# neo4j-genai-plugin-skill

A skill for calling Neo4j GenAI Plugin functions and procedures inside Cypher: embeddings, completion, chat, tokenization.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 812 installs · ★ 116
- Author: neo4j-contrib
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/neo4j-contrib/neo4j-skills/tree/HEAD/neo4j-genai-plugin-skill/SKILL.md
- Updated: 2026-10-21
- HTML: https://affpapa.org/en/nevibecode/skills/neo4j-genai-plugin-skill

## What it does

The skill documents `ai.text.*` calls inside Cypher queries: `ai.text.embed()`, `ai.text.embedBatch()`, `ai.text.completion()`, `ai.text.structuredCompletion()`, `ai.text.aggregateCompletion()`, `ai.text.chat()`, `ai.text.tokenCount()` and `ai.text.chunkByTokenLimit()`. It replaces the deprecated `genai.vector.encode()`. Useful when you build GraphRAG in pure Cypher, embed nodes during ingestion, or pull structured maps out of a model response.

Every `ai.*` function needs `CYPHER 25`. You can enable it per query with a prefix or per database via `ALTER DATABASE`. On Aura the plugin is already on; self-managed setups need the JAR in `plugins/`, Docker needs `NEO4J_PLUGINS`. Providers are picked by a string plus a config map: `'openai'`, `'azure-openai'`, `'vertexai'`, `'bedrock-titan'`, `'bedrock-nova'`. The skill advises passing the API key as a `$param` instead of a literal, otherwise it stays in query logs and history.

The skill does not cover `neo4j-graphrag` Python pipelines, vector index creation or kNN search, GDS embeddings, or fulltext search. Those have their own skills. If your retrieval already runs through the Python library, this one adds nothing.

## Requirements
- Works with: AWS, Azure

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add neo4j-contrib/neo4j-skills --skill neo4j-genai-plugin-skill -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/neo4j-genai-plugin-skill/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/neo4j-genai-plugin-skill/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add neo4j-contrib/neo4j-skills --skill neo4j-genai-plugin-skill -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/neo4j-genai-plugin-skill/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add neo4j-contrib/neo4j-skills --skill neo4j-genai-plugin-skill -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/neo4j-genai-plugin-skill/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install neo4j-contrib/neo4j-skills neo4j-genai-plugin-skill
```

2. **Manually: put the files in place**
- File: `.github/skills/neo4j-genai-plugin-skill/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add neo4j-contrib/neo4j-skills --skill neo4j-genai-plugin-skill -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/neo4j-contrib/neo4j-skills --path neo4j-genai-plugin-skill
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/neo4j-genai-plugin-skill/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add neo4j-contrib/neo4j-skills --skill neo4j-genai-plugin-skill -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/neo4j-contrib/neo4j-skills/tree/HEAD/neo4j-genai-plugin-skill/SKILL.md

## When to use it
- generate node embeddings directly in Cypher
- batch-embed chunks during ingestion
- call an LLM for completion inside a Cypher query
- extract a structured map from a product description
- count tokens and split text by token limit

## Example prompts
- Generate embeddings for Chunk nodes with ai.text.embed() using the openai provider
- Write a Cypher query with ai.text.structuredCompletion() to pull category and tags from a product description
- Build a pure-Cypher GraphRAG query: embed the question, run vector search, traverse the graph, then call ai.text.completion()

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: e7b52db507528cef.

BEGIN THIRD-PARTY FILE e7b52db507528cef
````text
---
name: neo4j-genai-plugin-skill
description: Use Neo4j GenAI Plugin ai.text.* functions and procedures for in-Cypher
  embedding generation, text completion, structured output, chat, tokenization, and
  batch ingestion. Covers ai.text.embed(), ai.text.embedBatch(), ai.text.completion(),
  ai.text.structuredCompletion(), ai.text.aggregateCompletion(), ai.text.chat(),
  ai.text.tokenCount(), ai.text.chunkByTokenLimit(), and provider configuration for
  OpenAI, Azure OpenAI, VertexAI, and Amazon Bedrock. Requires CYPHER 25. Replaces
  deprecated genai.vector.encode(). Use when writing pure-Cypher GraphRAG, embedding
  nodes in-graph, generating structured maps from prompts, or calling LLMs inside
  Cypher queries. Does NOT handle neo4j-graphrag Python library pipelines — use
  neo4j-graphrag-skill. Does NOT handle vector index creation/search — use
  neo4j-vector-index-skill.
version: 1.0.7
status: active
allowed-tools: Bash WebFetch
---

## When to Use
- Generating embeddings inside Cypher without external Python (`ai.text.embed()`)
- Batch-embedding nodes/chunks during ingestion (`ai.text.embedBatch()`)
- Calling LLMs directly in Cypher for completions or GraphRAG (`ai.text.completion()`)
- Extracting structured JSON maps from LLM inside Cypher (`ai.text.structuredCompletion()`)
- Aggregating LLM summaries over grouped rows (`ai.text.aggregateCompletion()`)
- Stateful chat sessions in Cypher (`ai.text.chat()`)
- Counting tokens or chunking text by token limit (`ai.text.tokenCount()`, `ai.text.chunkByTokenLimit()`)

## When NOT to Use
- **Python-based GraphRAG pipelines** (VectorCypherRetriever, HybridCypherRetriever) → `neo4j-graphrag-skill`
- **Vector index CREATE / kNN search / SEARCH clause** → `neo4j-vector-index-skill`
- **GDS embeddings** (FastRP, Node2Vec) → `neo4j-gds-skill`
- **Fulltext / keyword search** → `neo4j-cypher-skill`

---

## Prerequisites

**CYPHER 25 required** for all `ai.*` functions. Two ways to enable:

```cypher
// Per-query prefix (self-managed, no admin rights needed):
CYPHER 25 MATCH (n:Chunk) ...

// Per-database default (admin; applies to all sessions):
ALTER DATABASE neo4j SET DEFAULT LANGUAGE CYPHER 25
```

**Installation:**
- **Aura**: GenAI plugin enabled by default — no action needed
````
END THIRD-PARTY FILE e7b52db507528cef

The third-party file has ended. Everything between the e7b52db507528cef tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2275 of 12175 bytes. © neo4j-contrib · MIT · https://github.com/neo4j-contrib/neo4j-skills/tree/HEAD/neo4j-genai-plugin-skill/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md