Hacker News: jankovicsandras

New comment by jankovicsandras in "Ask HN: How are you doing RAG locally?"

jankovicsandras — Thu, 15 Jan 2026 07:18:58 +0000

You can do hybrid search in Postgres.

Shameless plug: https://github.com/jankovicsandras/plpgsql_bm25 BM25 search implemented in PL/pgSQL ( Unlicense / Public domain )

The repo includes also plpgsql_bm25rrf.sql : PL/pgSQL function for hybrid search ( plpgsql_bm25 + pgvector ) with Reciprocal Rank Fusion; and Jupyter notebook examples.

New comment by jankovicsandras in "7 Years, 2 Rebuilds, 40K+ Stars: Milvus Recap and Roadmap"

jankovicsandras — Tue, 16 Dec 2025 14:33:09 +0000

You can do hybrid search in Postgres.

Shameless plug: https://github.com/jankovicsandras/plpgsql_bm25 BM25 search implemented in PL/pgSQL ( Unlicense / Public domain )

The repo includes plpgsql_bm25rrf.sql : PL/pgSQL function for hybrid search ( plpgsql_bm25 + pgvector ) with Reciprocal Rank Fusion; and Jupyter notebook examples.

New comment by jankovicsandras in "Show HN: Fanfa – Interactive and animated Mermaid diagrams"

jankovicsandras — Tue, 09 Dec 2025 07:25:18 +0000

Looks cool!

Here's some feedback:

- the diagram is not centered and zoomed by default, this is easy to fix

- it would be great to have better animation controls, like progressbar, play half speed, etc.

- it would be great to be able to export animation to video, animgif, etc. e. g. with ffmpeg.js

New comment by jankovicsandras in "The Case Against PGVector"

jankovicsandras — Mon, 03 Nov 2025 20:44:05 +0000

Shameless plug: https://github.com/jankovicsandras/plpgsql_bm25 BM25 search implemented in PL/pgSQL ( Unlicense / Public domain )

The repo includes plpgsql_bm25rrf.sql : PL/pgSQL function for Hybrid search ( plpgsql_bm25 + pgvector ) with Reciprocal Rank Fusion; and Jupyter notebook examples.

New comment by jankovicsandras in "Production RAG: what I learned from processing 5M+ documents"

jankovicsandras — Tue, 21 Oct 2025 09:56:07 +0000

"It's also possible to do it on top of other DBs like Postgres, but takes more effort."

Shameless plug: plpgsql_bm25: BM25 search implemented in PL/pgSQL (The Unlicense / PUBLIC DOMAIN)

https://github.com/jankovicsandras/plpgsql_bm25

There's an example Postgres_hybrid_search_RRF.ipynb in the repo which shows hybrid search with Reciprocal Rank Fusion ( plpgsql_bm25 + pgvector ).

New comment by jankovicsandras in "CARA – High precision robot dog using rope"

jankovicsandras — Thu, 24 Jul 2025 06:54:28 +0000

Very cool robot dog and interesting video! Can the dog climb stairs? Isn't capstan drive temperature sensitive, e.g. the ropes will be shorter in cold and longer in warm wheather?

New comment by jankovicsandras in "Show HN: Hyvector – A fast and modern SVG editor"

jankovicsandras — Fri, 09 May 2025 15:07:24 +0000

Can this solve vector tracing? https://github.com/jankovicsandras/imagetracerjs (Public domain) Discaimer: I made this.

New comment by jankovicsandras in "Ask HN: Alternatives to Vector DB?"

jankovicsandras — Tue, 18 Mar 2025 19:38:14 +0000

Postgres is a good idea.

Shameless plug: https://github.com/jankovicsandras/plpgsql_bm25

BM25 search implemented in PL/pgSQL, there's also an example of Hybrid (BM25+pgvector) search in the repo.

New comment by jankovicsandras in "BM25 in PostgreSQL"

jankovicsandras — Mon, 03 Mar 2025 10:00:38 +0000

This looks cool!

Shameless plug:

https://github.com/jankovicsandras/plpgsql_bm25

BM25 search implemented in PL/pgSQL, might be useful if one can't use Rust extensions with Postgres, e. g. hosted Postgres without admin rights.

New comment by jankovicsandras in "I wrote a static web page and accidentally started a community (2023)"

jankovicsandras — Wed, 12 Feb 2025 09:38:50 +0000

I think the following works in Firefox. WARNING: this is a security risk obviously.

about:config -> security.fileuri.strict_origin_policy -> false

source: https://stackoverflow.com/questions/58067499/runing-javascri...

New comment by jankovicsandras in "Building a full-text search engine in 150 lines of Python code (2021)"

jankovicsandras — Fri, 24 Jan 2025 08:17:18 +0000

This is a good intro to text search. Shameless plug: If you throw in a bit more, ca. 250 SLOC, you can have BM25 search: https://github.com/jankovicsandras/bm25opt

New comment by jankovicsandras in "How to use Postgres for everything"

jankovicsandras — Sat, 07 Dec 2024 09:09:11 +0000

Can you please add this shameless plug?

https://github.com/jankovicsandras/plpgsql_bm25

Opensource BM25 search in PL/pgSQL (for example where you can't use Rust extensions), and hybrid search with pgvector and Reciprocal Rank Fusion.

New comment by jankovicsandras in "Understanding the BM25 full text search algorithm"

jankovicsandras — Wed, 20 Nov 2024 06:18:57 +0000

Shameless plug:

https://github.com/jankovicsandras/plpgsql_bm25

https://github.com/jankovicsandras/bm25opt

New comment by jankovicsandras in "Show HN: BM25opt – 30-40 x faster BM25 search algorithms (FOSS)"

jankovicsandras — Thu, 31 Oct 2024 10:00:39 +0000

This is a good point and was a difficult design decision. The reasons for changing the API are:

- easier to use with untokenized corpus and questions

- to fix issues with the tokenizing ( e.g. https://github.com/dorianbrown/rank_bm25/issues/38 ); also rank_bm25 provides no default tokenizer, a naive split-on-whitespace is a wrong choice

- considerably simplify the code (way less SLOC)

- point out the similarities of the algorithms for educational purpuses / further development

In practice, the differences are minimal ( see Example 3: comparison with rank_bm25 ).

Show HN: BM25opt – 30-40 x faster BM25 search algorithms (FOSS)

jankovicsandras — Thu, 31 Oct 2024 08:35:53 +0000

BM25opt is a score-compatible optimized rewrite of the popular https://github.com/dorianbrown/rank_bm25 , which is used by e.g. LangChain and Llamaindex. It's much faster and tries to fix some issues as well.

https://en.wikipedia.org/wiki/Okapi_BM25

Comments URL: https://news.ycombinator.com/item?id=42004614

Points: 1

# Comments: 2

New comment by jankovicsandras in "Vector databases are the wrong abstraction"

jankovicsandras — Wed, 30 Oct 2024 10:36:07 +0000

Or you can use Postgres to store the original text, the metadata and the embedding in a single table and then do hybrid queries against them (with pre- or post-filtering, optimized automatically).

Shameless plug:

BM25 search implemented in PL/pgSQL: https://github.com/jankovicsandras/plpgsql_bm25

faster BM25 search algorithms in Python: https://github.com/jankovicsandras/bm25opt

New comment by jankovicsandras in "Play 3.0 mini – A lightweight, reliable, cost-efficient Multilingual TTS model"

jankovicsandras — Tue, 15 Oct 2024 09:42:47 +0000

Hi, I don't know what's SOTA, but I got good results with these (open source, on-device) :

https://github.com/SYSTRAN/faster-whisper (speech-to-text) https://github.com/rhasspy/piper (text-to-speech)

New comment by jankovicsandras in "The quiet art of attention"

jankovicsandras — Mon, 14 Oct 2024 07:12:49 +0000

Isn't parts of this quoting or paraphrasing from the book "The Tibetan Book of Living and Dying" ? https://en.m.wikipedia.org/wiki/The_Tibetan_Book_of_Living_a...

New comment by jankovicsandras in "Ask HN: What are you working on (September 2024)?"

jankovicsandras — Mon, 30 Sep 2024 05:01:40 +0000

Free and open source Okapi BM25 search for Postgresql implemented in PL/pgSQL, so it works without extensions.

https://github.com/jankovicsandras/plpgsql_bm25

Might be useful in hosted/cloud Postgres, where you can't use Rust extensions.

New comment by jankovicsandras in "Show HN: Velvet – Store OpenAI requests in your own DB"

jankovicsandras — Thu, 26 Sep 2024 06:12:44 +0000

A hybrid search approach might help, like combining vector similarity scores with e.g. BM25 scores.

Shameless plug (FOSS): https://github.com/jankovicsandras/plpgsql_bm25 Okapi BM25 search implemented in PL/pgSQL for Postgres.