hnswlib VS qdrant

How does this compare to hsnwlib - is it faster? https://github.com/nmslib/hnswlib

Last week I released Moodflix (https://moodflix.streamlit.app), a movie recommendation engine based to find movies based on your mood.

Moodflix was created on top of a movie dataset of 10k movies from The Movie Database. I vectorised the films using Hugging Face's T5 model (https://huggingface.co/docs/transformers/model_doc/t5) using the film's plot synopsis, genres and languages. Then I indexed the vectors using hnswlib (https://github.com/nmslib/hnswlib). LLMs can understand a movie's plot pretty well and distill the similarities between a user's query (mood) to the movie's plot and genres.

I have got feedback from close friends around linking movies to other review sites like IMDB or Rotten Tomatoes, linking movies to sites to stream the movie and adding movie posters. I would also love to hear from the community what things you like, what you want to see and what things you consider can be improved.

Actually the "ef" is not epsilon. It is a parameter of the HNSW index: https://github.com/nmslib/hnswlib/blob/master/ALGO_PARAMS.md...

If you want to go larger you could still use some simple setup in conjunction with faiss, annoy or hnsw.

Many vector databases are using Hnswlib and that is a supported vector index alongside Faiss and Annoy.

hnswlib (https://github.com/nmslib/hnswlib) is a strong alternative to faiss that I have enjoyed using for multiple projects. It is simple and has great performance on CPU.

After working through several projects that utilized local hnswlib and different databases for text and vector persistence, I integrated hnswlib with sqlite to create an embedded vector search engine that can easily scale up to millions of embeddings. For self-hosted situations of under 10M embeddings and less than insane throughput I think this combo is hard to beat.

https://github.com/jiggy-ai/hnsqlite

https://github.com/nmslib/hnswlib

Used it to index 40M text snippets in the legal domain. Allows incremental adding.

I love how it just works. You know, doesn’t ANNOY me or makes a FAISS. ;-)

3000 texts doesn't sound like to many, so may be a brute force cos calculation to find the most similar vector would work. If that's taking too much time, may be look at KNN or ANN modules to speed up finding the most similar vector. I use hsnwlib in knn mode for this. SOrt through about 350,000 vectors in about 30-50 msec.

hnswlib is in cpp and has python bindings (you should be able to make your own for other languages).

https://github.com/nmslib/hnswlib

embeddings - The embeddings index file. This is an Approximate Nearest Neighbor (ANN) index with either Faiss (default), Hnswlib or Annoy, depending on the settings.

I'm currently looking to implement locally, using QDrant [1] for instance.

I'm just playing around, but it makes sense to have a runnable example for our users at work too :) [2].

[1]. https://qdrant.tech/

Also compare with qdrant's Rust implementation; they tout their performance. https://github.com/qdrant/qdrant/tree/master/lib/segment/src...

There are much better known examples, such as https://qdrant.tech/ and https://github.com/lancedb/lancedb

For more information, see our release notes. Qdrant is an open source project. We welcome your contributions; raise issues, or contribute via pull requests!

Initialize the Qdrant Client with in-memory storage. The collection name will be “imagebind_data” and we will be using cosine distance.

Qdrant is an open-source vector search engine optimized for performance and flexibility. It supports both exact and approximate nearest neighbor search, providing a balance between accuracy and speed for various AI and ML applications.

Qdrant serves as a vector database, optimized for handling high-dimensional data typically found in AI and ML applications. It's designed for efficient storage and retrieval of vectors, making it an ideal solution for managing the data produced and consumed by AI models like Mistral 7B. In our setup, Qdrant handles the storage of vectors generated by the language model, facilitating quick and accurate retrievals.