CALL dbms.components() YIELD versions RETURN versions[0] AS neo4j_version

CYPHER 25
CREATE VECTOR INDEX chunk_embedding IF NOT EXISTS
FOR (c:Chunk) ON (c.embedding)
OPTIONS {
  indexConfig: {
    `vector.dimensions`: 1536,
    `vector.similarity_function`: 'cosine',
    `vector.quantization.enabled`: true,
    `vector.hnsw.m`: 16,
    `vector.hnsw.ef_construction`: 100
  }
}

CYPHER 25
CREATE VECTOR INDEX chunk_embedding IF NOT EXISTS
FOR (c:Chunk) ON (c.embedding)
WITH [c.source, c.lang, c.published_year]  // stored as metadata; filterable in SEARCH WHERE
OPTIONS { indexConfig: { `vector.dimensions`: 1536, `vector.similarity_function`: 'cosine' } }

CYPHER 25
CREATE VECTOR INDEX doc_embedding IF NOT EXISTS
FOR (n:Document|Article) ON n.embedding
WITH [n.author, n.published_year, n.lang]
OPTIONS { indexConfig: { `vector.dimensions`: 1536, `vector.similarity_function`: 'cosine' } }

CYPHER 25
CREATE VECTOR INDEX rel_embedding IF NOT EXISTS
FOR ()-[r:HAS_CHUNK]-() ON (r.embedding)
OPTIONS { indexConfig: { `vector.dimensions`: 768, `vector.similarity_function`: 'cosine' } }

SHOW VECTOR INDEXES YIELD name, state, populationPercent
WHERE name = 'chunk_embedding'
RETURN name, state, populationPercent

until cypher-shell -u neo4j -p "$NEO4J_PASSWORD" \
  "SHOW VECTOR INDEXES YIELD name, state WHERE name='chunk_embedding' RETURN state" \
  | grep -q ONLINE; do
  sleep 5
done

from neo4j import GraphDatabase

driver = GraphDatabase.driver(uri, auth=(user, password))

def embed_batch(texts: list[str]) -> list[list[float]]:
    response = openai_client.embeddings.create(
        model="text-embedding-3-small", input=texts
    )
    return [r.embedding for r in response.data]

def store_embeddings(records: list[dict], batch_size: int = 500):
    expected_dim = 1536  # must match vector.dimensions
    texts = [r["text"] for r in records]
    embeddings = embed_batch(texts)
    for emb in embeddings:
        assert len(emb) == expected_dim, f"Dim mismatch: {len(emb)} != {expected_dim}"
    rows = [{"id": r["id"], "embedding": emb}
            for r, emb in zip(records, embeddings)]
    for i in range(0, len(rows), batch_size):
        driver.execute_query(
            "UNWIND $rows AS row MATCH (c:Chunk {id: row.id}) SET c.embedding = row.embedding",
            rows=rows[i:i+batch_size]
        )

CYPHER 25
MATCH (c:Chunk)
  SEARCH c IN (
    VECTOR INDEX chunk_embedding
    FOR $queryEmbedding
    LIMIT 10
  ) SCORE AS score
RETURN c.text, score
ORDER BY score DESC

// Index must have been created with: WITH [c.source, c.lang, c.published_year]
CYPHER 25
MATCH (c:Chunk)
  SEARCH c IN (
    VECTOR INDEX chunk_embedding
    FOR $queryEmbedding
    WHERE c.source = $source AND c.lang = 'en' AND c.published_year >= 2024
    LIMIT 10
  ) SCORE AS score
RETURN c.text, c.source, score
ORDER BY score DESC

CYPHER 25
CALL db.index.vector.queryNodes('chunk_embedding', 50, $queryEmbedding)
YIELD node AS c, score
WHERE c.source = $source    // post-filter: fetch more, then filter
RETURN c.text, score
ORDER BY score DESC LIMIT 10

CYPHER 25
CALL db.index.vector.queryRelationships('rel_embedding', 5, $queryEmbedding)
YIELD relationship AS r, score
RETURN r.text, score

CYPHER 25
MATCH (c:Chunk)
  SEARCH c IN (
    VECTOR INDEX chunk_embedding
    FOR $queryEmbedding
    LIMIT 10
  ) SCORE AS score
MATCH (c)<-[:HAS_CHUNK]-(a:Article)
OPTIONAL MATCH (a)-[:MENTIONS]->(org:Organization)
RETURN c.text, a.title, score, collect(DISTINCT org.name) AS organizations
ORDER BY score DESC

MATCH (a:Chunk {id: $id1}), (b:Chunk {id: $id2})
RETURN vector.similarity.cosine(a.embedding, b.embedding) AS sim
// vector.similarity.euclidean(a, b) — same signature, 0–1 range

// vector_distance (2025.10+) — metrics: EUCLIDEAN, EUCLIDEAN_SQUARED, MANHATTAN, COSINE, DOT, HAMMING
// Returns distance (lower = more similar, inverse of similarity)
RETURN vector_distance(a.embedding, b.embedding, 'COSINE') AS dist

// vector_dimension_count (2025.10+)
RETURN vector_dimension_count(n.embedding) AS dims

// vector_norm (2025.20+) — metrics: EUCLIDEAN, MANHATTAN
RETURN vector_norm(n.embedding, 'EUCLIDEAN') AS norm

// vector(value, dimension, coordinateType)
// coordinateType: FLOAT64, FLOAT32, INTEGER8/16/32/64
WITH vector([1.0, 2.0, 3.0], 3, 'FLOAT32') AS v
RETURN vector_dimension_count(v)

// Show all vector indexes with config
SHOW VECTOR INDEXES YIELD name, state, populationPercent,
  labelsOrTypes, properties, indexConfig
RETURN name, state, populationPercent, labelsOrTypes, properties, indexConfig;

// Drop (node data unchanged — only index structure removed)
DROP INDEX chunk_embedding IF EXISTS;

// No ALTER VECTOR INDEX — to change dimensions or similarity function:
// 1. DROP INDEX old_index IF EXISTS
// 2. CREATE VECTOR INDEX new_index ... with new OPTIONS
// 3. Re-generate all embeddings with new model
// 4. Poll until ONLINE

// Syntax (requires CYPHER 25)
CYPHER 25
// ai.text.embed(resource :: STRING, provider :: STRING, configuration :: MAP) :: VECTOR

CYPHER 25
WITH ai.text.embed(
    "What are good open source projects",
    "openai",
    { token: $openaiKey, model: 'text-embedding-3-small' }) AS userEmbedding
CALL db.index.vector.queryNodes('chunk_embedding', 6, userEmbedding)  // deprecated 2026.04
YIELD node AS c, score
RETURN c.text, score
ORDER BY score DESC

CYPHER 25
WITH ai.text.embed("my query", "openai", { token: $openaiKey, model: 'text-embedding-3-small' }) AS userEmbedding
MATCH (c:Chunk)
  SEARCH c IN (VECTOR INDEX chunk_embedding FOR userEmbedding LIMIT 6) SCORE AS score
RETURN c.text, score
ORDER BY score DESC

LOAD CSV WITH HEADERS FROM 'https://example.com/data.csv' AS row
MERGE (q:Question {text: row.question})
WITH q, row
CALL db.create.setNodeVectorProperty(q, 'embedding', apoc.convert.fromJsonList(row.question_embedding))

❌ Created index with 'euclidean' but model outputs L2-normalized vectors
   → scores are mathematically correct but rankings differ from expected cosine order
   → no error thrown; wrong results silently returned
✅ Verify: run vector.similarity.cosine(a.embedding, b.embedding) manually on known
   similar pairs — score should be > 0.9 for near-duplicate text

MATCH (c:Chunk) WITH c LIMIT 2
WITH collect(c) AS nodes
RETURN vector.similarity.cosine(nodes[0].embedding, nodes[1].embedding) AS cosine_check,
       vector.similarity.euclidean(nodes[0].embedding, nodes[1].embedding) AS euclidean_check