Alyka
Re:Qdrant v0.11: fully scalable vector search engine
on Wednesday October 26, 2022 @11:37AM (#33345342)
A new release of Qdrant vector search engine went live!
Version 0.11 brings the replication, making Qdrant fully scalable! There is a new administration API and exact search support, but also some more improvements.
0.11 is backwards compatible with 0.10.5 storage in single-node deployment!
Re:Airbnb.com.au Show total listing price including any fees
on Tuesday October 18, 2022 @11:36AM (#33248974)
ahh... lucky Australia))
Re:Airbnb.com.au Show total listing price including any fees
on Tuesday October 18, 2022 @08:24AM (#33246149)
Finally! I wish other domains do the same
Integration of Qdrant ANN vector database back end with txtai
Re:Integration of Qdrant ANN vector database back end with txtai
on Tuesday October 18, 2022 @08:17AM (#33246083)
Qdrant has implemented https://github.com/qdrant/qdrant-txtai, a library making it easy to combine both tools together
There are still other options available :) For example, Qdrant vector search engine. It's written in Rust, and it's not about crypto. And currently they are hiring Rust developer. Check job openings in LinkedIn
Re:Building a Semantic Search System
on Monday October 17, 2022 @04:01AM (#33230881)
A case study on how to simply create a search system with txtai, Qdrant and pretrained language models. The cool thing about the semantic search is that none of the words used in a query has to be used in any document in our dataset, as the model is already capable of capturing synonyms. This is a huge advantage over conventional search algorithms like BM25.
Building a Semantic Search System
Re:New Climate Maps Show a Transformed United States
on Wednesday October 05, 2022 @12:14PM (#33097415)
Scary tendency. Was interesting to read
Re:Storing Multiple Vectors per Object
on Wednesday October 05, 2022 @09:07AM (#33095054)
Qdrant 0.10 is the first version supporting storing multiple vectors per object. Kacper Łukawski shared how to set it up.
Storing Multiple Vectors per Object
Re:Solo Travel Disasters
on Tuesday September 27, 2022 @01:41PM (#32998556)
Because, solo traveling is a pretty good experience when you don't need to wait for smb if you want to travel (totally agree with it btw). And disaster is not about solo traveling.
Re:Music on the brain: Listening can influence our brain’s activity
on Monday September 26, 2022 @12:15PM (#32984951)
The topic is interesting. But there way too many books and articles about it
Re:Solo Travel Disasters
on Monday September 26, 2022 @11:38AM (#32984521)
I'd say that title is completely opposite to the article.
But it was interesting to read)
Batch vector search – multiple vectors
Re:Batch vector search – multiple vectors
on Monday September 26, 2022 @11:30AM (#32984407)
The latest release of Qdrant 0.10.0 has introduced a lot of functionalities that simplify some common tasks. Those new possibilities come with some slightly modified interfaces of the client library. One of the recently introduced features is the possibility to query the collection with multiple vectors at once — a batch search mechanism.
Re:ARM architecture for vector search engine
on Friday September 23, 2022 @05:43AM (#32949783)
Qdrant 0.10 supports ARM architecture out of the box! If you use Apple M1 or were wondering about using ARM processors in the cloud, you no longer need to emulate an x86 Docker image.
ARM architecture for vector search engine
Show HN: Number of layers for efficient fine-tuning. Experiments
https://qdrant.tech/articles/embedding-recycler/
Model fine-tuning allows you to improve the quality of the pre-trained models with just a fraction of the resources spent on training the original model. Qdrant team has run several experiments to test the number of layers to fine-tune.
Re:Vector search engine with dynamic cluster scaling capabilities
on Wednesday August 10, 2022 @10:04AM (#32412136)
Qdrant has released the new version vector similarity search engine - v.0.9.0. It features the dynamic cluster scaling capabilities. Now Qdrant is more flexible with cluster deployment, allowing to move shards between nodes and remove nodes from the cluster.
Vector search engine with dynamic cluster scaling capabilities
Re:Qdrant vector search engine v0.9.0 update went live
on Monday August 08, 2022 @12:17PM (#32387453)
Qdrant has released the new version vector similarity search engine - v.0.9.0. It features the dynamic cluster scaling capabilities. Now Qdrant is more flexible with cluster deployment, allowing to move shards between nodes and remove nodes from the cluster.
Qdrant vector search engine v0.9.0 update went live
Re:
on Wednesday August 03, 2022 @11:29AM (#32333060)
Andrey Vasnetsov, CTO at #Qdrant will speak about #VectorSearch and applications at #LearnNLP academy. 5.08.2022, at 15.00 CEST
Qdrant: Open-Source Vector Similarity Search Engine
Show HN: Finding errors in datasets with Similarity Search
https://qdrant.tech/articles/dataset-quality/
The process of splitting or labeling data is error-prone, and these errors can be very costly. George Panchuk, ML Engineer at Qdrant, shares how to define misplaced items with similarity search and avoid errors in categorized datasets.
Re:Distributed approximate nearest neighbours with Qdrant
on Monday June 27, 2022 @03:10PM (#31899297)
Qdrant 0.8.x has introduced an experiment distributed mode. This tutorial covers the basics of running the Qdrant cluster with docker-compose.
Distributed approximate nearest neighbours with Qdrant
Re:7 Reasons To Use A Tag Manager
on Monday June 20, 2022 @06:07AM (#31808419)
But what is the point using another tag manager? All this advantages are true, but you can have them with google tag manager