awesome-repositories.comBlog
© 2026 Bringes Technology SRL·VAT RO45896025·hello@bringes.io
MCPBlogSitemapPrivacyTerms
Qdrant | Awesome Repository
← All repositories

qdrant/qdrant

0
View on GitHub↗
28,954 stars·2,046 forks·Rust·apache-2.0·0 viewsqdrant.tech↗

Qdrant

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Let's find more awesome repositories

Features

  • Vector Databases - Stores, indexes, and searches high-dimensional vectors alongside structured metadata for intelligent retrieval applications.
  • Vector Search Engines - Builds high-performance search applications that find relevant information by comparing mathematical representations of data.
  • Vector Search Engines - Manages high-dimensional vectors in production environments with associated metadata for efficient similarity search.
  • Hybrid Search Engines - Combines keyword-based retrieval with semantic search for comprehensive results.
  • Vector Indexing - Retrieves data quickly by indexing vectors using graph-based algorithms.
  • Vector Storage - Supports in-memory and memory-mapped storage for efficient vector data handling.
  • Vector Search - Identifies records by constraining search spaces using positive and negative vector pairs.
  • Distributed Search Engines - Provides a scalable infrastructure platform that manages large-scale data clusters for low-latency similarity search.
  • Hybrid Search - Combines approximate nearest neighbor algorithms with boolean metadata filtering to narrow search results.
  • Multivector Search - Retrieves documents with high accuracy using multiple token-level vectors per document.
  • Agent Memory Systems - Provides persistent storage for autonomous agents to retrieve context and past experiences during reasoning tasks.
  • Recommendation Engines - Suggests relevant records by calculating search spaces from provided example vectors.
  • Multi-Tenant Data Stores - Provides a robust storage architecture that isolates data partitions and metadata for multiple users while maintaining consistent performance.
  • Vector Collection Management - Organizes vectors into collections with shared dimensionality and distance metrics.
  • Write-Ahead Logging - Records all incoming data modifications in a sequential log to guarantee durability.
  • Distributed Consensus Protocols - Coordinates state changes across cluster nodes to ensure data consistency and high availability.
  • Managed Database Services - Automates infrastructure scaling, backups, and performance monitoring for managed database clusters.
  • Identity and Access Management - Manages account-level security and user membership within the cloud environment.
  • Transport Security - Secures data transmission between applications and servers using TLS encryption.
  • Metric Learning - Enables training of metric learning models to measure similarity between objects without requiring manually labeled datasets.
  • High-Throughput Indexing - Organizes massive volumes of unstructured data into searchable structures for rapid retrieval in production environments.
  • Memory-Mapped Indexing - Maps vector data directly into virtual address space for efficient access to large datasets.
  • Metadata Filtering - Restricts search results by matching specific values, sets, or text patterns including range and null-check conditions.
  • Query Interfaces - Executes similarity searches and random sampling tasks using a unified interface supporting filtering and pagination.
  • Segmented Storage Architectures - Partitions data into immutable segments that are merged in the background to optimize performance.
  • Semantic Search Engines - Retrieves relevant documents from a collection by embedding text queries on the fly using integrated machine learning models.
  • Production Deployment Tools - Supports deployment using managed cloud services, Kubernetes operators, or Helm charts for production-grade scaling.
  • API Authentication - Restricts database operations to specific access levels using secure API keys.
  • Identity and Access Management - Controls access to database API keys, cluster backups, and cluster metadata to secure managed cloud infrastructure.
  • AI Orchestration Frameworks - Embeds vector search capabilities into intelligent agents and orchestration tools to build production-ready applications.
  • Backup & Recovery - Provides automated snapshot creation and restoration to ensure data persistence and recovery.
  • Collection Schemas - Allows specification of dimensionality, distance metrics, and data types for optimized storage.
  • Full Text Search - Improves matching logic by searching for specific substrings, tokens, or phrases within text fields.
  • Multi-Tenancy Architectures - Manages large-scale datasets for multiple users while ensuring strict privacy and resource separation.
  • Storage Configuration - Configures in-memory or disk-based persistence to optimize filtering performance.
  • Vector Quantization - Applies scalar quantization to multi-vector representations to reduce memory usage.
  • Vector Search Middleware - Connects machine learning pipelines and AI agents to persistent storage for rapid information retrieval.
  • Client Libraries - Simplifies data operations and ensures reliable communication using official language-specific drivers.
  • Access Control Lists - Grants read or write access to cluster data via the management interface.
  • Cloud Authentication - Provides secure access to cloud resources via management keys in API headers.
  • Embedding Model Adaptations - Adapts standard dense embedding models for late interaction to improve retrieval performance.
  • Boolean Query Languages - Refines search criteria by creating complex expressions using nested logical operators like AND, OR, and NOT.
  • Data Partitioning - Isolates data by user or group using metadata to ensure tenant privacy.
  • Data Snapshotting - Backs up data by creating and downloading collection snapshots from individual cluster nodes.
  • Data Upsert Operations - Inserts new records or updates existing ones using unique identifiers to ensure data remains current.
  • Geospatial Databases - Enables filtering and querying of location-based information by combining coordinate constraints with vector similarity.
  • Multi-Vector Retrieval Systems - Ranks and retrieves highly relevant documents by combining dense semantic embeddings with fine-grained late-interaction embeddings.
  • Multitenancy Isolation - Partitions records to ensure strict resource separation and data privacy.
  • Storage Engines - Optimizes storage performance by converting mutable data segments into immutable structures for hardware-level efficiency.
  • Cloud Infrastructure Automation - Automates cloud platform resources, including account management, cluster provisioning, and backup scheduling.
  • Binary Communication Protocols - Uses high-performance binary serialization for internal and external data exchange.
  • gRPC Interfaces - Maximizes application throughput and minimizes latency using a high-performance binary protocol.
  • Credential Management - Generates database API keys with configurable expiration and granular permissions.
  • Search Optimization - Balances retrieval recall against query latency by tuning search-time parameters like graph exploration depth.

    • Qdrant is a high-performance vector similarity database designed to store, index, and search high-dimensional vectors alongside structured metadata. It functions as a distributed search engine that manages large-scale data clusters, providing low-latency retrieval and complex filtering capabilities. The system is built to serve as a specialized middleware layer, connecting machine learning pipelines and AI agents to persistent storage for intelligent information retrieval and recommendation tasks.

    The platform distinguishes itself through advanced retrieval techniques, including support for hybrid search that combines dense and sparse vectors, and multivector search that utilizes late interaction models for high-accuracy relevance scoring. It provides robust multi-tenant data isolation, allowing organizations to partition records and manage resources securely within a single cluster. To maintain performance at scale, the engine employs a segment-based storage architecture with asynchronous background optimization, ensuring that indexing and compaction processes do not block incoming queries.

    The system covers a broad capability surface, including comprehensive metadata filtering, geospatial search, and full-text indexing. It supports production-grade operations through distributed consensus protocols, write-ahead logging for durability, and memory-mapped indexing for efficient resource utilization. Administrative features include atomic collection aliasing, point-in-time snapshotting, and integrated tools for metric learning and search recall tuning.

    The project provides standardized REST and gRPC interfaces, supported by official client libraries for various programming environments. It is designed for flexible deployment, offering support for containerized local execution, Kubernetes-based production scaling, and infrastructure-as-code management via Terraform.