Co-founder & CEO @ Qdrant. Search AI for humans, agents, and robots.
Berlin
- Tweets 356
- Following 310
- Followers 673
- Likes 370
Your embeddings default to flat space, not because anyone checked if your data is flat.
Hierarchical data isn't. On WordNet, a 5-dim Poincaré embedding hit 0.823 MAP. A 200-dim Euclidean one hit 0.168, with 40x more dimensions.
That's super power of Hyperbolic Embeddings:
qdrant.tech/articles/hyperbo…
1
4
94
We do a lot of research at @qdrant_engine: about embeddings, storage, quantization, and information retrieval in general. And we want to share our research topics and results with the community.
Eight sessions today, eight actual engineering problems:
Vector Space lifestream: luma.com/vector-space-stream
2
45
Contextual relevance: 0.92 out of 1.00.
Incorrect answers: 40%.
Repeated ingestion had increased the number of items from 8,416 to 22,946; consequently, the top five results retrieved by the agent repeatedly contained the same text segments.
Deletion of 14,530 duplicates → accuracy increased from 0.57 to 0.76. Same model, same prompt.
Full write-up, including the one failure none of these checks can see:
qdrant.tech/blog/clean-vecto…
1
4
113
Default hybrid search settings usually aren't tuned for your data.
We benchmarked two fusion methods, RRF and DBSF, across five datasets. Tuning just the k parameter changed the top result for 42% of WANDS queries, a +0.036 nDCG@10 gain.
qdrant.tech/articles/how-to-…
1
4
338
Next week is all about search—at least in Berlin! :-) Numerous events centered on search and information retrieval are taking place, ranging from the two-day Haystack conference (We still ❤️ you) to various workshops and community meetups. Naturally, @qdrant_engine will be part of the action.
1
2
6
431
On Wednesday, the 16th of September, we are organizing together with the beloved @cognee_ team a Bring Your Own Demo Night, a community meetup for Berlin's AI builders: good 🍕, cold 🍺, and people who want to see what you've built with vector search and AI memory.
▶️ Register: luma.com/berlin-sept-meetup
1
1
41
And for those who are not in Berlin, we have an even bigger global event on Thursday, 09/17. First ever: Vector Space Stream, a >4-hour virtual stream of the latest research topics in (vector) search.
▶️ Agenda: luma.com/vector-space-stream
See the full Search Week schedule at berlinsearchweek.com
1
25
Most vector databases give you one knob: RAM or disk.
We built Qdrant @qdrant_engine to give you five, because a collection doesn't outgrow its RAM budget all at once.
New benchmark-backed breakdown of when to use which 🧵
1
3
8
439
Caching full-precision vectors alone is a fine default. Until it isn't.
We watched one configuration go from a top performer to nearly the worst within a few million points, on the same cluster, just because the RAM-to-dataset ratio shifted.
1
35
Takeaway: stop sizing against point count.
Size against how much of your cluster's RAM the working set occupies right now. Re-check that ratio at every scaling step, not just at setup.
Full benchmarks + code: qdrant.tech/articles/memory-…
34
@ActianCorp launched a vector DB. Their comparison post says it's 22x faster than Qdrant.
I was curious what they'd built, so I opened the docs...
Core concepts: Collections, points, vectors, payload... Wait. I know it from somewhere. 🤔
1
1
6
729
Compatibility is a door, and doors swing both ways.
Anyone on VectorAI DB can move to Qdrant with near-zero code changes. And when they do: no 5,000 vector cap, real clustering instead of three inert fields, full and up-to-date feature set, and open-source.
1
66
Let's see how quickly they obfuscate it: docs.vectoraidb.actian.com/a…
1
53