annoy
Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk (by spotify)
hnswlib
Header-only C++/python library for fast approximate nearest neighbors (by nmslib)
Our great sponsors
| annoy | hnswlib | |
|---|---|---|
| 15 | 3 | |
| 9,871 | 1,977 | |
| 3.0% | 2.7% | |
| 4.4 | 7.5 | |
| about 2 months ago | 16 days ago | |
| C++ | C++ | |
| Apache License 2.0 | Apache License 2.0 |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
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.
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.
annoy
Posts with mentions or reviews of annoy.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2022-03-02.
-
Is doing knn on the output of a music artist classifier a good way to build a system that suggests new music?
Approximate Nearest Neighbors is what Spotify uses for music recommendations: https://github.com/spotify/annoy
-
Anatomy of a txtai index
embeddings - The embeddings index file. This is an Approximate Nearest Neighbor (ANN) index with either Faiss (default), Hnswlib or Annoy, depending on the settings.
-
Should we begin Linear Algebra with Matrices, or start with Vector Spaces?
Take for example Spotifies implementation of ANN https://github.com/spotify/annoy.
- Faiss: Facebook's open source vector search library
-
I built an Image Search Engine using OpenAI CLIP and Images from Wikimedia
I used for this project Flask and OpenAI CLIP. For the vector search I used approximate nearest neighbors provided by spotify/annoy. I used Flask-SQLAlchemy with GeoAlchemy2 to query GPS coordinates. The embedding was done using UMAP.
-
Facebook AI Similarity Search (Faiss)
I’ve used annoy [0] for vector-similarity search before. Does anyone know the differences between Faiss and annoy? Thanks!
-
txtai - Semantic search backed by machine-learning powered workflows
🔎 Large-scale similarity search with multiple index backends (Faiss, Annoy, Hnswlib)
-
NLP Method(s) for Finding Commonalities?
Create a ANN search index using Annoy or FAISS
-
Announcing Hora 0.1.0, an approximate nearest neighbor search algorithm library in rust
How does this compare to something like annoy, it's used and written by Spotify.
-
[D] can you use a decision tree for clustering?
https://medium.com/@kevin_yang/simple-approximate-nearest-neighbors-in-python-with-annoy-and-lmdb-e8a701baf905
hnswlib
Posts with mentions or reviews of hnswlib.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2022-03-02.
-
Anatomy of a txtai index
embeddings - The embeddings index file. This is an Approximate Nearest Neighbor (ANN) index with either Faiss (default), Hnswlib or Annoy, depending on the settings.
- Find anything fast with Google's vector search technology
-
txtai - Semantic search backed by machine-learning powered workflows
🔎 Large-scale similarity search with multiple index backends (Faiss, Annoy, Hnswlib)
What are some alternatives?
When comparing annoy and hnswlib you can also consider the following projects:
faiss - A library for efficient similarity search and clustering of dense vectors.
implicit - Fast Python Collaborative Filtering for Implicit Feedback Datasets
TensorRec - A TensorFlow recommendation algorithm and framework in Python.
spotlight - Deep recommender models using PyTorch.
fastFM - fastFM: A Library for Factorization Machines
hora - 🚀 efficient approximate nearest neighbor search algorithm collections library written in Rust 🦀 .
libffm - A Library for Field-aware Factorization Machines
qdrant - Qdrant - vector similarity search engine with extended filtering support
vald - Vald. A Highly Scalable Distributed Vector Search Engine
tlsh
awesome-vector-search - Collections of vector search related libraries, service and research papers