Viewing profile — etiennedi
etiennedi
HN member- Joined
- Tue, Apr 03, 2018, 8:54 PM UTC
- HN karma
- 20
- Public activity
- 18 items
- HN profile
- View on Hacker News ↗
About etiennedi
No profile information was provided.
Recent public activity
-
comment
Comment #37402956
We (at Weaviate) support separate BM25, vector, and combined hybrid search, so I can talk about the performance aspect of all of these a lot. The tl;dr is: It's complicated. What y…
-
comment
Comment #36779845
Thanks, appreciate your perspective. This is much more insightful than just "affiliated==botnet". I agree that this can be a huge positive and - at least for me - that was the moti…
-
comment
Comment #36775736
Fair point, edited my post. The fact that I love the visual design is my personal opinion though :-D
-
comment
Comment #36775067
Not sure if that alone is what made Go successful. But yes, having great networking tools in the stdlib is very refreshing! One of the things Go got right.
-
comment
Comment #36774965
Love the visual design, too. The generative/RAG/semantic search is the interesting part, but it's also just very pleasant to look at. Which can go a long way. EDIT: Disclaimer, I a…
- story
- story
- story
-
comment
Comment #32482436
Hi, the author and long-time Go user here. Let me know if you have any questions. For me the introduction of GOMEMLIMIT finally makes Go a viable choice for high-heap applications.…
- story
-
comment
Comment #29568005
I agree, but at the same time now is the easiest it's ever been to create great vectors. Sentence-Bert [1] by Nils Reimers is a collection of pre-trained models specficially traine…
-
comment
Comment #29567536
The models that create the vector embeddings are trained on either general or domain specific knowledge. So, to oversimplify it a bit: The model has learned - based on the training…
-
comment
Comment #29558768
Spot on! Both of those were motivating factors when building Weaviate (Open Source Vector Search Engine). We really wanted it to feel like a full database or search engine. You sho…
-
comment
Comment #29557586
Checkout the open source vector search engine Weaviate: https://github.com/semi-technologies/weaviate It’s not a relational db, but it supports Graph-like connections between objec…
-
comment
Comment #26769029
Exactly. See my reply on this comment thread comment thread to see how Weaviate solves the filter-issue by using an inverted index to produce a whitelist of IDs which is then passe…
-
comment
Comment #26769020
Main author and architect of Weaviate ( https://github.com/semi-technologies/weaviate ) here. This real-time requirement was one of the major design principles from the get-go in W…
-
comment
Comment #26768991
You might be interested in checking out Weaviate ( https://github.com/semi-technologies/weaviate ) which supports combining vector search with boolean filters. In Weaviate, the vec…
- story