landing_page/qdrant-landing/content/documentation/guides/installation.md

title, weight, aliases

title	weight	aliases
Installation	10	../install ../installation

Installation requirements

The following sections describe the requirements for deploying Qdrant.

CPU and memory

The CPU and RAM that you need depends on:

• Number of vectors
• Vector dimensions
• Payloads and their indexes
• Storage
• Replication
• How you configure quantization

Our Cloud Pricing Calculator can help you estimate required resources without payload or index data.

Storage

For persistent storage, Qdrant requires a block storage device with a proper file system such es ext4. This is especially important, if you mount an external volume inside the Qdrant container or if you use a Kubernetes Persistent Volume. Qdrant won't work on a file storage device, such as NFS, or an object storage such as S3.

The amount of storage depends on the size of your data.

If you offload vectors to disk, you also have to ensure that your disk storage is performant. You should at least use SSDs or NVMEs. HDDs are not recommended.

Networking

Each Qdrant instance opens 3 ports:

• 6333 - For the HTTP API, including the health and metric endpoints
• 6334 - For the gRPC API
• 6335 - For internal replication communication

All Qdrant instances in a cluster must be able to communicate with each other over these ports.

Each Qdrant instance must also allow incoming connections to ports 6333 and 6334 from the clients that will be using Qdrant.

Installation options

Qdrant can be installed in different ways depending on your needs:

For testing or development setups, you can run the Qdrant container or as a binary executable.

For production, you can use our Qdrant Cloud to run Qdrant either fully managed in our infrastructure or with Hybrid SaaS in yours.

If you want to run Qdrant in your own infrastructure, without any cloud connection, we recommend to install Qdrant in a Kubernetes cluster with our Helm chart, or to use our Qdrant Enterprise Operator

Production

Qdrant Cloud

The easiest way to run Qdrant for a production setup is to use the Qdrant Cloud, which provides fully managed Qdrant databases. Out-of-the-box you will get easy horizontal and vertical scaling, one click installation and upgrades, monitoring, logging and backup and disaster recovery. For more information, see the Qdrant Cloud documentention.

Kubernetes

You can use a ready-made Helm Chart to run Qdrant in your Kubeternetes cluster.

helm repo add qdrant https://qdrant.to/helm
helm install qdrant qdrant/qdrant

Read further instructions at qdrant-helm.

Qdrant Operator

We provide a Qdrant Enterprise Operator for Kubernetes installations. If you are interested in using it, please contact us.

Development

Docker

The easiest way to start using Qdrant for testing or development is to run the Qdrant container image. The latest versions are always available on DockerHub.

Make sure that Docker, Podman or the container runtime of your choice is installed and running. The following instructions use Docker.

Pull the image:

docker pull qdrant/qdrant

Run the container:

docker run -p 6333:6333 \
    -v $(pwd)/path/to/data:/qdrant/storage \
    qdrant/qdrant

With this command, you will start a Qdrant instance with the default configuration. It will store all data in the ./path/to/data directory.

By default, Qdrant uses port 6333, so at localhost:6333 you should see the welcome message.

To change the Qdrant configuration, you can overwrite the production configuration:

docker run -p 6333:6333 \
    -v $(pwd)/path/to/data:/qdrant/storage \
    -v $(pwd)/path/to/custom_config.yaml:/qdrant/config/production.yaml \
    qdrant/qdrant

Alternatively, you can use your own custom_config.yaml configuration file:

docker run -p 6333:6333 \
    -v $(pwd)/path/to/data:/qdrant/storage \
    -v $(pwd)/path/to/custom_config.yaml:/qdrant/config/custom_config.yaml \
    qdrant/qdrant \
    ./qdrant --config-path config/custom_config.yaml

For more information, see the Configuration documentation.

Docker Compose

You can also use Docker Compose to run Qdrant.

Here is an example compose file for a single node Qdrant cluster with custom configuration:

services:
  qdrant:
    image: qdrant/qdrant:v1.6.1
    restart: always
    container_name: qdrant
    ports:
      - 6333:6333
      - 6334:6334
    expose:
      - 6333
      - 6334
      - 6335
    configs:
      - source: qdrant_config
        target: /qdrant/config/production.yaml
    volumes:
      - ./qdrant_data:/qdrant_data

configs:
  qdrant_config:
    content: |
      log_level: INFO  

From source

Qdrant is written in Rust and can be compiled into a binary executable. This installation method can be helpful if you want to compile Qdrant for a specific processor architecture or if you do not want to use Docker.

Before compiling, make sure that the necessary libraries and the rust toolchain are installed. The current list of required libraries can be found in the Dockerfile.

Build Qdrant with Cargo:

cargo build --release --bin qdrant

After a successful build, the binary is available at ./target/release/qdrant.

Client libraries

In addition to the service itself, Qdrant provides client libraries for different programming languages. For a full list and documentation, see the Client libraries section.