Vector Podcast Dmitry Kan

00:00 Intro
01:54 Reflection on the past year in AI
08:08 Reader LLM (and RAG)
12:36 Does it need fine-tuning to a domain?
14:20 How LLMs can lie
17:32 What if data isn't perfect
21:21 SWIRL's secret sauce with Reader LLM
23:55 Feedback loop
26:14 Some surprising client perspective
31:17 How Gen AI can change communication interfaces
34:11 Call-out to the Community

00:00 Intro
00:42 Louis's background
05:39 From Facebook to Rockset
07:41 Embeddings prior to deep learning / LLM era
12:35 What's Rockset as a product
15:27 Use cases
18:04 RocksDB as part of Rockset
20:33 AI capabilities: ANN index, hybrid search
25:11 Types of hybrid search
28:05 Can one learn the alpha?
30:03 Louis's prediction of the future of vector search
33:55 RAG and other AI capabilities
41:46 Call out to the Vector Search community
46:16 Vector Databases vs Databases
49:16 Question of WHY

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