← All insightsCareer

Vector Databases interview questions, with answers

Nir Geier, CodeWizard · 20 August 2025 · 3 min read · Beginner

Preparing for a DevOps interview that covers Vector Databases? These questions come up again and again - here are strong, concrete answers.

Q: What is Vector Databases and why use it?

Vector databases store high-dimensional embeddings and retrieve the nearest neighbours to a query vector, powering retrieval-augmented generation (RAG), semantic search and recommendations. Popular options include Pinecone, Weaviate and Qdrant.

  • Fast approximate nearest-neighbour search at scale
  • The retrieval layer that grounds LLMs in your data
  • Metadata filtering for hybrid semantic + keyword search

Q: What are the best practices you follow?

  • Keep the same embedding model for index and query
  • Combine vector search with metadata filters (hybrid search)
  • Version your embeddings and plan re-indexing

Q: What mistakes have you seen?

  • Mismatched embedding model between indexing and querying
  • Ignoring metadata filtering, so results lack precision
  • No re-embedding strategy when the model changes

Q: Show a basic configuration

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'})])

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