Home
AWS Marketplace AMI

Qdrant Vector Database

Production-ready vector database for AI/RAG applications on Ubuntu 22.04

Qdrant Latest Stable OS Ubuntu 22.04 Auto-Tuning Enabled

Quick Start Guide

Get your Qdrant vector database up and running in minutes

1

Connect to Your Instance

SSH into your instance using the key pair you selected during launch

ssh -i your-key.pem ubuntu@your-instance-ip
2

View Your Credentials

API keys are auto-generated on first boot. View them securely

sudo cat /opt/flowops/credentials.txt
3

Access the Dashboard

Open the Qdrant web dashboard in your browser

https://your-instance-ip:6333/dashboard
4

Test the API

Verify Qdrant is running with a simple API call

curl -k -H "api-key: YOUR_API_KEY" \ https://localhost:6333/collections

AMI Details

Everything you need to know about your Qdrant instance

Included Components

  • Qdrant Vector Database (latest stable)
  • Auto-tuning based on instance size
  • TLS/HTTPS encryption
  • Prometheus metrics endpoint
  • S3 backup integration
  • Separate 20GB data volume

Ports & Endpoints

  • Port 6333: REST API + Dashboard
  • Port 6334: gRPC API
  • /healthz: Health check
  • /metrics: Prometheus metrics
  • /dashboard: Web UI

Data & Configuration Paths

# Credentials and API keys /opt/flowops/credentials.txt # Qdrant configuration /etc/qdrant/config.yaml # Data directory (separate EBS volume) /qdrant-data/storage # Collections and vectors /qdrant-data/snapshots # Local snapshots # Service management sudo systemctl status qdrant sudo systemctl restart qdrant sudo journalctl -u qdrant -f

Security Notice

API keys are auto-generated on first boot and stored in credentials.txt. Keep them secure and never share them publicly. The Read-Only key can only perform search operations.

Connect Your Application

Quick example using the official Qdrant Python client

# Install the client pip install qdrant-client # Connect to your Qdrant instance from qdrant_client import QdrantClient from qdrant_client.models import VectorParams, Distance client = QdrantClient( url="https://your-instance-ip:6333", api_key="your-admin-api-key", https=True ) # Create a collection for OpenAI embeddings (1536 dimensions) client.create_collection( collection_name="documents", vectors_config=VectorParams(size=1536, distance=Distance.COSINE) ) # Insert vectors client.upsert( collection_name="documents", points=[ {"id": 1, "vector": [0.1] * 1536, "payload": {"text": "Hello world"}}, {"id": 2, "vector": [0.2] * 1536, "payload": {"text": "Qdrant is great"}} ] ) # Search for similar vectors results = client.search( collection_name="documents", query_vector=[0.15] * 1536, limit=5 )

Backups & Monitoring

Keep your data safe and monitor performance

S3 Backups

Setup automated snapshots to S3 with one command

sudo /opt/flowops/setup-backups.sh

Prometheus Metrics

Monitor collection sizes, queries, and performance

curl -k https://localhost:6333/metrics

Health Checks

Use health endpoints for load balancer integration

curl -k https://localhost:6333/healthz

Need Help?

Our UK-based support team is available 24/7 with guaranteed response within 24 hours

support@flowopsconsulting.co.uk