---
title: "Vector databases | Skills We Assign For | Azendo"
description: "Vector databases and vector search — index choice, filtering, hybrid retrieval, plus the Azendo roles assigned for it."
url: "https://azendo.co/skills/vector-databases/"
---

[Skills](https://azendo.co/skills/) AI and machine learning 

# Vector databases.

Vector databases store embeddings and retrieve by similarity rather than exact match, using approximate nearest neighbour indexes. They underpin semantic search and retrieval-augmented generation.

## Where Vector databases fits on a long engagement.

The first question is usually whether a dedicated vector database is needed at all. Postgres with pgvector handles millions of vectors comfortably, and keeping vectors beside the relational data removes a system, a synchronisation path and a consistency problem. Dedicated databases earn their place at larger scale or under specific latency requirements.

Metadata filtering is where implementations differ most and where requirements are usually discovered late. Restricting a similarity search to one tenant, one date range or one document type is a common need, and systems handle it with very different efficiency — pre-filtering, post-filtering and hybrid approaches all have sharply different performance profiles.

## What an assigned team does with Vector databases.

Pure vector search is frequently worse than a hybrid of vector and keyword search. Exact terms — product codes, names, identifiers — are precisely what embeddings handle poorly, and they are often what users search for.

Combining both is usually the largest single improvement available to a retrieval system, and it is the kind of judgement scoped under [managed ai services](https://azendo.co/services/ai-engineering/).

## What we use Vector databases for.

* Starting in the database you already run pgvector where volumes allow, avoiding a second system and its sync path.
* Filtered similarity search Tenant and date restrictions applied efficiently rather than bolted on after retrieval.
* Hybrid keyword and vector retrieval Exact terms handled by keyword search, which embeddings are poor at.

## How Vector databases capacity is assigned.

Retrieval infrastructure is assigned inside AI capacity, starting from whether an additional system is genuinely required.

## Service lines it sits in

* [AI engineering](https://azendo.co/services/ai-engineering/)

Capacity is agreed as a committed monthly capacity across a discipline, not per skill.

## Related in ai and machine learning

* [vLLM — skill we assign for](https://azendo.co/skills/vllm/)
* [MLflow — skill we assign for](https://azendo.co/skills/mlflow/)
* [Kubeflow — skill we assign for](https://azendo.co/skills/kubeflow/)
* [OpenAI — skill we assign for](https://azendo.co/skills/openai/)
* [Anthropic — skill we assign for](https://azendo.co/skills/anthropic/)
* [Google Gemini — skill we assign for](https://azendo.co/skills/google-gemini/)
* [Meta Llama — skill we assign for](https://azendo.co/skills/meta-llama/)
* [Google and open-weight models — skill we assign for](https://azendo.co/skills/google-and-open-weight-models/)

## Tell us what your roadmap needs Vector databases for.

A service delivery manager replies with the disciplines we would assign, the monthly capacity and what the first month looks like.

[All skills we assign for](https://azendo.co/skills/)