hora
vector-db-benchmark
Our great sponsors
hora | vector-db-benchmark | |
---|---|---|
9 | 6 | |
2,554 | 224 | |
0.8% | 12.5% | |
0.0 | 9.1 | |
3 months ago | 8 days ago | |
Rust | Python | |
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
- An efficient library for nearest neighbor search in native rust
-
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
- Hora: Efficient approximate nearest neighbor search algorithms in Rust
- [Project] Announcing Hora 0.1.1, an blazingly fast AI Similarity search algorithm library
- [Project] Announcing Hora 0.1.0, an blazingly fast approximate nearest neighbor search algorithm library
-
Announcing Hora 0.1.0, an approximate nearest neighbor search algorithm library in rust
github: https://github.com/hora-search/hora
vector-db-benchmark
-
RAG is Dead. Long Live RAG!
Qdrant’s benchmark results are strongly in favor of accuracy and efficiency. We recommend that you consider them before deciding that an LLM is enough. Take a look at our open-source benchmark reports and try out the tests yourself.
-
Evaluate Vector Database / Benchmarks?
Qdrant made their own benchmark. It is quite simple and also takes into consideration more options, so it should be better suited for benchmarking for production purposes.
-
Qdrant, Pinecone, Supabase
is noWhen it comes to Supabase, it's using pgvector under the hood, so it would make sense to benchmark it with the other Open Source tools. There is an open PR for that, but it's pretty old: https://github.com/qdrant/vector-db-benchmark/pull/50
-
Building a Vector Database with Rust to Make Use of Vector Embeddings
P.S.: Perhaps you want to add your database to our benchmarks repo?
-
New and Improved Embedding Model for OpenAI
Do we have any idea why lucene vector search underperforms? As of lucene 9.1 (and elastic 8.4), it runs the same sort of filtered/categorical HNSW that qdrant runs (https://lucene.apache.org/core/9_1_0/core/org/apache/lucene/...). Qdrant's benchmarking code (https://github.com/qdrant/vector-db-benchmark/blob/9263ba/en...) does use the new filtered ann query with elastic 8.4, so it appears to be a fair benchmark. Why is lucene/elastic so much slower? Is it a rust vs. java thing? Or some memory management issues?
-
Which vector search engine is the fastest?
There is also an open-source framework for benchmarking https://github.com/qdrant/vector-db-benchmark
What are some alternatives?
vald - Vald. A Highly Scalable Distributed Vector Search Engine
citrus - (distributed) vector database
annoy - Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk
ann-benchmarks - Benchmarks of approximate nearest neighbor libraries in Python
Milvus - A cloud-native vector database, storage for next generation AI applications
vector-search - The definitive guide to using Vector Search to solve your semantic search production workload needs.
instant-distance - Fast approximate nearest neighbor searching in Rust, based on HNSW index
qdrant - Qdrant - High-performance, massive-scale Vector Database for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
NumToA - An efficient method of heaplessly converting numbers into their string representations, storing the representation within a reusable byte array.
weaviate-examples - Weaviate vector database – examples
ritelinked - RiteLinked - LinkedHashMap & LinkedHashSet in Rust