How do I install the Documentdb Vector Search skill?

Run npx skillmds@latest add azure/documentdb-vector-search in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Documentdb Vector Search safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Documentdb Vector Search?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Documentdb Vector Search free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.

Who published Documentdb Vector Search?

Azure (@azure) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Documentdb Vector Search by azure — Agent Skill

Name: Documentdb Vector Search
Author: Azure

Documentdb Vector Search

Vector search best practices for Azure DocumentDB using `cosmosSearch` — choosing between DiskANN / HNSW / IVF, creating indexes, tuning `lBuild` / `lSearch` / `maxDegree`, Product Quantization (up to 16,000 dims), half-precision (fp16) indexing, and normalizing embeddings for cosine similarity. Use when building RAG / semantic-search applications, creating a vector index, tuning recall/latency, or reducing vector-index memory footprint.

Azure 92c2a81 7 files · 12.7 KB Updated Sep 17, 2026

File contents

Vector Search — Azure DocumentDB (`cosmosSearch`)

Azure DocumentDB's native vector index type is cosmosSearch. Pick the sub-type by scale:

Index sub-type	Scale sweet spot	Tier
`vector-diskann` (recommended)	Up to 500k+ vectors	M30+
`vector-hnsw`	Up to ~50k vectors	M30+
`vector-ivf`	Under ~10k vectors	M10+

Similarity options: COS (cosine), L2 (Euclidean), IP (inner product).

Rules

vector-choose-index-type — Prefer DiskANN for production; use HNSW up to 50k, IVF under 10k.
vector-create-diskann-index — Create a vector-diskann index with correct dimensions, similarity, maxDegree, and lBuild.
vector-knn-query — Query with $search + cosmosSearch; tune lSearch and k; combine with pre-filters.
vector-product-quantization — Shrink high-dimensional vectors (up to 16,000 dims) while preserving recall.
vector-half-precision — Halve vector memory with fp16 indexing and minimal recall loss.
vector-normalize-embeddings — Normalize embeddings when using cosine similarity; store model + dimensions alongside vectors.

Frequently asked questions