Hacker News: dmitrykan

New comment by dmitrykan in "Ask HN: What Are You Working On? (December 2025)"

dmitrykan — Sun, 14 Dec 2025 21:29:01 +0000

On a Research Assistant: https://muves.io/

It helps to comprehend research papers (and not only papers - any document on any language) faster.

The tool is free to use, because we have credits from GCP. I guess at some point we'll need to introduce some level of subscription fee to keep it alive and useful, as it uses LLMs and vector search quite a bit.

Feedback is welcome!

New comment by dmitrykan in "[dead]"

dmitrykan — Sat, 08 Feb 2025 07:13:24 +0000

Leo Boytsov, my guest on the Vector Podcast, made an honest and an eye-opening claim about vector search being intellectually rewarding, but professionally undervalued. What picked my attention was how he gives credit to people who actually deserve it, and how he speaks modestly about his own achievements. When professionally as a researcher, he accumulated over 1800 citations by now and helped to create the famous HNSW vector search algorithm.

New comment by dmitrykan in "The Rise, Fall, and Future of Vector Databases: How to Pick the One That Lasts"

dmitrykan — Thu, 16 Jan 2025 21:28:41 +0000

My take on whether we've lost the category of vector databases.

The Rise, Fall, and Future of Vector Databases: How to Pick the One That Lasts

dmitrykan — Thu, 16 Jan 2025 21:28:41 +0000

Article URL: https://dmitry-kan.medium.com/the-rise-fall-and-future-of-vector-databases-how-to-pick-the-one-that-lasts-6b9fbb43bbbe

Comments URL: https://news.ycombinator.com/item?id=42731126

Points: 1

# Comments: 1

New comment by dmitrykan in "OTranscribe: A free and open tool for transcribing audio interviews"

dmitrykan — Fri, 09 Aug 2024 11:56:43 +0000

I'm working on the tool, that includes AI. My original target is to test it on my https://www.youtube.com/c/VectorPodcast by offering something that Lex Fridman does for his episodes.

Current features: 1. Download from YT 2. Transcribe using Vosk (output has time codes included) 3. Speaker diarization using pyannote - this isn't perfect and needs a bit more ironing out.

What needs to be done: 4. Store the transcription in a search engine (can include vectors) 5. Implement a webapp

If anyone here is interested to join forces, let me know.

New comment by dmitrykan in "Ask HN: Could you share your personal blog here?"

dmitrykan — Wed, 05 Jul 2023 07:12:56 +0000

https://dmitry-kan.medium.com/

I write about vector search, ANN algorithms, neural search frameworks, search engines and algorithms in general and publish episodes of the Vector Podcast.

New comment by dmitrykan in "What are embeddings?"

dmitrykan — Mon, 26 Jun 2023 21:08:33 +0000

Nice post, thanks for sharing! Learnt about new dbs / solutions for vector search from it.

Vicki mentions this survey I wrote some time ago: https://towardsdatascience.com/milvus-pinecone-vespa-weaviat...

Hoping it'll be useful as well!

New comment by dmitrykan in "Neural Search Frameworks: A Head-to-Head Comparison"

dmitrykan — Sat, 24 Dec 2022 09:44:53 +0000

thank you, Doug! It is mutual. Had a fantastic discussion with you on the podcast: https://www.youtube.com/watch?v=Kpua1Euc-B8

New comment by dmitrykan in "Vector Podcast – Journey of Vespa from Sparse into Neural Search"

dmitrykan — Tue, 12 Apr 2022 16:07:37 +0000

It was great to discuss with Jo Kristian on these topics and more:

- History of Vespa - Tensor data structure and its use cases - Multi-stage ranking pipeline - Game-changing vector search in Vespa - Approximate vs exact nearest neighbor search tradeoffs - Misconceptions in neural search - Multimodal search is where vector search shines - Power of building fully-fledged demos - How to combine vector search with sparse search: Reciprocal Rank Fusion - The question of WHY (my favourite)

I wonder what topics are interesting to HN community -- it would help me focus on these topics / embed into my questions in new episodes.

New comment by dmitrykan in "The next Google"

dmitrykan — Wed, 06 Apr 2022 06:33:28 +0000

Thanks for the article, I've learnt new search engines despite spending a couple of years recently in web scale search. I think you may consider https://usearch.com/ as another dimension in web scale search, where query log is learnt from the data, making it quite unique.

New comment by dmitrykan in "Show HN: We made an open-source personalization engine"

dmitrykan — Wed, 23 Mar 2022 20:27:03 +0000

Great project! Elasticsearch / OpenSearch / Solr have their own learning to rank plugins. Have you considered integrating Metarank with such systems? Or is your vision to provide a reranker layer, that can be independent of the underlying search engine architecture?

New comment by dmitrykan in "Vectorizing the entire eCFR for $3.00 and 22 minutes"

dmitrykan — Wed, 16 Mar 2022 16:20:25 +0000

This is fantastic work, Max! I like where you're going with this unit economy.

It is increasingly more and more common that companies need ways of productizing their deep learning models with tight SLA constraints and tight budgets. I think, one of the logical steps could be integration with vector databases / frameworks and measuring gains there in client setups.

New comment by dmitrykan in "[dead]"

dmitrykan — Wed, 22 Dec 2021 12:59:03 +0000

5th episode of Vector Podcast with Tom Lackner, VP Engineering at classic.com explaning the choise of Qdrant vector DB for his projects.

New comment by dmitrykan in "Semantic search through Wikipedia with the Weaviate vector search engine"

dmitrykan — Mon, 29 Nov 2021 16:50:02 +0000

thanks!

New comment by dmitrykan in "Semantic search through Wikipedia with the Weaviate vector search engine"

dmitrykan — Mon, 29 Nov 2021 16:49:48 +0000

To learn about vector search and get practical with it, you can check out my blog as well: https://dmitry-kan.medium.com/list/vector-search-e9b564d1427...

I'm also hosting a podcast around these topics: https://www.youtube.com/channel/UCCIMPfR7TXyDvlDRXjVhP1g

New comment by dmitrykan in "Semantic search through Wikipedia with the Weaviate vector search engine"

dmitrykan — Mon, 29 Nov 2021 15:39:57 +0000

11M+ Wikipedia articles indexed for similarity search.

Semantic search through Wikipedia with the Weaviate vector search engine

dmitrykan — Mon, 29 Nov 2021 15:39:57 +0000

Article URL: https://github.com/semi-technologies/semantic-search-through-wikipedia-with-weaviate

Comments URL: https://news.ycombinator.com/item?id=29381051

Points: 13

# Comments: 4

New comment by dmitrykan in "Vector Search"

dmitrykan — Fri, 12 Nov 2021 20:52:12 +0000

From code to podcast to billion-scale ANN challenge and statistics

Vector Search

dmitrykan — Fri, 12 Nov 2021 20:52:12 +0000

Article URL: https://dmitry-kan.medium.com/list/vector-search-e9b564d14274

Comments URL: https://news.ycombinator.com/item?id=29204388

Points: 3

# Comments: 1

New comment by dmitrykan in "Ć Programming Language"

dmitrykan — Sun, 10 Oct 2021 10:24:22 +0000

Thanks! One practical target I imagine having is: 1. write the program in Python. 2. translate it into Ć ("interlingua") 3. compile Ć into Go -- for instance there is a belief around me, that Python is not suitable for web scale loads, while Go is more suitable.

Go source code / binary in this case are of less importance for code readability, because they are meant for production deployments. Something that happened in GWT: write in Java, compile into JavaScript.