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

# Deploy Qdrant

> Set up Qdrant and connect its dependencies with Spring Winter.

## Deploy with an agent

Copy agent prompt

Help me deploy Qdrant. Read [https://docs.springwinter.dev/deploy/open-source/qdrant](https://docs.springwinter.dev/deploy/open-source/qdrant.md), [https://qdrant.tech/documentation/installation/](https://qdrant.tech/documentation/installation/), and [https://docs.springwinter.dev/api-reference/agents](https://docs.springwinter.dev/api-reference/agents.md). Fetch the public OpenAPI specification from my Spring Winter origin. Use my local SPRINGWINTER\_TOKEN or existing SPRINGWINTER\_API\_TOKEN. Keep credentials out of chat, logs and source.

Confirm my project, AWS connection, Region and budget. Pin a release. Check its required services, container port, health path, network access and durable storage. Data requirements for this deployment: Qdrant is the database. You do not need PostgreSQL or MySQL.

1. Choose Qdrant Cloud or a persistent container host with supported block storage and a POSIX filesystem. Attach durable storage at /qdrant/storage before starting a self-hosted instance.
2. Configure TLS and an API key. Use the private HTTP endpoint on port 6333 for REST or port 6334 for gRPC when your network supports it. Keep intra-cluster ports private if using a cluster.
3. Store the endpoint and scoped API key in the Spring Winter client application’s runtime configuration. Qdrant REST clients authenticate with the api-key header.
4. Start and verify Qdrant first. Create or initialize collections, then deploy the Spring Winter application that indexes and queries them.

Show me the planned resources, database and migration order, secret names and estimated cost. Identify components that require separate hosting. Wait for approval before making changes. Include any planned restart, task replacement or restore in that approval. Use documented Spring Winter operations and wait for each workflow to finish. Index a few sample vectors, query them with a read-only key, and verify the collection persists after a restart. Report resource links and anything you could not verify.

## Before you start

[Connect your AWS account](https://docs.springwinter.dev/connect-aws.md) and choose a project. Review the [upstream deployment instructions](https://qdrant.tech/documentation/installation/) for the release you plan to pin.

## Data dependencies

Qdrant is the database. You do not need PostgreSQL or MySQL.

## Deployment order

1. Choose Qdrant Cloud or a persistent container host with supported block storage and a POSIX filesystem. Attach durable storage at `/qdrant/storage` before starting a self-hosted instance.
2. Configure TLS and an API key. Use the private HTTP endpoint on port 6333 for REST or port 6334 for gRPC when your network supports it. Keep intra-cluster ports private if using a cluster.
3. Store the endpoint and scoped API key in the Spring Winter client application’s runtime configuration. Qdrant REST clients authenticate with the `api-key` header.
4. Start and verify Qdrant first. Create or initialize collections, then deploy the Spring Winter application that indexes and queries them.

Use [Runtime variables](https://docs.springwinter.dev/concepts/environment-variables.md) for runtime credentials. For a [Spring Winter web server](https://docs.springwinter.dev/deploy/web-servers.md), set an app-supported health path that returns HTTP 200 without credentials. Check **History** before running the application check.

## Verify the deployment

Index a few sample vectors, query them with a read-only key, and verify the collection persists after a restart.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.