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
·

46 repositorios

Awesome GitHub RepositoriesVector Stores

In-memory data structures specifically optimized for storing and querying high-dimensional embeddings.

Distinct from In-Memory Data Stores: Specifically for vector embeddings rather than general application state or transient data.

Explore 46 awesome GitHub repositories matching data & databases · Vector Stores. Refine with filters or upvote what's useful.

Awesome Vector Stores GitHub Repositories

Encuentra los mejores repositorios con IA.Buscaremos los repositorios que mejor coincidan usando IA.
  • garrytan/gbrainAvatar de garrytan

    garrytan/gbrain

    23,848Ver en GitHub↗

    gbrain is an agent framework and retrieval-augmented generation system that combines a durable task queue, a git-synced vector store, and a knowledge graph engine. It provides a foundation for building AI agents that interact with structured knowledge bases using the Model Context Protocol. The system synchronizes markdown files from a git repository into a database for high-performance semantic retrieval and creates typed edges between data pages by extracting entity references and wikilinks. It uses a database-backed queue to execute persistent background jobs and tool loops, ensuring relia

    Synchronizes markdown files from a Git repository into a database for fast semantic retrieval.

    TypeScript
    Ver en GitHub↗23,848
  • mayooear/ai-pdf-chatbot-langchainAvatar de mayooear

    mayooear/ai-pdf-chatbot-langchain

    16,543Ver en GitHub↗

    This project is a retrieval-augmented generation application designed to answer questions from uploaded PDF documents. It functions as a document question-answering engine and a streaming AI chat interface that provides responses backed by specific source citations. The system utilizes a state-machine workflow orchestrator to coordinate multi-step document ingestion and retrieval pipelines. This orchestration allows for step-by-step visualization and debugging of the process as documents are parsed and processed. The application manages the full lifecycle of document interaction, including P

    Stores numerical vector embeddings of PDF text chunks to enable efficient semantic similarity searching.

    TypeScriptagentsaichatbot
    Ver en GitHub↗16,543
  • n8n-io/self-hosted-ai-starter-kitAvatar de n8n-io

    n8n-io/self-hosted-ai-starter-kit

    14,997Ver en GitHub↗

    This project provides a dockerized AI workflow stack and orchestration templates for deploying a self-hosted AI environment. It establishes a localized infrastructure for building autonomous agents and model chains that process private data on-premises without external cloud dependencies. The environment is designed to support autonomous agent development, allowing models to dynamically select tools, execute shell commands, and interact with local file systems. It includes integrated vector database support to enable retrieval augmented generation and private document analysis. The stack cov

    Uses a locally hosted vector database as a knowledge store for document embedding and similarity retrieval.

    aiai-agentslow-code
    Ver en GitHub↗14,997
  • wasmedge/wasmedgeAvatar de WasmEdge

    WasmEdge/WasmEdge

    10,665Ver en GitHub↗

    WasmEdge is an extensible WebAssembly runtime that executes WebAssembly bytecode in a secure sandbox for cloud, edge, and embedded applications. It functions as a multi-language compiler, compiling applications written in Rust, JavaScript, Go, and Python into WebAssembly bytecode for sandboxed execution, and as a server-side JavaScript runtime that runs JavaScript programs with ES6 modules, NPM packages, and Node.js-compatible APIs. The runtime also serves as an AI inference runtime, executing AI models from JavaScript using WASI-NN plug-ins for inference tasks on personal devices and edge har

    Connects to Qdrant vector databases from within WebAssembly applications using a Rust driver.

    C++artificial-intelligencecloudcloud-native
    Ver en GitHub↗10,665
  • spring-projects/spring-aiAvatar de spring-projects

    spring-projects/spring-ai

    9,001Ver en GitHub↗

    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

    Offers a portable API to store and query vector embeddings across a wide range of database providers.

    Javaartificial-intelligencejavaspring-ai
    Ver en GitHub↗9,001
  • meta-llama/llama-stackAvatar de meta-llama

    meta-llama/llama-stack

    8,417Ver en GitHub↗

    Llama-stack es un stack de orquestación estandarizado y una puerta de enlace de API para IA generativa. Proporciona una capa de comunicación unificada y una interfaz consistente para desplegar, gestionar e interactuar con varios proveedores y despliegues de modelos de lenguaje de gran tamaño. El sistema funciona como un framework de agentes que gestiona la ejecución de herramientas y paquetes de habilidades versionados para automatizar tareas complejas. Incluye un sistema de procesamiento por lotes para manejar grandes volúmenes de solicitudes asíncronas mediante procesamiento offline y una interfaz de base de datos vectorial para almacenar y buscar documentos, permitiendo la generación aumentada por recuperación (RAG). El stack cubre capacidades de alto nivel, incluyendo la orquestación de agentes de IA, el despliegue de modelos y la estandarización de APIs de modelos para permitir el cambio entre proveedores sin reescribir el código de la aplicación.

    Ships a standardized interface to manage indexing and retrieval logic across vector stores to enable retrieval augmented generation.

    Python
    Ver en GitHub↗8,417
  • zilliztech/deep-searcherAvatar de zilliztech

    zilliztech/deep-searcher

    7,899Ver en GitHub↗

    Deep Searcher is an open-source retrieval-augmented generation engine that indexes private documents into a vector database and uses large language models to answer complex questions with cited reasoning. It functions as both a command-line interface and a web API research tool, enabling users to load data and generate comprehensive reports by combining indexed private information with LLM-powered analysis. The system distinguishes itself through a plugin-based provider architecture that supports multiple embedding models, LLM providers, vector databases, and file loaders as interchangeable c

    Stores document embeddings in Milvus and queries them with LLMs for grounded, cited answers.

    Pythonagentagentic-ragclaude
    Ver en GitHub↗7,899
  • langchain-ai/rag-from-scratchAvatar de langchain-ai

    langchain-ai/rag-from-scratch

    7,393Ver en GitHub↗

    This project is an educational implementation guide and framework for building Retrieval Augmented Generation systems. It provides a workflow for constructing a knowledge base pipeline that partitions documents, indexes them as vectors, and provides external context for language model prompts. The system features a document chunking framework that uses recursive character splitting to fit text into model context windows. It includes an in-memory vector store and a similarity search system that retrieves relevant text segments by calculating the mathematical distance between dense embedding ve

    Ships a local in-memory data structure for storing and retrieving document embeddings.

    Jupyter Notebook
    Ver en GitHub↗7,393
  • rethinkdb/horizonAvatar de rethinkdb

    rethinkdb/horizon

    6,738Ver en GitHub↗

    Horizon is a realtime API server and RethinkDB backend designed to push database changes instantly to front-end clients. It utilizes a WebSocket data streaming API to synchronize data between the database and user interfaces without requiring manual polling. The project integrates an OAuth identity manager for verifying user identities through third-party providers and a role-based access control system to define granular permissions for viewing or modifying database documents. It is delivered as a containerized backend framework, allowing the server and its dependencies to be deployed as a p

    Enables the removal of single or multiple documents from a collection using unique identifiers.

    JavaScript
    Ver en GitHub↗6,738
  • feast-dev/feastAvatar de feast-dev

    feast-dev/feast

    6,727Ver en GitHub↗

    Feast is an open-source feature store for machine learning that provides a central platform for defining, storing, and serving features across both training and inference workflows. It operates as a declarative system where feature definitions are written as code in Python files, synchronized to a central registry, and made available for low-latency online retrieval or point-in-time correct historical joins for training datasets. The project abstracts storage behind a pluggable architecture, allowing offline and online backends to be swapped without changing retrieval logic, and coordinates ma

    Enables PGVector support to store vector embeddings and retrieve the top-k closest vectors for similarity search.

    Pythonbig-datadata-engineeringdata-quality
    Ver en GitHub↗6,727
  • superagent-ai/superagentAvatar de superagent-ai

    superagent-ai/superagent

    6,631Ver en GitHub↗

    Superagent is an AI safety platform that protects applications from prompt injections, data leaks, and harmful outputs through built-in guardrails. It functions as a prompt injection detection system, data redaction tool, and red team testing tool, automatically removing personally identifiable information and protected health data from AI inputs and outputs while scanning image uploads with vision AI to detect visual prompt injection attacks before processing. The platform routes every prompt through a sequential pipeline of safety checks including injection detection, data redaction, and co

    Converts documents into vector embeddings and stores them in supported vector databases for semantic search.

    TypeScriptaianthropicguardrails
    Ver en GitHub↗6,631
  • hazelcast/hazelcastAvatar de hazelcast

    hazelcast/hazelcast

    6,570Ver en GitHub↗

    Hazelcast is a distributed data platform that combines an in-memory data grid with a stream processing engine to support real-time analytics and event-driven applications. It functions as a partitioned, distributed key-value store that replicates data across cluster nodes to provide low-latency access and high availability. The platform also serves as a distributed SQL query engine, allowing users to execute standard SQL statements against both in-memory datasets and external data sources. What distinguishes Hazelcast is its use of a distributed consensus subsystem to maintain strongly consis

    Maintains collections of vectors and associated metadata, allowing for key-based storage and retrieval of high-dimensional data points.

    Javabig-datacachingdata-in-motion
    Ver en GitHub↗6,570
  • wenda-llm/wendaAvatar de wenda-LLM

    wenda-LLM/wenda

    6,173Ver en GitHub↗

    Wenda es una plataforma de orquestación de LLM y motor de flujo de trabajo personalizado diseñado para gestionar múltiples backends de modelos de lenguaje a través de una interfaz unificada. Funciona como una puerta de enlace de IA autohospedada que permite la ejecución de secuencias de tareas complejas y flujos de conversación automatizados. El sistema utiliza plugins de JavaScript para orquestar flujos de trabajo y activar llamadas a APIs externas. Admite generación aumentada por recuperación (RAG) inyectando datos relevantes desde almacenes vectoriales y archivos offline en los prompts para aumentar la precisión de las respuestas. La plataforma está construida para despliegues en redes privadas, con gestión de acceso multiusuario y la capacidad de ejecutar modelos de código abierto cuantizados para ajustarse a restricciones de hardware específicas. También incluye seguimiento de historial basado en sesiones para mantener el contexto conversacional.

    Injects relevant data from vector stores and offline files into prompts to increase response accuracy.

    JavaScriptchatglm-6bchatrwkvrwkv
    Ver en GitHub↗6,173
  • l15y/wendaAvatar de l15y

    l15y/wenda

    6,173Ver en GitHub↗

    Wenda es una plataforma de infraestructura y gateway autohospedada para desplegar modelos de lenguaje dentro de redes internas para garantizar la privacidad y seguridad de los datos. Funciona como un hub centralizado y API gateway que unifica la comunicación entre varios ejecutores de modelos offline y proveedores de servicios online a través de una única interfaz. La plataforma incluye un orquestador de flujo de trabajo que utiliza scripts personalizados y llamadas a API para automatizar flujos de conversación complejos y configuraciones de modelos. También incorpora un sistema de recuperación que aumenta las respuestas del modelo con conocimiento externo recuperado de bases de datos vectoriales y motores de búsqueda. El sistema gestiona el estado y la memoria conversacional persistiendo el historial de diálogo en una base de datos para mantener el contexto a través de las sesiones de usuario. Utiliza un enfoque de integración modular para permitir la adición de nuevos proveedores de modelos sin modificar la aplicación principal.

    Uses vector databases to perform retrieval augmented generation by injecting relevant document snippets into prompts.

    JavaScript
    Ver en GitHub↗6,173
  • go-ego/riotAvatar de go-ego

    go-ego/riot

    6,059Ver en GitHub↗

    Riot es un motor de búsqueda distribuido y servidor de indexación basado en Go diseñado para indexación y recuperación de texto completo. Funciona como un sistema de recuperación que ordena documentos por relevancia utilizando algoritmos de ranking BM25, frecuencia de términos y frecuencia inversa de documento (TF-IDF). El motor proporciona soporte especializado para el idioma chino, con segmentación de texto concurrente y mapeo fonético Pinyin para hacer coincidir la entrada romanizada con los caracteres. Utiliza una arquitectura distribuida que emplea fragmentación (sharding) de índice basada en hash para equilibrar la carga de datos y el rendimiento a través de múltiples nodos de servidor. El sistema cubre una amplia gama de capacidades de búsqueda, incluyendo ejecución de consultas con lógica booleana, filtrado de proximidad y gestión del ciclo de vida del índice en tiempo real. Mantiene un índice de búsqueda rápido en memoria mientras utiliza almacenamiento respaldado por disco para la persistencia y durabilidad de los datos. Se incluyen herramientas de monitoreo para rastrear la utilización de memoria, disco y CPU en todo el entorno distribuido.

    Provides the ability to delete specific documents from the search index using their unique identifiers.

    Gogogolanggwk
    Ver en GitHub↗6,059
  • elastic/go-elasticsearchAvatar de elastic

    elastic/go-elasticsearch

    6,051Ver en GitHub↗

    The official Go client for Elasticsearch

    Removes a single document from a search index by its unique identifier.

    Go
    Ver en GitHub↗6,051
  • greptimeteam/greptimedbAvatar de GreptimeTeam

    GreptimeTeam/greptimedb

    5,968Ver en GitHub↗

    GreptimeDB is a distributed, open-source time-series database built for unified observability. It stores and queries metrics, logs, and traces together in a single columnar engine, supporting both SQL and PromQL for analysis. The database is designed as a Kubernetes-native operator with a decoupled compute and storage architecture, enabling horizontal scaling and multi-region deployment. What distinguishes GreptimeDB is its role as a multi-protocol ingestion gateway, accepting data through OpenTelemetry, Prometheus Remote Write, InfluxDB, Loki, Elasticsearch, Kafka, and MQTT protocols without

    Stores arrays of 32-bit floats with a fixed dimension specified at table creation for AI feature representation.

    Rustanalyticscloud-nativedatabase
    Ver en GitHub↗5,968
  • wassupjay/n8n-free-templatesAvatar de wassupjay

    wassupjay/n8n-free-templates

    5,892Ver en GitHub↗

    Este proyecto es una biblioteca de plantillas de flujo de trabajo de n8n preconfiguradas y planos estructurales diseñados para automatizar procesos de negocio y tareas de IA. Proporciona una colección de archivos JSON que pueden importarse a un motor de flujo de trabajo para desplegar secuencias de automatización, incluyendo configuraciones especializadas para integrar bases de datos vectoriales y modelos de lenguaje grandes. La colección se centra en el desarrollo de agentes de IA conscientes del contexto, utilizando buffers de memoria y sistemas de recuperación para crear tuberías inteligentes de generación y recuperación de datos. Incluye planos dedicados para la generación aumentada por recuperación (RAG) y búsqueda semántica a través de integraciones de almacenes vectoriales. Las plantillas cubren una amplia gama de áreas de capacidad, incluyendo análisis de datos impulsado por IA, tuberías de contenido para gestión de medios y redes sociales, y automatización específica de la industria para sectores como legal, salud, bienes raíces y comercio electrónico. También proporciona flujos de trabajo de utilidad para la automatización de tareas financieras, análisis de reclutamiento de RRHH y monitoreo de infraestructura.

    Provides specialized configurations for implementing retrieval augmented generation by connecting language models to vector stores.

    automationautomation-templatesintegration
    Ver en GitHub↗5,892
  • helicone/heliconeAvatar de Helicone

    Helicone/helicone

    5,830Ver en GitHub↗

    Helicone is an AI gateway and observability platform designed to intercept, manage, and monitor interactions with large language models. By acting as a reverse-proxy, it provides a centralized layer for routing requests across multiple AI providers, allowing developers to maintain consistent application logic while gaining deep visibility into model performance, usage, and costs. The platform distinguishes itself through a robust suite of traffic management and prompt engineering tools. It enables policy-driven control, including automatic failover between providers, rate limiting, and edge-b

    Records interactions with vector databases to monitor data retrieval and storage operations.

    TypeScript
    Ver en GitHub↗5,830
  • openai-php/clientAvatar de openai-php

    openai-php/client

    5,805Ver en GitHub↗

    Este proyecto es un cliente de API PHP y SDK para integrar servicios de OpenAI en aplicaciones PHP. Sirve como una librería de integración y wrapper para interactuar con modelos de lenguaje grandes para generar texto, imágenes y audio mediante llamadas a la API REST. La librería proporciona orquestación especializada para asistentes de IA, gestionando hilos de conversación y almacenes vectoriales. También incluye herramientas para el ajuste fino (fine-tuning) de modelos personalizados, implementación de búsqueda semántica mediante embeddings de texto y procesamiento de audio para transcripción y síntesis. La superficie de capacidad cubre la moderación de contenido, gestión de archivos y el manejo de chats y completado de texto. Soporta la entrega de datos en tiempo real mediante streaming de eventos enviados por el servidor (SSE), procesamiento por lotes asíncrono y la verificación de firmas de webhook.

    Supports the organization and querying of high-dimensional embeddings in vector stores.

    PHP
    Ver en GitHub↗5,805
Ant.123Siguiente
  1. Home
  2. Data & Databases
  3. In-Memory Data Stores
  4. Vector Stores

Explorar subetiquetas

  • Cross-Store Vector SearchCapabilities to query embeddings across multiple independent vector stores from a single interface. **Distinct from Vector Stores:** Specifically addresses the aggregation of multiple vector stores rather than the storage structure of a single store
  • Data LoadersExtracts, transforms, and loads data from various sources into a vector database to support retrieval-augmented generation. **Distinct from Vector Stores:** Distinct from Vector Stores: focuses on the ETL process of loading data into vector stores, not the storage mechanism itself.
  • Document Deletions1 sub-etiquetaRemoves stored documents by their unique IDs or by a metadata-based filter expression. **Distinct from Vector Stores:** Distinct from Vector Stores: focuses on the deletion operation, not general storage or querying.
  • Document Embedding StoresStoring vector embeddings of document chunks in a feature store for later retrieval by similarity search. **Distinct from Vector Stores:** Distinct from Vector Stores: focuses on storing embeddings of document chunks specifically, not general vector storage.
  • Document WritersStores processed Document objects into a vector database for use in retrieval-augmented generation workflows. **Distinct from Vector Stores:** Distinct from Vector Stores: focuses on writing Document objects into vector stores, not general storage or querying.
  • Faiss Index StoresPersisting feature values as dense vectors in a Faiss index for efficient similarity search and nearest-neighbor lookups. **Distinct from Vector Stores:** Distinct from Vector Stores: focuses on using Faiss as the specific in-memory vector store backend, not general vector store data structures.
  • Filtered QueriesOffers a portable API across vector database providers, including a SQL-like metadata filter for precise retrieval. **Distinct from Vector Stores:** Distinct from Vector Stores: focuses on querying with metadata filters, not general storage or querying.
  • Fixed-DimensionStores arrays of 32-bit floats with a fixed dimension specified at table creation, enabling AI feature representation. **Distinct from Vector Stores:** Distinct from Vector Stores: specifies that vectors have a fixed dimension defined at table creation time, not general vector storage.
  • Git-SynchronizedVector stores that automatically synchronize their content with a Git repository of markdown files. **Distinct from Vector Stores:** Specifically adds Git-based synchronization to a vector store, unlike generic in-memory vector storage.
  • Local Vector Store Backends1 sub-etiquetaRunning and testing agents with a locally hosted vector database as a knowledge store for document retrieval. **Distinct from Vector Stores:** Distinct from Vector Stores: focuses on local-file-based vector persistence (e.g., ChromaDB) for agent knowledge, not general vector storage.
  • Metadata FiltersApplies portable SQL-like metadata filters to vector store queries for precise result retrieval. **Distinct from Vector Stores:** Distinct from Vector Stores: focuses on filtering query results by metadata, not general storage or querying.
  • Milvus Feature StoresMaterializing feature values into a Milvus vector database for low-latency online retrieval. **Distinct from Vector Stores:** Distinct from Vector Stores: focuses on using Milvus as the specific vector database backend for feature store materialization, not general in-memory vector data structures.
  • Multimodal StoresVector stores capable of managing mixed data modalities including tensors and structured text in one environment. **Distinct from Vector Stores:** Distinct from Vector Stores: emphasizes the ability to handle diverse data types beyond just simple embedding vectors.
  • Pinecone IntegrationsConnectors for using Pinecone as a cloud-based vector database for embedding storage. **Distinct from Vector Stores:** Distinct from Vector Stores: focuses specifically on the Pinecone cloud service implementation rather than general vector storage logic.
  • Product Catalog EmbeddingsVector stores that embed product descriptions for semantic retrieval to ground responses in factual knowledge. **Distinct from Vector Stores:** Distinct from Vector Stores: specifically stores product catalog embeddings for sales agent knowledge grounding.
  • Qdrant IntegrationsConnectors for using Qdrant as a vector database across local, Docker, or cloud environments. **Distinct from Vector Stores:** Distinct from Vector Stores: specifically targets the Qdrant engine's deployment modes and API.
  • Tabular-to-Vector IngestionConversion of tabular data frames into vector embeddings for storage in vector databases. **Distinct from Vector Stores:** Specifically targets the ingestion of pandas DataFrames into vector stores, not general offline persistence.
  • Vector Index MappersTools that map structured data frames to high-dimensional vector indices. **Distinct from Vector Stores:** Focuses on the mapping of data frames to indices rather than the store's internal architecture.
  • Vector Store Interaction MonitorsRecords timing and tracing data for vector store add, delete, and query operations, including similarity search details. **Distinct from Vector Stores:** Distinct from Vector Stores: focuses on monitoring and tracing vector store operations, not on the storage structure or querying of embeddings.
  • Vector Store OrchestratorsSystems that manage indexing strategies and retrieval logic across one or more vector databases. **Distinct from Vector Stores:** Distinct from Vector Stores: focuses on the orchestration and management of retrieval strategies rather than the storage itself.
  • Vector Store SynchronizationProcesses for clearing and regenerating all embeddings within a vector store to ensure data consistency. **Distinct from Vector Stores:** Focuses on the synchronization and regeneration process rather than the data structure of the store itself.
  • Vector-Store Augmented GenerationUsing vector databases to inject relevant document shards into model prompts. **Distinct from Vector Stores:** Combines vector storage with the RAG process of augmenting prompts, rather than just the storage mechanism.