← All insightsAutomation

Automating Vector Databases from scratch

CodeWizard Academy · 21 August 2025 · 3 min read · Intermediate

Anything you do to Vector Databases twice should be automated. This walks the path from a manual install to a repeatable, pipeline-driven setup.

1. Install it reproducibly

bash
# Run Qdrant locally
docker run -p 6333:6333 qdrant/qdrant
pip install qdrant-client

2. Describe the desired state

Create a collection and upsert embeddings.

python
from qdrant_client import QdrantClient
from qdrant_client.models import Distance, VectorParams, PointStruct

c = QdrantClient('localhost', port=6333)
c.recreate_collection('docs', vectors_config=VectorParams(size=1536, distance=Distance.COSINE))
c.upsert('docs', [PointStruct(id=1, vector=emb, payload={'source': 'runbook'})])

3. Run it from CI

Run the vector DB as a service for integration tests.

yaml
services:
  qdrant:
    image: qdrant/qdrant
    ports: ['6333:6333']

Want senior help putting Vector Databases to work - or a team bootcamp on it? CodeWizard runs Israel's largest DevOps community and embeds named senior engineers with a transparent hours log. Book a free consult or explore the Academy.

Like where this is going?

Get hands-on help from the engineers who write these posts.

Book a free consult