8 Efficient Similarity Search Libraries and Tools for Neural Search

Open Source Neural Search Tools

• 

  Annoy

  

  Annoy (Approximate Nearest Neighbors Oh Yeah) is a C++ library with Python bindings to search for points in space that are close to a given query point.

  License: Apache License 2.0

  GitHub
  
• 

  CLIP-as-service

  

  CLIP-as-service is a low-latency high-scalability service for embedding images and text. It can be easily integrated as a microservice into neural search solutions.

  License: Other

  GitHub
  Website: https://clip-as-service.jina.ai
• 

  DocArray

  

  DocArray is a library for nested, unstructured, multimodal data in transit, including text, image, audio, video, 3D mesh, etc. It allows deep-learning engineers to efficiently process, embed, search, recommend, store, and transfer multimodal data with a Pythonic API.

  License: Apache License 2.0

  GitHub
  Website: https://docs.docarray.org/
• 

  Faiss

  

  Faiss is a library for efficient similarity search and clustering of dense vectors.

  License: MIT License

  GitHub
  Website: https://faiss.ai
• 

  Finetuner

  

  Finetuner provides an effective way to improve performance on neural search tasks.

  License: Apache License 2.0

  GitHub
  Website: https://finetuner.jina.ai
• 

  NGT

  

  NGT provides commands and a library for performing high-speed approximate nearest neighbor searches against a large volume of data in high dimensional vector data space.

  License: Apache License 2.0

  GitHub
  
• 

  NMSLIB

  

  Non-Metric Space Library (NMSLIB): An efficient similarity search library and a toolkit for evaluation of k-NN methods for generic non-metric spaces.

  License: Apache License 2.0

  GitHub
  
• 

  Qdrant

  

  An open source vector similarity search engine with extended filtering support.

  License: Apache License 2.0

  GitHub
  Website: https://qdrant.tech

Last Updated: Dec 26, 2023