Awesome GitHub RepositoriesEmbedding Generation

Acest proiect este un serviciu de embedding BERT de înaltă performanță și un server de inferență conceput pentru a mapa secvențele de text în vectori numerici de lungime fixă. Funcționează ca un microserviciu de învățare automată și server de model distribuit care decuplează gestionarea cererilor de calculul intensiv. Sistemul utilizează o infrastructură de mesagerie ZeroMQ pentru a oferi comunicare cu latență scăzută între clienții distribuiți și serverul de inferență. Încorporează procesarea în loturi pe partea de server și scalarea workload-ului GPU pentru a maximiza utilizarea hardware-ului și a gestiona volume mari de cereri. Platforma suportă infrastructura de căutare semantică prin generarea de embedding-uri cross-modale atât pentru text, cât și pentru imagini într-un spațiu vectorial partajat. Acest lucru permite căutarea cross-modală, clasarea relevanței conținutului și re-clasarea rezultatelor pe baza alinierii semantice între conținutul vizual și descrierile textuale. Serviciul poate fi implementat ca un microserviciu elastic accesibil prin protocoale gRPC, HTTP sau WebSocket, dispunând de streaming duplex non-blocant pentru gestionarea seturilor mari de date.

Spring AI is an application framework for Java that provides a portable, fluent API for integrating AI models, tools, and vector stores into applications. It wraps multiple AI providers behind a common interface, allowing developers to switch between chat, embedding, image, and speech models without changing application code. The framework includes a chainable chat client API similar to WebClient or RestClient, supports both synchronous and streaming interactions, and offers structured output conversion that transforms unstructured AI responses into strongly-typed Java objects. The framework

Reor is a local AI knowledge management application that stores, links, and searches personal notes using large language models and vector embeddings entirely on the user's device. It functions as a private AI note assistant, keeping all data and processing local for full privacy without relying on external cloud services. The application integrates with Ollama to manage the lifecycle of local LLMs and embedding models, handling downloads, updates, and execution. Notes are imported from markdown files, preserving existing file structure, and are automatically linked through vector-similarity

This project is a reference implementation and application template for Retrieval-Augmented Generation (RAG). It integrates Azure OpenAI with Azure AI Search to enable conversational chat interfaces that provide grounded responses based on private enterprise data. The system is distinguished by its multimodal AI interface, allowing it to process and reason over combined text, image, and PDF content. It employs a hybrid search architecture that combines vector and keyword retrieval with semantic reranking to prioritize the most relevant documents for prompt augmentation. The project covers a

pgai este un toolkit și framework AI pentru PostgreSQL, conceput pentru a integra modele de limbaj mari (LLM) și vector embeddings direct în baza de date. Acesta servește drept punte pentru executarea cererilor către modele de machine learning și pentru efectuarea traducerilor text-to-SQL în cadrul interogărilor standard de bază de date. Proiectul oferă un pipeline automatizat de vector embedding care gestionează încărcarea, parsarea și fragmentarea textului din tabele și documente nestructurate. Acest sistem utilizează un background worker pentru a sincroniza automat embedding-urile pe măsură ce datele sursă se modifică și include instrumente specializate pentru construirea de aplicații de tip retrieval-augmented generation (RAG) și motoare de căutare semantică. Toolkit-ul acoperă domenii largi de capabilități, inclusiv procesarea datelor nestructurate cu OCR, crearea de cataloage semantice pentru maparea schemelor de bază de date în limbaj natural și implementarea căutărilor de similaritate de înaltă performanță prin indexare vectorială și reranking. De asemenea, permite îmbogățirea datelor, clasificarea și moderarea conținutului prin apelarea modelelor externe via SQL.

Acest proiect este un plugin de bază de cunoștințe și manager de context RAG care utilizează o interfață de bază de date vectorială locală pentru a permite căutarea semantică și maparea relațiilor. Transformă textul în vectori numerici pentru a găsi note și fragmente corelate semantic pe baza semnificației conceptuale, nu doar a potrivirilor de cuvinte cheie. Sistemul se diferențiază printr-un vizualizator de grafuri semantice care mapează notele în clustere pentru a dezvălui conexiuni conceptuale. De asemenea, dispune de un manager de context capabil să grupeze note și fragmente locale în pachete reutilizabile pentru a oferi baze factuale solide pentru conversațiile cu modele de limbaj mari (LLM). Instrumentul acoperă o gamă largă de capabilități, inclusiv interogarea cunoștințelor în limbaj natural, executarea automatizată a fluxurilor de lucru pentru crearea de note și capacitatea de a ruta prompturile între modele AI locale și cele bazate pe cloud. Oferă mai multe interfețe de descoperire, cum ar fi indicatori de conținut corelat inline și un panou de subsol pentru afișarea documentelor similare în timpul procesului de editare.

zvec is an embedded vector database engine and indexing library designed for high-dimensional similarity search. It functions as a hybrid search engine and a retrieval-augmented generation knowledge base, allowing for the storage and retrieval of dense and sparse vectors. The system is distinguished by its hybrid retrieval pipeline, which fuses vector similarity, full-text keyword matching, and scalar metadata filtering into single query operations. It supports a plugin-based model integration system for registering custom embedding models and rerankers, as well as language bindings for nativ

BiliNote is a tool that converts video URLs into structured, organized notes. It works by extracting video content and metadata from major platforms, transcribing audio to text entirely on-device using a local speech recognition model, and then summarizing the transcript with a language model to produce clean notes that can include screenshots and timestamp links. What sets BiliNote apart is its configurable AI backend, which lets you choose and switch between different language model providers for generating summaries. All transcription happens offline and locally, preserving privacy and ena

This project is a collection of TensorFlow machine learning examples providing reference implementations for various neural network paradigms. It covers supervised, unsupervised, reinforcement, and sequential learning models. The repository includes implementations for convolutional neural networks focused on image classification and ranking, as well as recurrent neural networks for time-series forecasting and sequence-to-sequence translation. It further provides examples of reinforcement learning agents trained via reward optimization and unsupervised learning techniques such as autoencoders

Casibase is an open-source platform that orchestrates multi-turn conversations with large language models and manages retrieval-augmented knowledge bases from a single interface. It provides a unified system for connecting to over 30 AI model providers, ingesting documents into vector embeddings for semantic search, and running autonomous agent loops that can drive a browser, search the web, execute commands, and integrate with external tools. The platform distinguishes itself by combining AI conversation management with infrastructure and application orchestration capabilities. It includes a

Memgraph is an in-memory, distributed graph database designed for high-performance labeled property graph management. It utilizes a Cypher query engine for declarative data retrieval and manipulation, providing a scalable knowledge graph backend that integrates vector search and graph traversals. The system distinguishes itself as a real-time graph analytics platform, employing native C++ and CUDA implementations to execute complex network analysis and dynamic community detection on streaming data. It provides specialized support for AI integration, including GraphRAG capabilities, the constr

RavenDB is a multi-model NoSQL document database designed for high-performance, ACID-compliant data storage. It persists structured information as schema-flexible JSON documents and utilizes a unit-of-work session pattern to track entity changes and batch modifications into atomic transactions. The platform is built on a distributed architecture that supports horizontal scaling through sharding and ensures high availability via multi-node, master-to-master cluster replication. The database distinguishes itself through a self-optimizing query engine that automatically creates and maintains ind

Lightly is a self-supervised learning framework and computer vision data curation tool designed to manage large image datasets and train models on unlabeled data. It functions as a PyTorch vision library and dataset management SDK, providing tools to convert raw images into high-dimensional vectors for similarity search, visualization, and feature extraction. The project implements a variety of self-supervised architectures, including MoCo, SimCLR, VICReg, Barlow Twins, and masked image modeling. It distinguishes itself by combining these learning frameworks with active learning capabilities,

GraphSAGE is a graph neural network framework designed for inductive representation learning on large-scale graphs. It functions as an inductive graph embedding tool and neighborhood aggregation engine, enabling the generation of numerical node representations that generalize to previously unseen data. The system distinguishes itself by computing node embeddings through the aggregation of features from local neighborhoods rather than relying on a global lookup table. This approach allows the framework to operate as both a supervised graph classifier for predicting categorical node classes and

FalkorDB is a high-performance graph database management system and vector graph database. It serves as a knowledge graph construction tool and a GraphRAG knowledge store, integrating structured property graphs with vector search to provide grounded context for large language models. The engine is designed as a multi-tenant graph engine, capable of hosting thousands of isolated datasets within a single instance. The system distinguishes itself by using linear algebra for query execution, treating relationship tensors as matrix multiplications to achieve low-latency multi-hop traversals. It ut

This project is a Model Context Protocol server and AI agent database connector. It provides a standardized communication layer that allows language models to interact with relational data stores, read database schemas, and manage PostgreSQL database resources. The implementation acts as a serverless host for the Model Context Protocol, deploying on distributed edge functions to connect AI assistants to a project. This enables AI agents to perform database administration, execute SQL queries, and handle schema migrations through an AI-compatible interface. The system covers broader capabilit

Superlinked is a development framework designed for building semantic search and retrieval pipelines. It functions as a machine learning data pipeline and semantic retrieval engine, providing the tools necessary to unify data schema definition, embedding generation, and vector database integration within a single application. The framework distinguishes itself by acting as a vector database orchestrator that manages the lifecycle of machine learning models alongside complex search logic. It enables developers to construct structured data models that map raw content and metadata into unified r