---
name: "opensearch-neural-search-plugin"
description: "Deploy dense vector embeddings, sparse neural encoders, and semantic search in OpenSearch."
metadata:
  author: "OpenSearch"
  version: "1.0.0"
  runtime_compatibility:
    - "codex"
    - "claude-code"
    - "cursor"
    - "windsurf"
triggers:
  - "setup opensearch neural search"
  - "create opensearch knn index"
  - "configure opensearch search pipeline"
permissions:
  fs_read: true
  fs_write: "workspace"
  shell_exec: false
  net_access: false
---

# OpenSearch Neural Search & Vector Clustering

Configures OpenSearch 2+: setting up ML Commons integration, deploying local neural model connectors, configuring neural search pipelines, k-NN index engines (nmslib, faiss, lucene), and hybrid score normalization.

## When to Invoke
Invoke this skill whenever you need to:
- setup opensearch neural search
- create opensearch knn index
- configure opensearch search pipeline

## Execution SOP & Rules
1. Enable k-NN in cluster settings: PUT _cluster/settings { 'persistent': { 'knn.algo_param.index_thread_qty': 4 } }.
2. Create k-NN index: PUT /my-index { 'mappings': { 'properties': { 'my_vector': { 'type': 'knn_vector', 'dimension': 384 } } } }.
3. Set up search pipeline with neural query clause to eliminate external embedding service dependencies.
4. Execute hybrid search queries combining standard match clauses with neural vector clauses.

## Verification Checklist
- Run local linting, syntax validation, and type-checks before reporting completion.
- Ensure all created or modified files adhere to workspace boundaries and avoid uncommitted secrets.
- Verify tests or build commands exit cleanly with return code 0.