Evgeniya (Jenny) Sukhodolskaya
mrscoopers.bsky.social
Evgeniya (Jenny) Sukhodolskaya
@mrscoopers.bsky.social
21 followers 24 following 26 posts
Qdrant ๐Ÿฅ‘ | ๐Ÿฅจ organizer of "Bavaria, Advancements in SEarch Development" (BASED) Meetup | love NLP & always end up working on smth search tech-related | latent PHD | certified yapper ๐Ÿ’™
Posts Media Videos Starter Packs
After seeing 3 questions full of confusion on
@qdrant.bsky.social Discord, I finally got a hint๐Ÿซก

Threw together a guide on decay functions for #relevance score boosting, aka fresher by time/closer by geo

๐Ÿช„https://medium.com/qdrant/untangling-relevance-score-boosting-in-vector-search-ccffb4a574d0
Starting with:
โœ”๏ธone dense high-dim;
โœ”๏ธone dense small-dim;
โœ”๏ธone sparse neural;
โœ”๏ธone sparse lexical (BM25, obviously);
โœ”๏ธone multimodal (text + images).

๐Ÿ‘‰ Demo youtu.be/nJIX0zhrBL4?...
Introducing Qdrant Cloud Inference
YouTube video by Qdrant Vector Database & Search Engine
youtu.be
Inferencing embeddings & using them in @qdrant.bsky.social in one go.

๐ŸŒฉ๏ธ #Cloud #inference dropped RN (local with FastEmbed was sneakily there for some time).

So here comes the convenient plugging in of text/images in Qdrant, while saving on latency.

๐Ÿ‘‡A lb of details
The week of 22โ€“26 == the search week in #Berlin

Qdrant will host a full day of workshops & talks on #vector #search & #AI at Colosseum Berlin on the 26th.
Btw, itโ€™s a Filmtheater, so weโ€™ll all be kinda movie stars (pun heavily intended).

๐Ÿ‘€ Details: qdrant.tech/blog/vector-...
Yesss, fin amazing talk on BASED Meetup turned into a cute blog!

P.S. Mostly got a stroke spelling "hitchhiker"
An open source engineer from @llamaindex.bsky.social shares trial-and-error-learned lessons.

For anyone implementing textual RAG, check the blog by @cle-does-things.bsky.social!
โœ… useful tips, from chunking to evals-related;
โœ… projects applying each tip in the wild.

๐Ÿ‘‰ qdrant.tech/blog/hitchhi...
Will spill tea around @qdrant.bsky.social dreams to make Qdrant MCP server the default solution against coding assistant hallucinations๐Ÿ‘€

Next Wed, #Munich, lu.ma/xh0natks
Yooo, Sparse Neural Retrieval fi-na-lly getting the attention it deserves!

Kudos to @hf.co for making this 5th version of SentenceTransformers real, I really-really want to see what the HF community will craft with this ๐Ÿ‘€๐Ÿ‘€๐Ÿ‘€

๐Ÿ”ฅ huggingface.co/blog/train-s...
huggingface.co
Attending Office Hours of @DataTalksClub's "LLM Zoomcamp" reminded me I'm not even in the vector search bubble, I am in a vector search snow globe...

I do be unironically loving people asking questionsโค๏ธ

P.S. A link to @LukawskiKacper & my "Vector Search" module JFYI ๐Ÿ‘‡
#bbuzz went beyond expectations (#MICES also were amazing)
Huge thanks to our hosts Tacto, the vibe was perfect!
Made me sad & jealous I donโ€™t have such an office to go to๐ŸŒš

I hope we'll continue being THAT lucky & aiming for the next meetup in Septemberโ€“October!
๐Ÿ‘‰ lu.ma/based_meetup
We had two amazing speakers:

๐Ÿ› ๏ธ Clelia Astra Bertelli blew minds with her open-sourced AI engineer experience, condensed into 35 mins
๐Ÿ‘ฉโ€๐ŸŽ“ Monica Riedler showed how multimodality in RAG really matters, backed by her research.

All materials are here:
๐Ÿ‘‰ lnkd.in/dGnkwpqA
๐Ÿฅจ/๐Ÿงต Yesterday, @wrigley_dan & I nailed the 2nd ๐๐€๐’๐„๐ƒ #search meetup in #Munich!

๐Ÿ’™ It's heartwarming to recognize people walking in. Iโ€™ll proudly assume we have regulars already :)
At the same time, every new member is super precious:3

#RAG #AI #tech
Last Friday Qdrant dropped an official n8n node with e-v-e-r-y-t-h-i-n-g.

Was possible due to new n8n's amazing feature - verified community nodes.

No more HTTP nodes for calling Qdrant's API ever again!
@qdrant.bsky.social + @n8n.io = ๐Ÿค˜

๐Ÿ‘‡links
โค๏ธ I am sincerely excited, I love train rides, meeting my colleagues irl (remote work is slowly driving me nuts) & this conf!

P.S. @qdrant.bsky.social added a bit to the #BBuzz organization, so you'll see us on coffee breaks; our Kacper ลukawski will be taking care of showing what we've got:)
โฐ ๐Ž๐ง๐ž ๐ฐ๐ž๐ž๐ค ๐ญ๐ข๐ฅ๐ฅ ๐๐ž๐ซ๐ฅ๐ข๐ง ๐๐ฎ๐ณ๐ณ๐ฐ๐จ๐ซ๐๐ฌ
I'll really try to make my talk (on the 17th at 11:10 am in Kesselhaus) fit this "๐˜๐˜ฎ๐˜ฎ๐˜ฎ๐˜ฎ, ๐˜ ๐˜ด๐˜ฉ๐˜ฐ๐˜ถ๐˜ญ๐˜ฅ ๐˜ต๐˜ณ๐˜บ ๐˜ต๐˜ฉ๐˜ช๐˜ด ๐˜ณ๐˜ฏ" vibe of @berlinbuzzwords.de!
To TLDR, it's about making ๐ฌ๐ฉ๐š๐ซ๐ฌ๐ž ๐ฉ๐š๐ซ๐ญ ๐ข๐ง ๐ก๐ฒ๐›๐ซ๐ข๐ ๐ฌ๐ž๐š๐ซ๐œ๐ก๐ž๐ฌ as ๐ซ๐ž๐ฅ๐ข๐š๐›๐ฅ๐ž as BM25, but ๐ฌ๐ž๐ฆ๐š๐ง๐ญ๐ข๐œ๐š๐ฅ๐ฅ๐ฒ ๐š๐ฐ๐š๐ซ๐ž (so ๐›๐ž๐ญ๐ญ๐ž๐ซ than BM25)
<Doing video editing>

CapCut:

- Lemme quickly transcribe your "FastEmbed" as "fast & bad", ha?
- How about we call "upsert operation" an "absurd operation"?

Is CapCut secretly paid by our competitors?๐Ÿค”
Was at Stiven Wilson's concert this weekend

Here's a riddle for you: if an LLM finishes generation when it sees EOS, when do prog rock artists understand that the song should end?
Finished Thought-Action-Observation

- "In the case of LLMs fine-tuned for function-calling, the thought process is optional"
> the thought process is optional.
... me every other day.

Seriously, are we teaching agents to think before they act, when 90% of us here don't do that?
Finished tools & special messages & found my sweet spot of self-motivation: dumb questions into the void๐Ÿค”

1. Is there a good read on jailbreaking agents? (spooky-scary)
2. Are instruct models slowly transforming to instruct-to-call-tools ones?

#hf_agents_course #agents
Finished "What are LLMs" (bach & masters in ML certainly are a cheat code);

๐Ÿค”2 q's:
1. How ADHD are agents? How many steps do they need to forget what they are doing in the kitchen?
2. Do we already have a united prompting protocol? Does MCP solve it?

#hf_agents_course #agents
Will check out @huggingface.bsky.social's "Agents Course"

๐ŸซฃI think I've never finished any online course ever & am interested to see:
a) as a devrel, how ppl out there do courses;
b) as a vector search advocate, how ppl out there approach agents.