Hero Banner

Top Builders

Explore the top contributors showcasing the highest number of app submissions within our community.

Qdrant

Qdrant is a high-performance, open-source vector database and search engine designed specifically for vector similarity search. Written in Rust, Qdrant offers fast and reliable performance even under high load, making it an ideal choice for applications that demand speed and scalability. With Qdrant, you can turn your embeddings or neural network encoders into powerful, full-fledged applications for a wide range of use cases including matching, search, recommendation, and complex operations on large datasets.

Qdrant's comprehensive API and extended filtering support make it well-suited for various applications, including faceted search, semantic-based matching, and hybrid search combining vector similarity with keyword matching. The platform offers both self-hosted and managed cloud solutions, providing flexibility for different deployment scenarios.

General
Release DateOctober 29, 2021
AuthorQdrant
TypeVector Database & Search Engine
LanguageRust
LicenseApache License 2.0
Latest Version1.15.x (July 2025)
GitHub Stars19,000+ (as of 2025)

Core Features

High-Performance Vector Search

  • HNSW (Hierarchical Navigable Small World) indexing algorithm
  • Sub-millisecond search latency for millions of vectors
  • Handles billions of vectors with horizontal scaling
  • SIMD hardware acceleration for optimal CPU utilization

Advanced Quantization Techniques

  • Scalar Quantization: Reduces memory usage by 4x with minimal accuracy loss
  • Binary Quantization: Up to 32x compression with 40x speed improvement
  • Product Quantization: Higher compression ratios for high-dimensional vectors
  • 1.5-bit and 2-bit Quantization: New compression options balancing efficiency and accuracy
  • Asymmetric Quantization: Different encoding for stored vectors vs. queries

Hybrid Search Capabilities

  • Dense Vectors: Traditional semantic similarity search using neural embeddings
  • Sparse Vectors: Keyword-based search with neural network weighting (BM25, SPLADE)
  • Combined Search: Unified queries across both dense and sparse vectors in single collections
  • BM42 Algorithm: Proprietary hybrid search combining vector and keyword methods

Comprehensive Filtering & Payload Support

  • Rich JSON payload attachment to vectors
  • Advanced filtering conditions (must, should, must_not clauses)
  • Geo-location, numerical ranges, and full-text filtering
  • Custom business logic implementation on top of similarity matching

Latest Enhancements (2024-2025)

Qdrant 1.15.x (July 2025)

  • Smarter Quantization: Enhanced 1.5-bit and 2-bit quantization options
  • Advanced Full-Text Filtering: Improved text search capabilities
  • Performance Optimizations: Better resource utilization and faster processing

Qdrant 1.14.x (April 2025)

  • Score-Boosting Reranker: Blend vector similarity with custom rules and context
  • Incremental HNSW Indexing: Build indexes gradually as data arrives
  • Optimized Batch Search: Parallel processing for large query batches
  • Memory Optimization: Reduced RAM usage for large datasets

Qdrant Cloud Inference (July 2025)

  • Unified Embedding Generation: Generate, store, and index embeddings in single API calls
  • Multimodal Support: Text and image embedding models integrated natively
  • Supported Models: MiniLM, SPLADE, BM25, Mixedbread Embed-Large, CLIP
  • Free Tier: 5 million tokens per model monthly, unlimited BM25 tokens

Deployment Options

Self-Hosted (Open Source)

  • Full control over infrastructure and data
  • Horizontal scaling through sharding and replication
  • Zero-downtime rolling updates and dynamic scaling
  • Available on GitHub with comprehensive documentation

Qdrant Cloud (Managed Service)

  • Fully managed SaaS solution across AWS, Google Cloud, and Azure
  • Automatic scaling, monitoring, and maintenance
  • Built-in backups and disaster recovery
  • Simple setup with production-ready clusters in minutes

Hybrid Cloud

  • Deploy across diverse environments for performance and compliance
  • Integrate on-premise and cloud infrastructure
  • Maintain data residency requirements while leveraging cloud benefits

Private Cloud

  • Full Kubernetes-based deployment on any infrastructure
  • Complete control and customization for enterprise requirements
  • Air-gapped deployments for maximum security

Key Use Cases

Retrieval-Augmented Generation (RAG)

  • Semantic search over knowledge bases and documents
  • Context retrieval for large language models
  • Enterprise knowledge management and Q&A systems

Recommendation Systems

  • Product recommendations based on user behavior
  • Content discovery and personalization
  • Similar item matching across catalogs

Multimodal Search

  • Combined text and image search capabilities
  • Video content indexing and retrieval
  • Cross-modal similarity matching

Enterprise Search

  • Semantic document search with filtering
  • Compliance and regulatory document retrieval
  • Customer support knowledge bases

Anomaly Detection

  • Outlier detection in high-dimensional data
  • Fraud detection and security monitoring
  • Quality control and process optimization

Technical Specifications

Performance Characteristics

  • Throughput: Up to 10,000+ queries per second
  • Latency: Sub-millisecond search response times
  • Scale: Billions of vectors with horizontal scaling
  • Memory Efficiency: Up to 97% RAM reduction with quantization

Supported Distances

  • Cosine similarity
  • Euclidean (L2) distance
  • Dot product
  • Manhattan (L1) distance

Integration Ecosystem

  • Embeddings: OpenAI, Cohere, Hugging Face, Sentence Transformers
  • Frameworks: LangChain, LlamaIndex, Haystack
  • Languages: Python, Rust, JavaScript, Go, .NET
  • Platforms: Docker, Kubernetes, cloud providers

Recent Achievements

  • 250+ million installs across all open-source packages
  • Featured in The Forrester Waveâ„¢: Vector Databases, Q3 2024
  • Named one of Europe's top 10 startups in Sifted's 2025 B2B SaaS Rising 100
  • Powers AI applications at Tripadvisor, HubSpot, and Deutsche Telekom
  • Active community of 6,000+ members on Discord

Tutorials

Great tutorials on how to build with Qdrant

Resources

Getting Started

Community & Support

Qdrant represents the cutting edge of vector database technology, combining high performance with developer-friendly APIs and comprehensive feature sets. Whether building semantic search, recommendation systems, or complex AI applications, Qdrant provides the infrastructure needed to scale from prototype to production with confidence.

Edit on GitHub

Qdrant AI technology page Hackathon projects

Discover innovative solutions crafted with Qdrant AI technology page, developed by our community members during our engaging hackathons.

Secure-AI

Secure-AI

LLMs have recently adopted persistent memory to provide models with better user knowledge and personalisation. However, this introduces a new vector for adversarial manipulation. This report investigates Memory Injection, a threat model where adversaries exploit indirect prompt injection within web content to poison an agent's long-term memory. Employing user manipulation scenarios, we show that memory attacks, should they succeed, are effective at changing model behaviour towards the user, often more so than a direct system prompt. Hence, this highlights the need for more robust evaluations of memory updates in agentic memory systems.

AI Powered Java Project Security Scanner

AI Powered Java Project Security Scanner

" CodeAtlas is an advanced, AI-driven code analysis platform designed to bring clarity and security to Java repositories. By combining static analysis (AST), vector embeddings (Qdrant), and Large Language Models (Claude & Gemini), CodeAtlas creates a deep semantic understanding of your codebase. Key features include: Security Vulnerability Detection: Identifies OWASP Top 10 issues with AI-driven context. Interactive Graph Visualization: Explores complex call graphs and dependencies via a React Flow-based ""Cyber-Noir"" interface. AI Chat Assistant: Enables developers to query their codebase using natural language (RAG). Real-time Monitoring: Tracks scan progress step-by-step with Server-Sent Events (SSE). Built with a modern stack featuring React 19, FastAPI, and PydanticAI, CodeAtlas transforms static code into a living, queryable knowledge base, making security audits and onboarding effortless."

FIS AEGIS

FIS AEGIS

Financial Intelligence Swarm (FIS) Compliance, Risk, and Anti-Fraud Architecture for the Post-ISO 20022 Era AI-powered fraud detection platform using a Prosecutor-Skeptic-Judge debate pattern for AML/CFT investigations. Features LangGraph Agentic Architecture: Multi-agent debate system with Prosecutor (finds fraud), Skeptic (finds alibis), and Judge (renders verdict). ISO 20022 Support: Parse pacs.008, pain.001, camt.053 XML messages using xsdata and xmltodict. Reified Graph Intelligence: Neo4j-powered hidden link detection and fraud ring analysis using a "Reified Transaction Model" where transactions are first-class nodes. Semantic Search: Qdrant vector search for document evidence (PDFs parsed via Docling) and fuzzy sanctions screening. Behavioral Analysis: Mem0-based entity profiling and drift detection to track user behavior over time. EU AI Act Compliant: Article 13 transparency and explainability built-in with human-in-the-loop checkpoints. Generative UI Dashboard: Next.js 16 frontend with streaming investigation updates using Vercel AI SDK.

Prometheus Siren Autonomous Zero Day Defense

Prometheus Siren Autonomous Zero Day Defense

In 2025, the financial sector faced a staggering 742 million attacks in just six months, a 60% surge that places platforms like Deriv at the center of an existential digital war. Deriv’s leadership has identified a critical matrix of risks, including account takeovers, API gaps, and P2P fraud. Traditional security is failing because it is reactive; by the time an analyst patches a breach days later, the damage is done. Prometheus-Siren flips this paradigm by shifting from human-speed defense to AI-driven autonomy. Built on a stack of Qdrant, Gemini AI, and XGBoost, the system identifies the semantic intent of an attack rather than just matching old signatures. It catches novel SQL injections and obfuscated payloads in real-time. Using Kubernetes sidecars, it makes blocking decisions in sub-seconds, maintaining Deriv's strict <500ms latency. Most importantly, it self-heals: Gemini AI generates and deploys validated patches in under an hour—a process that usually takes days. Once a threat is identified, "global immunity" is shared across all Deriv instances within seconds. With a 94.6% detection accuracy and a 400% ROI in Year 1, Prometheus-Siren transforms security from a massive cost center into a self-paying asset. It reduces the zero-day vulnerability window from days to seconds, ensuring that Deriv stays ahead of attackers while slashing operational costs by $500K annually.

CodeEcho Voice Agentic AI Developer with RAG

CodeEcho Voice Agentic AI Developer with RAG

CodeEcho is an Agentic AI-driven development assistant that enables developers to build software using voice commands, multi-agent orchestration, and retrieval-augmented code intelligence. It solves the problem of slow development, context switching, and fragmented tooling by unifying code generation, RAG-based understanding, refactoring, testing, and quality metrics into one seamless workflow. Users can generate code hands-free, perform AI-assisted code reviews, run and compare multiple tests, track cyclomatic complexity and maintainability, and view real-time project health. CodeEcho integrates directly with IDEs like VS Code and supports GitHub PR automation. It is designed for developers, students, and teams who want to accelerate development using IBM watsonx-powered agentic workflows.

KeySync Lite

KeySync Lite

KeySync Lite is an AI-first lead intelligence system built for Dubai and GCC real estate brokerages flooded with WhatsApp, email, and portal inquiries. Today, agents manually sort through hundreds of mixed-quality leads, often responding to low-value renters before high-intent buyers — resulting in lost opportunities and inconsistent customer experiences. KeySync Lite solves this by using Gemini-powered extraction, multi-agent personas, and Qdrant vector search to analyze each incoming message, understand buyer intent, and score the lead from 0 to 10. Low and medium-priority leads are answered instantly by the AI using the firm’s brand tone, while high-priority leads are safely escalated to managers to avoid losing serious buyers or investors. The system includes a real-time broker dashboard, a WhatsApp-style buyer view, and a transparent AI Pipeline that shows every step: extraction, retrieval, persona routing, scoring, and property recommendations. Qdrant serves as the core memory layer, storing Dubai market intelligence, firm-specific knowledge, and multi-modal property data. KeySync Lite helps brokerages cut response times from hours to seconds, protect VIP clients, reduce operational workload, and create a scalable AI-driven front office for the GCC real estate market.