hora
vald
Our great sponsors
hora | vald | |
---|---|---|
9 | 13 | |
2,545 | 1,444 | |
0.9% | 1.5% | |
0.0 | 9.4 | |
about 2 months ago | 7 days ago | |
Rust | Go | |
Apache License 2.0 | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
hora
-
Building a Vector Database with Rust to Make Use of Vector Embeddings
We have been playing around with Hora as a replacement for the Rust-CV implementation as we want PQ as well. I'll check out instanct-distance, looks very interesting!
-
Faiss: A library for efficient similarity search
Maybe https://github.com/hora-search/hora but I've never used it
-
Hora, an blazingly fast AI Similarity search algorithm library (IOS Version)
$ rustup target add aarch64-apple-ios aarch64-apple-ios $ cargo install cargo-lipo $ git clone https://github.com/hora-search/hora-ios $ cd hora-ios/hora $ cargo lipo --release
-
Announcing Hora 0.1.0, an approximate nearest neighbor search algorithm library in rust
github: https://github.com/hora-search/hora
vald
-
Top 10 Best Vector Databases & Libraries
Vald (1.2k ⭐) → A highly scalable distributed fast approximate nearest neighbor dense vector search engine. Vald is designed and implemented based on the Cloud-Native architecture. It uses the fastest ANN Algorithm NGT to search neighbors. Vald has automatic vector indexing and index backup, and horizontal scaling which made for searching from billions of feature vector data.
- open-source google-like search for workplace knowledge
-
[P] Embeddinghub: A vector database built for ML embeddings
Another approximate nearest neighbor system to look at: https://vald.vdaas.org/
- Vector Search Indexes
-
Hacker News top posts: Apr 9, 2021
Vald: A Highly Scalable Distributed Vector Search Engine\ (26 comments)
- Vald: A Highly Scalable Distributed Vector Search Engine
-
[P] Vald: a highly scalable distributed fast approximate nearest neighbour dense vector search engine.
GitHub: https://github.com/vdaas/vald
Thank you for the nice feedback, actually, we have a link in the https://vald.vdaas.org top pages python logo is the link, but it's hard to find.
What are some alternatives?
Milvus - A cloud-native vector database, storage for next generation AI applications
faiss - A library for efficient similarity search and clustering of dense vectors.
Weaviate - Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database.
annoy - Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk
alvd - alvd = A Lightweight Vald. A lightweight distributed vector search engine works without K8s.
ann-benchmarks - Benchmarks of approximate nearest neighbor libraries in Python
You-Dont-Need-GUI - Stop relying on GUI; CLI **ROCKS**
instant-distance - Fast approximate nearest neighbor searching in Rust, based on HNSW index
pgvector - Open-source vector similarity search for Postgres
NumToA - An efficient method of heaplessly converting numbers into their string representations, storing the representation within a reusable byte array.