> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/qdrant/qdrant/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction to Qdrant

> Qdrant is a high-performance vector search engine and database written in Rust, designed for production-ready semantic search, recommendations, and RAG applications.

# Introduction to Qdrant

Qdrant (read: *quadrant*) is a **vector similarity search engine and vector database** that provides a production-ready service with a convenient API to store, search, and manage points—vectors with additional payload data.

<Note>
  Qdrant is written in **Rust** 🦀, which makes it fast and reliable even under high load. See [benchmarks](https://qdrant.tech/benchmarks/) for performance comparisons.
</Note>

## What is Qdrant?

Qdrant is designed to turn embeddings or neural network encoders into full-fledged applications for matching, searching, recommending, and much more. It provides extended filtering support, making it useful for all sorts of neural-network or semantic-based matching, faceted search, and other advanced applications.

### Key Features

<CardGroup cols={2}>
  <Card title="Filtering & Payloads" icon="filter">
    Attach JSON payloads to vectors and filter based on values, including keyword matching, full-text filtering, numerical ranges, and geo-locations.
  </Card>

  <Card title="Hybrid Search" icon="magnifying-glass">
    Support for both dense and sparse vectors to combine semantic search with keyword-based matching (BM25/TF-IDF style).
  </Card>

  <Card title="Vector Quantization" icon="compress">
    Reduce RAM usage by up to 97% with built-in vector quantization while maintaining search quality.
  </Card>

  <Card title="Distributed Deployment" icon="network-wired">
    Horizontal scaling through sharding and replication with zero-downtime rolling updates.
  </Card>
</CardGroup>

## Core Capabilities

### High-Performance Architecture

Qdrant leverages modern hardware and software optimizations:

* **SIMD Hardware Acceleration**: Utilizes x86-x64 and ARM Neon architectures for better performance
* **Async I/O**: Uses `io_uring` on Linux to maximize disk throughput, even on network-attached storage
* **Write-Ahead Logging (WAL)**: Ensures data persistence with update confirmation, protecting against power outages
* **Query Planning**: Leverages payload indexes to optimize query execution strategies

<Info>
  The default WAL capacity is **32 MB** per segment with configurable segments ahead for optimal write performance.
</Info>

### Storage & Memory Management

Qdrant offers flexible storage options configured in `config/config.yaml`:

```yaml theme={null}
storage:
  # Where to store all the data
  storage_path: ./storage
  
  # Where to store snapshots
  snapshots_path: ./snapshots
  
  # If true - point payloads will not be stored in memory
  on_disk_payload: true
  
  # Write-ahead-log configuration
  wal:
    wal_capacity_mb: 32
    wal_segments_ahead: 0
```

### HNSW Index Configuration

The Hierarchical Navigable Small World (HNSW) algorithm powers Qdrant's fast approximate nearest neighbor search:

```yaml theme={null}
hnsw_index:
  # Number of edges per node (higher = more accurate, more space)
  m: 16
  
  # Number of neighbors during index building (higher = more accurate, slower build)
  ef_construct: 100
  
  # Threshold for full-scan vs HNSW (in KiloBytes)
  full_scan_threshold_kb: 10000
  
  # Store index on disk or in RAM
  on_disk: false
```

## Use Cases

### Semantic Search

Transform text embeddings into powerful search capabilities that understand meaning, not just keywords. Perfect for document search, knowledge bases, and content discovery.

### Recommendation Systems

Build sophisticated recommendation engines by finding similar items based on user preferences, product attributes, or behavioral patterns.

### Retrieval Augmented Generation (RAG)

Power AI applications by retrieving relevant context from vector databases to enhance LLM responses with accurate, domain-specific information.

<Accordion title="RAG Integration Example">
  Qdrant integrates seamlessly with popular RAG frameworks:

  * **LangChain**: Use Qdrant as a memory backend
  * **LlamaIndex**: Vector store integration for document indexing
  * **OpenAI ChatGPT**: Retrieval plugin for context enhancement
  * **Microsoft Semantic Kernel**: Persistent memory integration
</Accordion>

### Additional Applications

* **Chat Bots**: Context-aware conversational AI with memory
* **Matching Engines**: Find similar users, products, or content
* **Anomaly Detection**: Identify outliers in high-dimensional data
* **Image Search**: Visual similarity search for photos and media
* **Extreme Classification**: Multi-class, multi-label problems with millions of labels

## Architecture Overview

### Core Components

<Steps>
  <Step title="Collections">
    Named sets of points (vectors with payloads) that share the same vector configuration and indexing parameters.
  </Step>

  <Step title="Points">
    Individual entries consisting of a vector, unique ID, and optional JSON payload for metadata and filtering.
  </Step>

  <Step title="Segments">
    Internal data structures that optimize storage and search. Qdrant automatically manages segment optimization.
  </Step>

  <Step title="Shards">
    Horizontal partitions of collections enabling distributed deployment and scaling.
  </Step>
</Steps>

### Distance Metrics

Qdrant supports multiple distance metrics for vector similarity:

* **Dot Product**: Best for normalized vectors (cosine similarity)
* **Cosine**: Measures angle between vectors
* **Euclidean**: L2 distance for spatial proximity
* **Manhattan**: L1 distance for specific use cases

## API Interfaces

### REST API

Full-featured HTTP API with OpenAPI 3.0 specification:

* **Port**: 6333 (default)
* **Documentation**: [https://api.qdrant.tech/](https://api.qdrant.tech/)
* **Format**: JSON request/response

### gRPC API

High-performance binary protocol for production workloads:

* **Port**: 6334 (default, optional)
* **Use Case**: Faster searches with lower latency
* **Features**: Streaming support, efficient serialization

<Warning>
  By default, Qdrant starts without authentication. Always enable `api_key` in production and use TLS encryption.
</Warning>

## Integrations

Qdrant integrates with the most popular AI and ML frameworks:

* **Cohere**: Embeddings integration
* **Haystack**: Document store backend
* **LangChain**: Vector memory backend
* **LlamaIndex**: Vector store integration
* **OpenAI**: ChatGPT retrieval plugin
* **Microsoft Semantic Kernel**: Persistent memory

## Getting Started

The fastest way to get started with Qdrant is using Docker:

```bash theme={null}
docker run -p 6333:6333 qdrant/qdrant
```

Then connect with any client library:

```python theme={null}
from qdrant_client import QdrantClient

qdrant = QdrantClient("http://localhost:6333")
```

<Tip>
  For local development and testing, the Python client offers an in-memory mode: `QdrantClient(":memory:")` or file-based mode: `QdrantClient(path="path/to/db")`.
</Tip>

## Official Client Libraries

Qdrant provides official client libraries for multiple programming languages:

* [Python](https://github.com/qdrant/qdrant-client)
* [JavaScript/TypeScript](https://github.com/qdrant/qdrant-js)
* [Rust](https://github.com/qdrant/rust-client)
* [Go](https://github.com/qdrant/go-client)
* [.NET/C#](https://github.com/qdrant/qdrant-dotnet)
* [Java](https://github.com/qdrant/java-client)

Community clients are also available for Elixir, PHP, Ruby, and more.

## Cloud Deployment

Qdrant is available as a fully managed cloud service at [Qdrant Cloud](https://cloud.qdrant.io/), including a **free tier** for development and testing.

## License

Qdrant is open-source software licensed under the Apache License, Version 2.0.

## Next Steps

<CardGroup cols={2}>
  <Card title="Quick Start" icon="rocket" href="/quickstart">
    Get Qdrant running in minutes with a practical example
  </Card>

  <Card title="Installation" icon="download" href="/installation">
    Explore all installation methods and deployment options
  </Card>
</CardGroup>