vector-databases skillA
vector-databases is agent-read markdown (skill) from jnpiyush/agentx: Choose, configure, and operate vector databases for embeddings and hybrid search. Covers Azure AI Search, Pinecone, Qdrant, Weaviate, Milvus, pgvector, LanceDB, MongoDB Atlas Vector, Elasticsearch / OpenSearch kNN. Selection criteria, index types (HNSW, IVF, DiskANN), filters, hybrid (BM25 + vector), embedding model selection, sharding, cost..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Vector Databases > **Purpose**: Pick the right vector store, configure it for production, and avoid the failure modes that wreck retrieval quality. --- ## When to Use This Skill - Choosing a vector store (existing infra reuse vs purpose-built) - Sizing index, picking distance metric, configuring HNSW/IVF/DiskANN parameters - Implementing hybrid search (keyword + vector) with reranking - Adding metadata filters, namespaces, multi-tenancy - Operating at scale (sharding, replication, cost) --- ## Selection Decision Tree ``` Already running PostgreSQL? -> Start with pgvector + HNSW. Migrate later if you outgrow it. Already running Elastic / OpenSearch / Mongo? -> Use their native vector index. Pure managed vector DB needed? -> Pinecone (serverless), Qdrant Cloud, Weaviate Cloud Need Microsoft / Azure ecosystem fit? -> Azure AI Search (hybrid + reranker built-in) Local / embedded / OSS-only? -> LanceDB or Qdrant local Massive scale (>500M vectors), dense recall? -> Milvus + DiskANN, or Pinecone enterprise ``` --- ## Comparison (April 2026) | Store | Strength | Trade-off | |-------|----------|-----------| …
Read the whole file at its exact version.
How to install
mdr add jnpiyush/agentx/vector-databases@v1.0.0mdr add jnpiyush/agentx/vector-databases@sha256:d600bd3723d29414Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_elankird2vfoxhw7)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2026-09-15 | f17c505 | 5,706 B | A | view · diff |
| v1.0.0 | 2026-04-30 | 4f38ce8 | 5,704 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5706 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
jnpiyush/agentx · 16 stars · license Apache-2.0 · pushed 2026-09-21 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_elankird2vfoxhw7 GET https://markdownregistry.com/api/v1/resolve?ref=jnpiyush/agentx/vector-databases GET https://markdownregistry.com/api/v1/blob/d600bd3723d29414243c3e73d4a0d4373a2abb46243eabf5c5392157a83212d4
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.