InfluxDB is the Time Series Platform where developers build real-time applications for analytics, IoT and cloud-native services. Easy to start, it is available in the cloud or on-premises. Learn more →
Ann-benchmarks Alternatives
Similar projects and alternatives to ann-benchmarks
-
-
faiss
A library for efficient similarity search and clustering of dense vectors.
-
InfluxDB
Build time-series-based applications quickly and at scale.. InfluxDB is the Time Series Platform where developers build real-time applications for analytics, IoT and cloud-native services. Easy to start, it is available in the cloud or on-premises.
-
-
-
annoy
Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk
-
-
Sonar
Write Clean Python Code. Always.. Sonar helps you commit clean code every time. With over 225 unique rules to find Python bugs, code smells & vulnerabilities, Sonar finds the issues while you focus on the work.
-
minisketch
Minisketch: an optimized library for BCH-based set reconciliation
-
-
-
t-digest
A new data structure for accurate on-line accumulation of rank-based statistics such as quantiles and trimmed means
-
-
pgANN
Fast Approximate Nearest Neighbor (ANN) searches with a PostgreSQL database.
-
-
-
entt
Gaming meets modern C++ - a fast and reliable entity component system (ECS) and much more
-
pyroscope
Continuous Profiling Platform. Debug performance issues down to a single line of code
-
AspNetCoreDiagnosticScenarios
This repository has examples of broken patterns in ASP.NET Core applications
-
-
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
ann-benchmarks reviews and mentions
-
[Discussion] NLP for products matching
Plus the graph posted there is rather self explanatory. Also it gives you names of competing libraries and their benchmarks. As you can see ScaNN is the best so far, but I use annoy since its speed is sufficient for me (I usually need to match around 10k strings to 80k strings) and it's usage is very simple and straightforward.
-
DiskANN Pure Rust Implementation Interest
Based on ANN-Benchmarks (and a few other anecdotal ones I have seen) DiskANN (Vamanas) is close, but I'd be very interested in seeing yours too!
-
Vectors are over, hashes are the future
Seems the author is proposing LSH instead of vectors for doing ANN?
There are benchmarks here, http://ann-benchmarks.com/ , but LSH underperforms the state of the art ANN algorithms like HNSW on recall/throughput.
LSH I believe was state of the art 10ish years ago, but has since been surpassed. Although the caching aspect is really nice.
- The Vector Database Index: Who, what, why now, & how
-
Ask HN: What are some 'cool' but obscure data structures you know about?
HNSW, or Hierarchical Navigable Small World is a graph data structure for approximate nearest neighbor search of vectors.
https://arxiv.org/abs/1603.09320
The problem space of ANN is one of those really deep holes you can go down. It’s a game of balancing time and space, and it’s got plenty of fascinating algorithms and datastructures.
Check out http://ann-benchmarks.com/ for a comparison. HNSW is not “the best” but it’s easy to understand and is quite effective.
- Fastest way to calculate distance (drift) between vectors - at scale (billions)
- [P] A library for efficient similarity search and clustering of dense vectors, open sourced by Facebook.
-
Facebook AI Similarity Search (Faiss)
There are benchmarks you can consider (with your use case and setup in mind of course)
- Introduction to Locality-Sensitive Hashing
-
Pgvector – vector similarity search for Postgres
No, you’re looking for Approximate Nearest Neighbor. Most popular libraries are Spotify’s Annoy and Facebook Faiss. NMSLIB is very good as well. See all ur choices here: https://github.com/erikbern/ann-benchmarks#evaluated
For most general use cases u should just use gensim: https://radimrehurek.com/gensim/auto_examples/tutorials/run_...
-
A note from our sponsor - InfluxDB
www.influxdata.com | 1 Feb 2023
Stats
erikbern/ann-benchmarks is an open source project licensed under MIT License which is an OSI approved license.