awesome-repositories.com
Blog
MCP
awesome-repositories.com

Descubre los mejores repositorios open-source con nuestra búsqueda potenciada por IA.

ExplorarBúsquedas curadasAlternativas open-sourceSoftware autohospedableBlogMapa del sitio
ProyectoServidor MCPAcerca deCómo clasificamosPrensa
Aviso legalPrivacidadTérminos
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·

27 repositorios

Awesome GitHub RepositoriesVector Document Indexing

Automated workflows for indexing documents into vector databases to support real-time search and retrieval.

Explore 27 awesome GitHub repositories matching data & databases · Vector Document Indexing. Refine with filters or upvote what's useful.

Awesome Vector Document Indexing GitHub Repositories

Encuentra los mejores repositorios con IA.Buscaremos los repositorios que mejor coincidan usando IA.
  • pathwaycom/pathwayAvatar de pathwaycom

    pathwaycom/pathway

    62,959Ver en GitHub↗

    Pathway is a high-performance data processing framework designed for building unified batch and streaming pipelines. It functions as an orchestrator for complex data transformations, utilizing a differential dataflow engine to process updates incrementally. By treating static datasets and continuous event streams with identical logic, the platform ensures exactly-once processing semantics and consistent results across diverse data sources. The framework distinguishes itself through its specialized support for real-time artificial intelligence and retrieval-augmented generation. It features in

    Integrates external vector database clients directly into data ingestion workflows to automate real-time document indexing.

    Pythonbatch-processingdata-analyticsdata-pipelines
    Ver en GitHub↗62,959
  • imartinez/privategptAvatar de imartinez

    imartinez/privateGPT

    57,281Ver en GitHub↗

    PrivateGPT is a private AI document assistant and local knowledge base manager designed for querying private files and documents using retrieval-augmented generation. It functions as a local language model application and API gateway, allowing users to obtain cited answers from unstructured data without sending information to external servers. The system differentiates itself by acting as a tool integrator that connects language models to external functions, including web search, tabular data analysis, and custom action extensions. It provides a standardized API layer that allows local infere

    Indexes unstructured documents into vector databases to support real-time semantic search and retrieval.

    Python
    Ver en GitHub↗57,281
  • yeachan-heo/oh-my-codexAvatar de Yeachan-Heo

    Yeachan-Heo/oh-my-codex

    30,984Ver en GitHub↗

    oh-my-codex is an AI coding workflow orchestrator and a retrieval augmented generation documentation assistant. It manages complex programming tasks through a structured sequence of planning, execution, and verification phases, while providing tools for querying and translating technical documentation. The project utilizes Git worktrees to isolate parallel coding sessions, ensuring that concurrent tasks remain independent. It integrates a vector-store knowledge base to index documents into embeddings, enabling semantic search and factual context retrieval across multiple languages. The syste

    Converts text documents into mathematical vectors for efficient semantic search and context retrieval.

    TypeScript
    Ver en GitHub↗30,984
  • gitbookio/gitbookAvatar de GitbookIO

    GitbookIO/gitbook

    28,902Ver en GitHub↗

    Gitbook is a documentation-as-code platform designed for centralized technical knowledge management. It functions as a knowledge management system that synchronizes documentation files directly with version control repositories, allowing teams to maintain content alongside their source code. The platform distinguishes itself through an integrated artificial intelligence layer that provides context-aware search assistance and automated content suggestions. By utilizing block-based content modeling, it enables the construction of structured, modular documentation that can be compiled into stati

    Automates the indexing of documentation into vector databases to enable natural language search and retrieval.

    TypeScriptdocumentationgitgitbook
    Ver en GitHub↗28,902
  • cinnamon/kotaemonAvatar de Cinnamon

    Cinnamon/kotaemon

    25,139Ver en GitHub↗

    Kotaemon is an orchestration framework designed for building modular, agentic workflows that integrate document processing, retrieval-augmented generation, and multi-step reasoning. It provides a comprehensive platform for developing document-based question answering systems, allowing users to chain language models, prompt templates, and external tools into complex, automated pipelines. The system distinguishes itself through a highly modular architecture that emphasizes component-based composition and schema-driven data exchange. It supports autonomous agents capable of decomposing complex q

    Automates the indexing of documents into vector databases to support real-time search and retrieval.

    Pythonchatbotllmsopen-source
    Ver en GitHub↗25,139
  • mastra-ai/mastraAvatar de mastra-ai

    mastra-ai/mastra

    21,221Ver en GitHub↗

    Mastra is an orchestration framework designed for building, deploying, and managing autonomous AI agents and multi-agent systems. It provides a comprehensive suite of primitives for creating resilient AI applications, including durable workflow orchestration, event-driven agent loops, and semantic memory management. By integrating these core components, the platform enables developers to build complex, multi-step processes that can reason about goals and execute tasks without manual intervention. The framework distinguishes itself through its focus on observability and secure, isolated execut

    Automates the indexing of documents into vector databases to support efficient semantic search.

    TypeScriptagentsaichatbots
    Ver en GitHub↗21,221
  • openai/chatgpt-retrieval-pluginAvatar de openai

    openai/chatgpt-retrieval-plugin

    21,192Ver en GitHub↗

    This project is a retrieval-augmented generation pipeline designed for building custom ChatGPT plugins that allow language models to query private or professional documents. It implements a full retrieval workflow, from processing and indexing document chunks to retrieving relevant context for natural language queries. The system distinguishes itself through a hybrid retrieval approach that combines dense vector embeddings with sparse keyword matching, further refined by a two-stage semantic re-ranking process. It includes specialized data privacy tools for screening personally identifiable i

    Implements automated workflows for updating and inserting document embeddings into vector databases to maintain an up-to-date knowledge base.

    Pythonchatgptchatgpt-plugins
    Ver en GitHub↗21,192
  • facebookresearch/llama-recipesAvatar de facebookresearch

    facebookresearch/llama-recipes

    18,379Ver en GitHub↗

    This repository is a collection of frameworks and guides for Llama models, functioning as a fine-tuning framework, an inference pipeline, and an AI workflow orchestrator. It provides tools for adapting large language models to specific datasets and domains. The project includes a parameter-efficient fine-tuning toolkit that utilizes techniques like low-rank adaptation to reduce memory and compute requirements. It also serves as an implementation guide for retrieval-augmented generation, combining model inference with external data retrieval to improve response accuracy. The capability surfac

    Queries external databases for relevant text chunks using semantic similarity to ground responses.

    Jupyter Notebook
    Ver en GitHub↗18,379
  • arc53/docsgptAvatar de arc53

    arc53/DocsGPT

    17,939Ver en GitHub↗

    DocsGPT is a retrieval-augmented generation platform and private knowledge base used to build AI agents that perform grounded search and analysis. It functions as a multi-model AI orchestrator and enterprise agent builder, allowing for the integration of various local and cloud language models to customize reasoning and text generation. The project provides a visual environment for developing automated assistants using conditional logic and third-party API connectivity. It enables the creation of private AI agents capable of performing enterprise search and detailed document analysis using pr

    Indexes text and audio data into vector databases to support semantic search and citations.

    Pythonagent-builderagentsai
    Ver en GitHub↗17,939
  • modsetter/surfsenseAvatar de MODSetter

    MODSetter/SurfSense

    14,816Ver en GitHub↗

    SurfSense is a self-hosted platform designed for building retrieval-augmented generation pipelines and managing private knowledge bases. It functions as a containerized research stack that allows users to index diverse data sources and query them using language models, ensuring that all information retrieval is grounded in specific source citations. The platform distinguishes itself through its modular architecture, which supports the integration of custom tools and diverse language models via a unified abstraction layer. It facilitates secure, collaborative research environments by implement

    Utilizes vector-database-backed indexing to maintain high-dimensional search capabilities for private knowledge bases.

    Pythonaceternity-uiagentagents
    Ver en GitHub↗14,816
  • netease-youdao/qanythingAvatar de netease-youdao

    netease-youdao/QAnything

    14,020Ver en GitHub↗

    QAnything is a retrieval-augmented generation application framework and self-hosted AI interface. It functions as a system that combines a vector database knowledge base, a document parsing service, and a hybrid search engine to generate answers based on private user data. The project features a modular pipeline architecture that allows users to independently replace components such as parsers, embedding models, and reranking engines. It supports local-first model deployment and offline operation to ensure data privacy, and includes a two-stage retrieval pipeline that merges dense vector embe

    Implements an automated pipeline that parses complex files into chunks and stores them as vector embeddings.

    Python
    Ver en GitHub↗14,020
  • unstructured-io/unstructuredAvatar de Unstructured-IO

    Unstructured-IO/unstructured

    14,019Ver en GitHub↗

    Unstructured is an enterprise-grade data orchestration engine designed to transform raw, unstructured files into structured, machine-readable formats. It functions as a comprehensive platform for document ingestion, partitioning, and enrichment, specifically engineered to prepare complex data for retrieval-augmented generation and agentic AI workflows. The platform distinguishes itself through its sophisticated document processing strategies, which combine rule-based extraction with vision-language models to handle diverse file layouts, tables, and images. It provides a modular architecture t

    Transfers processed document elements into vector database indices to support retrieval-augmented generation workflows.

    HTMLdata-pipelinesdeep-learningdocument-image-analysis
    Ver en GitHub↗14,019
  • cloudwego/einoAvatar de cloudwego

    cloudwego/eino

    9,675Ver en GitHub↗

    Eino is an AI agent development kit and LLM application framework designed for building autonomous agents and orchestrating complex language model workflows. It serves as a multi-agent orchestration engine and workflow orchestrator, providing a graph-based execution model to route data between models, tools, and retrievers. The framework distinguishes itself through a robust set of multi-agent coordination patterns, including supervisor-led management, sequential flows, and autonomous reasoning loops like ReAct. It features advanced agent execution controls such as active turn preemption, che

    Implements workflows for indexing documents into vector databases to enable semantic association searches.

    Goaiai-applicationai-framework
    Ver en GitHub↗9,675
  • genkit-ai/genkitAvatar de genkit-ai

    genkit-ai/genkit

    6,141Ver en GitHub↗

    Genkit es un framework de aplicaciones LLM y un toolkit para desarrolladores de IA generativa diseñado para construir aplicaciones de IA en producción. Sirve como un orquestador de flujos de trabajo de IA que coordina llamadas a modelos y el uso de herramientas agenticas a través de flujos de ejecución con seguridad de tipos. El proyecto proporciona una interfaz de modelo unificada y una arquitectura de plugins para estandarizar el acceso a diversos modelos de lenguaje grandes, almacenes vectoriales y backends de telemetría. Se distingue por una suite de observabilidad dedicada para rastrear pasos de ejecución y un toolkit para desarrolladores para realizar prompts, depurar y evaluar la lógica de IA a través de una interfaz local. El framework cubre una amplia superficie de capacidades, incluyendo orquestación de agentes con llamadas a herramientas y delegación de sub-agentes, generación aumentada por recuperación (RAG) mediante integración con bases de datos vectoriales y generación de salida estructurada usando validación basada en esquemas. También incluye sistemas para la gestión de sesiones con estado, streaming de respuestas basado en eventos y la capacidad de exponer flujos de IA como endpoints HTTP escalables. El desarrollo cuenta con soporte de una interfaz de línea de comandos para ejecutar funciones y gestionar logs.

    Indexes documents into vector stores to enable efficient similarity searches.

    TypeScript
    Ver en GitHub↗6,141
  • firebase/genkitAvatar de firebase

    firebase/genkit

    6,121Ver en GitHub↗

    Genkit is an open-source framework for building AI-powered applications. It provides a unified interface for connecting to hundreds of generative AI models from multiple providers, enabling text, image, audio, and video generation through a single API. The framework structures multi-step AI interactions—including chat, retrieval-augmented generation, tool use, and agentic workflows—as composable, traceable flows with built-in streaming and state management. The framework distinguishes itself through a comprehensive developer toolkit that includes a command-line interface and a local developer

    Fetches relevant documents from an index using vector embeddings for semantic similarity.

    TypeScript
    Ver en GitHub↗6,121
  • timescale/pgaiAvatar de timescale

    timescale/pgai

    5,802Ver en GitHub↗

    pgai es un kit de herramientas y framework de IA para PostgreSQL diseñado para integrar modelos de lenguaje de gran tamaño (LLM) y embeddings vectoriales directamente en la base de datos. Actúa como un puente para ejecutar solicitudes de modelos de machine learning y realizar traducciones de texto a SQL dentro de consultas estándar de base de datos. El proyecto proporciona un pipeline automatizado de embeddings vectoriales que gestiona la carga, el análisis y la fragmentación de texto desde tablas y documentos no estructurados. Este sistema utiliza un worker en segundo plano para sincronizar los embeddings automáticamente a medida que cambian los datos de origen e incluye herramientas especializadas para crear aplicaciones de generación aumentada por recuperación (RAG) y motores de búsqueda semántica. El kit de herramientas cubre amplias áreas de capacidad, incluyendo el procesamiento de datos no estructurados con OCR, la creación de catálogos semánticos para mapear esquemas de bases de datos a lenguaje natural, y la implementación de búsquedas de similitud de alto rendimiento mediante indexación vectorial y reordenamiento de resultados. También permite el enriquecimiento de datos, la clasificación y la moderación de contenido llamando a modelos externos mediante SQL.

    Provides automated pipelines that handle the full flow of chunking, embedding, and storing document data.

    PLpgSQL
    Ver en GitHub↗5,802
  • docker/genai-stackAvatar de docker

    docker/genai-stack

    5,333Ver en GitHub↗

    Este proyecto es un stack de desarrollo contenedorizado y framework de aplicaciones para construir sistemas de generación aumentada por recuperación (RAG). Proporciona un sandbox de IA dockerizado que integra entornos de ejecución de modelos locales, grafos de conocimiento y almacenes vectoriales para permitir la creación de chatbots contextuales. El stack se distingue por su almacén vectorial basado en grafos, que combina grafos de conocimiento estructurados con índices vectoriales para la recuperación de datos tanto semánticos como estructurales. Permite el alojamiento de modelos locales con aceleración de CPU o GPU, facilitando tareas generativas sin depender de APIs externas en la nube. El framework cubre una amplia gama de capacidades, incluyendo el procesamiento e indexación de documentos PDF, la orquestación de servicios de IA basados en contenedores y la implementación de generación de respuestas fundamentadas. Incluye una interfaz de chat basada en web con streaming de respuestas incremental y una interfaz estandarizada para cambiar entre diferentes proveedores de modelos de lenguaje. El entorno se inicializa mediante orquestación de contenedores para desplegar rápidamente un stack preconfigurado de modelos y bases de datos.

    Provides an automated pipeline to chunk, embed, and load external documents into a vector-graph database.

    Python
    Ver en GitHub↗5,333
  • brianpetro/obsidian-smart-connectionsAvatar de brianpetro

    brianpetro/obsidian-smart-connections

    5,195Ver en GitHub↗

    Este proyecto es un plugin de base de conocimientos y gestor de contexto RAG que utiliza una interfaz de base de datos vectorial local para permitir la búsqueda semántica y el mapeo de relaciones. Transforma texto en vectores numéricos para encontrar notas y extractos semánticamente relacionados basándose en el significado conceptual en lugar de coincidencias de palabras clave. El sistema se diferencia mediante un visualizador de grafos semánticos que mapea las notas en clústeres para revelar conexiones conceptuales. También cuenta con un gestor de contexto capaz de agrupar notas y extractos locales en paquetes reutilizables para proporcionar bases factuales fundamentadas para conversaciones con modelos de lenguaje grandes. La herramienta cubre una amplia gama de capacidades, incluyendo consultas de conocimiento en lenguaje natural, ejecución de flujos de trabajo automatizados para la creación de notas y la capacidad de enrutar prompts entre modelos de IA locales y basados en la nube. Proporciona varias interfaces de descubrimiento, como indicadores de contenido relacionado en línea y un panel inferior para mostrar documentos similares durante el proceso de edición.

    Surfaces semantically similar excerpts based on the active document to discover relevant prior work.

    JavaScriptchatgptclaudeembeddings
    Ver en GitHub↗5,195
  • alibaba/zvecAvatar de alibaba

    alibaba/zvec

    5,198Ver en GitHub↗

    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

    Provides workflows for indexing single or batch documents containing dense and sparse vectors.

    C++ann-searchembedded-databaserag
    Ver en GitHub↗5,198
  • facebookresearch/drqaAvatar de facebookresearch

    facebookresearch/DrQA

    4,468Ver en GitHub↗

    DrQA es un sistema de respuesta a preguntas de dominio abierto que recupera documentos relevantes de un gran corpus y extrae respuestas específicas a preguntas en lenguaje natural. Se implementa como un sistema de red neuronal que combina un motor de recuperación de documentos con un modelo de comprensión de lectura automática. El sistema utiliza una arquitectura de pipeline de dos etapas. Un recuperador de documentos de grano grueso utiliza vectores de palabras ponderados para identificar documentos potenciales, mientras que un modelo de comprensión de lectura automática de grano fino identifica y extrae el fragmento de texto exacto que contiene la respuesta. El proyecto también incluye un generador de datasets de procesamiento de lenguaje natural supervisado. Esta herramienta crea ejemplos de entrenamiento haciendo coincidir pares de pregunta-respuesta con párrafos de apoyo utilizando heurísticas de cadena automatizadas. La base de código proporciona capacidades adicionales para el procesamiento de texto y tokenización para preparar texto sin procesar para el procesamiento de redes neuronales.

    Uses vector embeddings for semantic document retrieval within a large unstructured corpus.

    Python
    Ver en GitHub↗4,468
Ant.12Siguiente
  1. Home
  2. Data & Databases
  3. Database Management Systems
  4. Database Engines
  5. Vector Databases
  6. Vector Document Indexing

Explorar subetiquetas

  • Document Chunking and Embedding PipelinesAutomated pipelines that split documents into chunks, generate vector embeddings, and store them in a vector database for retrieval. **Distinct from Vector Document Indexing:** Distinct from Vector Document Indexing: focuses on the full ingestion pipeline (chunking + embedding + storage) rather than just the indexing step.
  • Semantic Document RetrievalFetching relevant documents from an index using vector embeddings for semantic similarity. **Distinct from Vector Document Indexing:** Distinct from Vector Document Indexing: focuses on the retrieval step using embeddings, not the indexing workflow.