How to Build the Ultimate Hybrid Search with Qdrant

How to Build the Ultimate Hybrid Search with Qdrant

Qdrant - Vector Database & Search Engine

10 месяцев назад

8,229 Просмотров

Ссылки и html тэги не поддерживаются


Комментарии:

@andydataguy
@andydataguy - 19.07.2024 22:33

Great presentation! Nice to see the different search options in practice 🙏🏾

Ответить
@roberth8737
@roberth8737 - 19.07.2024 23:03

More of these!

Ответить
@javilobato4829
@javilobato4829 - 26.07.2024 08:58

Fantastic video! I loved how clearly you explained building the ultimate hybrid search with Qdrant. The step-by-step guide and practical examples made it so easy to follow. Can't wait to implement this in my projects! Any tips on optimizing performance for large datasets? Thanks for sharing!

Ответить
@samketola919
@samketola919 - 30.07.2024 00:23

can i use bm25 in combination with open ai embedding (tekt-embedding-3-smal)? I intend to put about 300 GB of pdf books in qdrant?is there a problem if i omit late interaction embedding?

Ответить
@iskrabesamrtna
@iskrabesamrtna - 03.08.2024 23:15

these new qdrant features look insane, great webinar, I have to test all this myself, really inspiring, thanks!

Ответить
@janfilips3244
@janfilips3244 - 11.08.2024 15:23

Kacper, is there a way to reach out to you?

Ответить
@viky2002
@viky2002 - 03.12.2024 11:58

this got better customizability compared to llamaindex

Ответить
@kenchang3456
@kenchang3456 - 18.12.2024 18:03

Excellent video, I watched it twice :-) Thank you very much.

Ответить
@adityakhandelwal6799
@adityakhandelwal6799 - 30.01.2025 18:48

Is there a way if we can assign weights to dense and sparse model?

Ответить
@rkenne1391
@rkenne1391 - 07.04.2025 11:15

I am a bit of an IR geek and I have tried many IR databases. This is by far the cleanest implementation and most complete approach for phased retrieval. Kudos to the team. BEAUTIFUL !!!

Ответить