https://twitter.com/srvbhr

00:00 Introduction
01:11 Yaniv’s background and intro to Searchium & GSI
04:12 Ways to consume the APU acceleration for vector search
05:39 Power consumption dimension in vector search
7:40 Place of the platform in terms of applications, use cases and developer experience
12:06 Advantages of APU Vector Search Plugins for Elasticsearch and OpenSearch compared to their own implementations
17:54 Everyone needs to save: the economic profile of the APU solution
20:51 Features and ANN algorithms in the solution
24:23 Consumers most interested in dedicated hardware for vector search vs SaaS
27:08 Vector Database or a relevance oriented application?
33:51 Where to go with vector search?
42:38 How Vector Search fits into Search
48:58 Role of the human in the AI loop
58:05 The missing bit in the AI/ML/Search space
1:06:37 Magical WHY question
1:09:54 Announcements
- Searchium vector search: https://searchium.ai/
- Dr. Avidan Akerib, founder behind the APU technology: https://www.linkedin.com/in/avidan-akerib-phd-bbb35b12/
- OpenSearch benchmark for performance tuning: https://betterprogramming.pub/tired-of-troubleshooting-idle-search-resources-use-opensearch-benchmark-for-performance-tuning-d4277c9f724
- APU KNN plugin for OpenSearch: https://towardsdatascience.com/bolster-opensearch-performance-with-5-simple-steps-ca7d21234f6b
- Multilingual and Multimodal Search with Hardware Acceleration: https://blog.muves.io/multilingual-and-multimodal-vector-search-with-hardware-acceleration-2091a825de78
- Muves talk at Berlin Buzzwords, where we have utilized GSI APU: https://blog.muves.io/muves-at-berlin-buzzwords-2022-3150eef01c4
- Not All Vector Databases are made equal: https://towardsdatascience.com/milvus-pinecone-vespa-weaviate-vald-gsi-what-unites-these-buzz-words-and-what-makes-each-9c65a3bd0696
Episode on YouTube: https://youtu.be/EerdWRPuqd4
Podcast design: Saurabh Rai: https://twitter.com/srvbhr