hnswlib

🛰️ An approximate nearest-neighbor search library for Python and Java with a focus on ease of use, simplicity, and deployability.

Lightweight Nearest Neighbors with Flexible Backends

Search with BERT vectors in Solr, Elasticsearch, OpenSearch and GSI APU

Alice is a smart desktop AI assistant application built with Vue.js, Vite, and Electron. Advanced memory system, function calling, MCP support and more.

人工智障本地图片检索工具，支持以图搜图、图片去重 | An EfficientNet based image retrieval tool

hnswlib-wasm attempts to create a browser friendly version of hnswlib

A production-ready, scalable Indexer for the Jina neural search framework, based on HNSW and PSQL

A private, free, open-source search engine built on a P2P network

hnswlib golang interface

gRPC server for hnswlib

face recognition and retrieve in ios

AI YouTube Video Chat application, to ask questions to a YouTube video bot and get answers.

AI / ML Embeddings applied to the Steam Store.

The thesis presents the parallelisation of a state-of-the art clustering algorithm, FISHDBC. This objective has been achived by improving the main data structures and components of the algorithm: HNSW, MST and HDBSCAN. My contribution is based on a lock-free strategy, completely wrote in Python.

Unstructured data refers to information that is not organised using a predetermined data model or schema and cannot be stored in a conventional relational database system. There are several methods for search unstructured data semantically- That is by taking the actual context/meaning of the sentences.One best approach is index based approach.

Chat with your Documents! OpenAI powered pdf-aware chat bot demo

Source code of our paper: SWFC-ART: A Cost-effective Approach for Fixed-Size-Candidate-Set Adaptive Random Testing through Small World Graphs

SoraDB is a custom-built vector storage engine designed to manage and query high-dimensional vector data.

Given a superhero description, find the superhero associate with that description - A Semantic Search Project