neo4j-genai-plugin-skill

Name: neo4j-genai-plugin-skill
Author: neo4j-contrib

332installs33forks

How to install neo4j-genai-plugin-skill?

neo4j-contrib/neo4j-skills/neo4j-genai-plugin-skill

$npx -y skills add neo4j-contrib/neo4j-skills --skill neo4j-genai-plugin-skill

Installs into the current project.

Summary

Use Neo4j GenAI Plugin ai.text.* functions and procedures for in-Cypher

Files · 1

View on GitHub

SKILL.md

1	## When to Use
2	- Generating embeddings inside Cypher without external Python (`ai.text.embed()`)
3	- Batch-embedding nodes/chunks during ingestion (`ai.text.embedBatch()`)
4	- Calling LLMs directly in Cypher for completions or GraphRAG (`ai.text.completion()`)
5	- Extracting structured JSON maps from LLM inside Cypher (`ai.text.structuredCompletion()`)
6	- Aggregating LLM summaries over grouped rows (`ai.text.aggregateCompletion()`)
7	- Stateful chat sessions in Cypher (`ai.text.chat()`)
8	- Counting tokens or chunking text by token limit (`ai.text.tokenCount()`, `ai.text.chunkByTokenLimit()`)
9
10	## When NOT to Use
11	- Python-based GraphRAG pipelines (VectorCypherRetriever, HybridCypherRetriever) → `neo4j-graphrag-skill`
12	- Vector index CREATE / kNN search / SEARCH clause → `neo4j-vector-index-skill`
13	- GDS embeddings (FastRP, Node2Vec) → `neo4j-gds-skill`
14	- Fulltext / keyword search → `neo4j-cypher-skill`
15
16	---
17
18	## Prerequisites
19
20	CYPHER 25 required for all `ai.*` functions. Two ways to enable:
21
22	```cypher
23	// Per-query prefix (self-managed, no admin rights needed):
24	CYPHER 25 MATCH (n:Chunk) ...
25
26	// Per-database default (admin; applies to all sessions):
27	ALTER DATABASE neo4j SET DEFAULT LANGUAGE CYPHER 25
28	```
29
30	Installation:
31	- Aura: GenAI plugin enabled by default — no action needed
32	- Self-managed JAR: copy plugin JAR to `plugins/` directory
33	- Docker: `--env NEO4J_PLUGINS='["genai"]'`
34
35	---
36
37	## Provider Config Quick Reference
38
39	All `ai.text.*` functions accept a `configuration :: MAP` as last argument.
40
41	\| Provider string \| Required keys \| Notes \|
42	\|---\|---\|---\|
43	\| `'openai'` \| `token`, `model` \| `token` = OpenAI API key \|
44	\| `'azure-openai'` \| `token`, `resource`, `model` \| `token` = OAuth2 bearer; `resource` = Azure resource name \|
45	\| `'vertexai'` \| `model`, `project`, `region`, `token` or `apiKey` \| `publisher` defaults to `'google'` \|
46	\| `'bedrock-titan'` \| `model`, `region`, `accessKeyId`, `secretAccessKey` \| Embedding only \|
47	\| `'bedrock-nova'` \| `model`, `region`, `accessKeyId`, `secretAccessKey` \| Completion only \|
48
49	Optional for all: `vendorOptions :: MAP` passes provider-specific extras (e.g. `{ dimensions: 1024 }` for OpenAI).
50
51	❌ Never hardcode API key literals. ✅ Always use `$param` passed via driver parameters dict.
52
53	Full provider config table → [references/providers.md](references/providers.md)
54
55	---
56
57	## Embedding
58
59	### Single embed [2025.11]
60
61	```cypher
62	CYPHER 25
63	MATCH (c:Chunk)
64	WHERE c.embedding IS NULL
65	WITH c
66	CALL {
67	WITH c
68	SET c.embedding = ai.text.embed(c.text, 'openai', {
69	token: $openaiKey,
70	model: 'text-embedding-3-small'
71	})
72	} IN TRANSACTIONS OF 500 ROWS
73	```
74
75	`ai.text.embed()` returns `VECTOR` — directly storable and queryable in a vector index.
76
77	### Batch embed procedure [2025.11]
78
79	```cypher
80	CYPHER 25
81	MATCH (c:Chunk) WHERE c.embedding IS NULL
82	WITH collect(c) AS chunks
83	UNWIND chunks AS c
84	WITH c.text AS text, c AS node
85	CALL ai.text.embedBatch(text, 'openai', { token: $openaiKey, model: 'text-embedding-3-small' })
86	YIELD index, resource, vector
87	MATCH (c:Chunk {text: resource})
88	SET c.embedding = vector
89	```
90
91	Procedure signature: `CALL ai.text.embedBatch(resource, provider, config) YIELD index, resource, vector`
92
93	### List configured embed providers
94
95	```cypher
96	CYPHER 25
97	CALL ai.text.embed.providers()
98	YIELD name, requiredConfigType, optionalConfigType, defaultConfig
99	RETURN name, requiredConfigType
100	```
101
102	---
103
104	## Text Completion [2025.11]
105
106	```cypher
107	CYPHER 25
108	RETURN ai.text.completion(
109	'Summarize: ' + $text,
110	'openai',
111	{ token: $openaiKey, model: 'gpt-4o-mini' }
112	) AS summary
113	```
114
115	Returns `STRING`.
116
117	### Aggregate completion — summarize across rows [2026.03]
118
119	```cypher
120	CYPHER 25
121	MATCH (c:Chunk)-[:PART_OF]->(a:Article {id: $articleId})
122	RETURN ai.text.aggregateCompletion(
123	c.text,
124	'Summarize the following article chunks in 3 sentences',
125	'openai',
126	{ token: $openaiKey, model: 'gpt-4o-mini' }
127	) AS summary
128	```
129
130	`value` parameter = each row's STRING fed to the LLM. Uses `toString()` for non-string values.
131
132	---
133
134	## Pure-Cypher GraphRAG Pattern
135
136	Embe

People who liked this also viewed

6 picks

Type

azure-storageAzure Storage Services including Blob Storage, File Shares, Queue Storage, Table Storage, and Data Lake. Answers questions about storage access tiers (hot, cool, cold, archive), when to use each tier,SkillsJul 2026471k1.3k
supabase-postgres-best-practicesPostgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries, schema designs, or database configurations.SkillsJul 2026302k2.4k
supabaseUse when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues); client libraries and SSR integrations (supabase-js, SkillsJul 2026179k2.4k
convex-quickstartCreates or adds Convex to an app. Use for new Convex projects, npm create convex@latest, frontend setup, env vars, or the first npx convex dev run.SkillsJul 202690k39
convex-performance-auditAudits Convex performance for reads, subscriptions, write contention, and function limits. Use for slow features, insights findings, OCC conflicts, or read amplification.SkillsJul 202689k39
convex-setup-authSets up Convex auth, identity mapping, and access control. Use for login, auth providers, users tables, protected functions, or roles in a Convex app.SkillsJul 202689k39

neo4j-genai-plugin-skill

332installs33forks

View on GitHub

How to install neo4j-genai-plugin-skill?

neo4j-contrib/neo4j-skills/neo4j-genai-plugin-skill

$npx -y skills add neo4j-contrib/neo4j-skills --skill neo4j-genai-plugin-skill

Installs into the current project.

Summary

Use Neo4j GenAI Plugin ai.text.* functions and procedures for in-Cypher

Files · 1

View on GitHub

SKILL.md

1	## When to Use
2	- Generating embeddings inside Cypher without external Python (`ai.text.embed()`)
3	- Batch-embedding nodes/chunks during ingestion (`ai.text.embedBatch()`)
4	- Calling LLMs directly in Cypher for completions or GraphRAG (`ai.text.completion()`)
5	- Extracting structured JSON maps from LLM inside Cypher (`ai.text.structuredCompletion()`)
6	- Aggregating LLM summaries over grouped rows (`ai.text.aggregateCompletion()`)
7	- Stateful chat sessions in Cypher (`ai.text.chat()`)
8	- Counting tokens or chunking text by token limit (`ai.text.tokenCount()`, `ai.text.chunkByTokenLimit()`)
9
10	## When NOT to Use
11	- Python-based GraphRAG pipelines (VectorCypherRetriever, HybridCypherRetriever) → `neo4j-graphrag-skill`
12	- Vector index CREATE / kNN search / SEARCH clause → `neo4j-vector-index-skill`
13	- GDS embeddings (FastRP, Node2Vec) → `neo4j-gds-skill`
14	- Fulltext / keyword search → `neo4j-cypher-skill`
15
16	---
17
18	## Prerequisites
19
20	CYPHER 25 required for all `ai.*` functions. Two ways to enable:
21
22	```cypher
23	// Per-query prefix (self-managed, no admin rights needed):
24	CYPHER 25 MATCH (n:Chunk) ...
25
26	// Per-database default (admin; applies to all sessions):
27	ALTER DATABASE neo4j SET DEFAULT LANGUAGE CYPHER 25
28	```
29
30	Installation:
31	- Aura: GenAI plugin enabled by default — no action needed
32	- Self-managed JAR: copy plugin JAR to `plugins/` directory
33	- Docker: `--env NEO4J_PLUGINS='["genai"]'`
34
35	---
36
37	## Provider Config Quick Reference
38
39	All `ai.text.*` functions accept a `configuration :: MAP` as last argument.
40
41	\| Provider string \| Required keys \| Notes \|
42	\|---\|---\|---\|
43	\| `'openai'` \| `token`, `model` \| `token` = OpenAI API key \|
44	\| `'azure-openai'` \| `token`, `resource`, `model` \| `token` = OAuth2 bearer; `resource` = Azure resource name \|
45	\| `'vertexai'` \| `model`, `project`, `region`, `token` or `apiKey` \| `publisher` defaults to `'google'` \|
46	\| `'bedrock-titan'` \| `model`, `region`, `accessKeyId`, `secretAccessKey` \| Embedding only \|
47	\| `'bedrock-nova'` \| `model`, `region`, `accessKeyId`, `secretAccessKey` \| Completion only \|
48
49	Optional for all: `vendorOptions :: MAP` passes provider-specific extras (e.g. `{ dimensions: 1024 }` for OpenAI).
50
51	❌ Never hardcode API key literals. ✅ Always use `$param` passed via driver parameters dict.
52
53	Full provider config table → [references/providers.md](references/providers.md)
54
55	---
56
57	## Embedding
58
59	### Single embed [2025.11]
60
61	```cypher
62	CYPHER 25
63	MATCH (c:Chunk)
64	WHERE c.embedding IS NULL
65	WITH c
66	CALL {
67	WITH c
68	SET c.embedding = ai.text.embed(c.text, 'openai', {
69	token: $openaiKey,
70	model: 'text-embedding-3-small'
71	})
72	} IN TRANSACTIONS OF 500 ROWS
73	```
74
75	`ai.text.embed()` returns `VECTOR` — directly storable and queryable in a vector index.
76
77	### Batch embed procedure [2025.11]
78
79	```cypher
80	CYPHER 25
81	MATCH (c:Chunk) WHERE c.embedding IS NULL
82	WITH collect(c) AS chunks
83	UNWIND chunks AS c
84	WITH c.text AS text, c AS node
85	CALL ai.text.embedBatch(text, 'openai', { token: $openaiKey, model: 'text-embedding-3-small' })
86	YIELD index, resource, vector
87	MATCH (c:Chunk {text: resource})
88	SET c.embedding = vector
89	```
90
91	Procedure signature: `CALL ai.text.embedBatch(resource, provider, config) YIELD index, resource, vector`
92
93	### List configured embed providers
94
95	```cypher
96	CYPHER 25
97	CALL ai.text.embed.providers()
98	YIELD name, requiredConfigType, optionalConfigType, defaultConfig
99	RETURN name, requiredConfigType
100	```
101
102	---
103
104	## Text Completion [2025.11]
105
106	```cypher
107	CYPHER 25
108	RETURN ai.text.completion(
109	'Summarize: ' + $text,
110	'openai',
111	{ token: $openaiKey, model: 'gpt-4o-mini' }
112	) AS summary
113	```
114
115	Returns `STRING`.
116
117	### Aggregate completion — summarize across rows [2026.03]
118
119	```cypher
120	CYPHER 25
121	MATCH (c:Chunk)-[:PART_OF]->(a:Article {id: $articleId})
122	RETURN ai.text.aggregateCompletion(
123	c.text,
124	'Summarize the following article chunks in 3 sentences',
125	'openai',
126	{ token: $openaiKey, model: 'gpt-4o-mini' }
127	) AS summary
128	```
129
130	`value` parameter = each row's STRING fed to the LLM. Uses `toString()` for non-string values.
131
132	---
133
134	## Pure-Cypher GraphRAG Pattern
135
136	Embe

People who liked this also viewed

6 picks

Type