What's Included
- Qdrant latest stable (Rust-powered)
- Web dashboard for visual management
- TLS/HTTPS encryption enabled
- API key authentication
- Auto-tuning based on instance size
- Prometheus metrics endpoint
- Separate 20GB EBS data volume
Step-by-Step Guide
Launch the AMI
Find "Qdrant FlowOps" on AWS Marketplace and launch with your preferred instance type.
# Recommended instance types:
# t3.medium (4GB) - Development, testing
# m5.large (8GB) - Small production
# r5.xlarge (32GB) - Production workloads
Access the Dashboard
Open the Qdrant web UI in your browser to manage collections visually.
# Get your API key
ssh -i your-key.pem ubuntu@your-instance-ip
sudo cat /opt/flowops/credentials.txt
# Access dashboard in browser:
https://your-instance-ip:6333/dashboard
# Test API
curl -k -H "api-key: YOUR_API_KEY" https://localhost:6333/collections
Create a Collection
Use the Python client to create a collection for your vectors.
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 collection for OpenAI embeddings
client.create_collection(
collection_name="documents",
vectors_config=VectorParams(size=1536, distance=Distance.COSINE)
)
Insert and Search with Filtering
Qdrant excels at filtered vector search - combine semantic similarity with metadata filters.
from qdrant_client.models import PointStruct, Filter, FieldCondition, MatchValue
# Insert documents with payloads
client.upsert(
collection_name="documents",
points=[
PointStruct(id=1, vector=[0.1]*1536,
payload={"text": "AI documentation", "category": "tech", "year": 2024}),
PointStruct(id=2, vector=[0.2]*1536,
payload={"text": "Legal contracts", "category": "legal", "year": 2023}),
]
)
# Search with filter - only tech documents from 2024
results = client.search(
collection_name="documents",
query_vector=[0.15]*1536,
query_filter=Filter(
must=[
FieldCondition(key="category", match=MatchValue(value="tech")),
FieldCondition(key="year", match=MatchValue(value=2024))
]
),
limit=5
)
Comparison
| Feature | Qdrant | Milvus | Pinecone |
|---|---|---|---|
| Language | Rust | Go | Proprietary |
| Web Dashboard | Built-in | Attu (separate) | Yes |
| Filtering | Excellent | Good | Good |
| Payload Indexing | Yes | Yes | Yes |
| Memory Efficiency | Excellent | Good | N/A |
Use Cases
- E-commerce product search
- Document retrieval systems
- Multi-tenant SaaS applications
- Real-time recommendations
- Content moderation
- Customer support search
Pricing
Our AMIs are available on AWS Marketplace with simple hourly pricing:
- Software: $0.10-0.15/hour (varies by product)
- EC2: Standard AWS pricing for your chosen instance
- Support: 24/7 included with guaranteed 24-hour response
Need Help?
Our UK-based support team is here to help you get the most out of your deployment. Email us at support@flowopsconsulting.co.uk for any questions.
Comments