Updated 6 months ago

usearch β€’ Rank 25.4 β€’ Science 77%

Fast Open-Source Search & Clustering engine Γ— for Vectors & Arbitrary Objects Γ— in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, C#, GoLang, and Wolfram πŸ”

Updated 6 months ago

flashrank β€’ Rank 20.1 β€’ Science 67%

Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cross-encoders and more. Created by Prithivi Da, open for PRs & Collaborations.

Updated 6 months ago

uform β€’ Rank 15.6 β€’ Science 64%

Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and πŸ”œ video, up to 5x faster than OpenAI CLIP and LLaVA πŸ–ΌοΈ & πŸ–‹οΈ

Updated 6 months ago

ustore β€’ Rank 15.3 β€’ Science 54%

Multi-Modal Database replacing MongoDB, Neo4J, and Elastic with 1 faster ACID solution, with NetworkX and Pandas interfaces, and bindings for C 99, C++ 17, Python 3, Java, GoLang πŸ—„οΈ

Updated 6 months ago

weaviate β€’ Rank 24.2 β€’ Science 44%

Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database​.

Updated 6 months ago

com.arcadedb:arcadedb-console β€’ Rank 21.8 β€’ Science 44%

ArcadeDB Multi-Model Database, one DBMS that supports SQL, Cypher, Gremlin, HTTP/JSON, MongoDB and Redis. ArcadeDB is a conceptual fork of OrientDB, the first Multi-Model DBMS. ArcadeDB supports Vector Embeddings.

Updated 5 months ago

deeplake β€’ Rank 25.6 β€’ Science 36%

Database for AI. Store Vectors, Images, Texts, Videos, etc. Use with LLMs/LangChain. Store, query, version, & visualize any AI data. Stream data in real-time to PyTorch/TensorFlow. https://activeloop.ai

Updated 6 months ago

ragoon β€’ Rank 9.3 β€’ Science 44%

High level library for batched embeddings generation, blazingly-fast web-based RAG and quantized indexes processing ⚑

Updated 5 months ago

https://github.com/ashvardanian/simsimd β€’ Rank 25.6 β€’ Science 26%

Up to 200x Faster Dot Products & Similarity Metrics β€” for Python, Rust, C, JS, and Swift, supporting f64, f32, f16 real & complex, i8, and bit vectors using SIMD for both AVX2, AVX-512, NEON, SVE, & SVE2 πŸ“

Updated 5 months ago

gpl β€’ Rank 11.9 β€’ Science 10%

Powerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled corpus and yields massive improvement: "GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval" https://arxiv.org/abs/2112.07577

Updated 6 months ago

lorann β€’ Science 36%

Approximate Nearest Neighbor search using reduced-rank regression, with extremely fast queries, tiny memory usage, and rapid indexing on modern vector embeddings.

Updated 6 months ago

mlann β€’ Science 44%

A Multilabel Classification Framework for Approximate Nearest Neighbor Search