Merge commit 'd803bfe2b1fe7f5e219e50ac20d6801a0a58ac75' as 'vendor/ruvector'

2026-02-28 14:39:40 -05:00
parent 7885bf6278 d803bfe2b1
commit cd5943df23
7854 changed files with 3522914 additions and 0 deletions
--- a/vendor/ruvector/npm/packages/postgres-cli/benchmarks/run_benchmarks_optimized.sql
+++ b/vendor/ruvector/npm/packages/postgres-cli/benchmarks/run_benchmarks_optimized.sql
@@ -0,0 +1,171 @@
+-- RuVector Optimized Benchmark Runner
+-- Tests performance of optimized operations
+
+\timing on
+
+-- ============================================================================
+-- Test 1: HNSW Vector Search (Target: ~24ms for 1000 vectors)
+-- ============================================================================
+\echo '=== Test 1: HNSW Vector Search ==='
+
+-- Warm up
+SELECT id, embedding <-> ruvector_random(128) AS distance
+FROM benchmark_vectors
+ORDER BY distance
+LIMIT 10;
+
+-- Benchmark: Find 10 nearest neighbors
+EXPLAIN ANALYZE
+SELECT id, embedding <-> ruvector_random(128) AS distance
+FROM benchmark_vectors
+ORDER BY distance
+LIMIT 10;
+
+-- ============================================================================
+-- Test 2: Hamming Distance with bit_count (Target: ~7.6ms)
+-- ============================================================================
+\echo '=== Test 2: Hamming Distance ==='
+
+EXPLAIN ANALYZE
+SELECT
+    a.id AS id_a,
+    b.id AS id_b,
+    bench_hamming_distance(a.binary_quantized, b.binary_quantized) AS hamming_dist
+FROM benchmark_quantized a
+CROSS JOIN benchmark_quantized b
+WHERE a.id < b.id
+LIMIT 1000;
+
+-- ============================================================================
+-- Test 3: Full-Text Search with GIN (Target: ~3.5ms)
+-- ============================================================================
+\echo '=== Test 3: Full-Text Search ==='
+
+EXPLAIN ANALYZE
+SELECT id, content, ts_rank(content_tsvector, query) AS rank
+FROM benchmark_documents, plainto_tsquery('english', 'vector database search') query
+WHERE content_tsvector @@ query
+ORDER BY rank DESC
+LIMIT 20;
+
+-- ============================================================================
+-- Test 4: GraphSAGE Aggregation (Target: ~2.6ms)
+-- ============================================================================
+\echo '=== Test 4: GraphSAGE Neighbor Aggregation ==='
+
+EXPLAIN ANALYZE
+WITH neighbor_features AS (
+    SELECT
+        e.source_id,
+        ruvector_mean(ARRAY_AGG(n.features)) AS mean_neighbor
+    FROM benchmark_edges e
+    JOIN benchmark_nodes n ON e.target_id = n.id
+    GROUP BY e.source_id
+)
+SELECT
+    s.id,
+    ruvector_concat(s.features, COALESCE(nf.mean_neighbor, s.features)) AS aggregated
+FROM benchmark_nodes s
+LEFT JOIN neighbor_features nf ON s.id = nf.source_id
+LIMIT 50;
+
+-- ============================================================================
+-- Test 5: Sparse Vector Dot Product (Target: ~27ms)
+-- ============================================================================
+\echo '=== Test 5: Sparse Dot Product ==='
+
+EXPLAIN ANALYZE
+SELECT
+    a.id AS id_a,
+    b.id AS id_b,
+    bench_sparse_dot(a.sparse_embedding, b.sparse_embedding) AS similarity
+FROM benchmark_documents a
+CROSS JOIN benchmark_documents b
+WHERE a.id < b.id
+LIMIT 500;
+
+-- ============================================================================
+-- Test 6: Graph Edge Lookup (Target: ~5ms)
+-- ============================================================================
+\echo '=== Test 6: Graph Edge Lookup ==='
+
+EXPLAIN ANALYZE
+SELECT
+    e.*,
+    s.features AS source_features,
+    t.features AS target_features
+FROM benchmark_edges e
+JOIN benchmark_nodes s ON e.source_id = s.id
+JOIN benchmark_nodes t ON e.target_id = t.id
+WHERE e.source_id IN (SELECT id FROM benchmark_nodes ORDER BY random() LIMIT 10);
+
+-- ============================================================================
+-- Test 7: Scalar Quantization Compression (Target: ~75ms)
+-- ============================================================================
+\echo '=== Test 7: Scalar Quantization ==='
+
+EXPLAIN ANALYZE
+SELECT
+    id,
+    octet_length(scalar_quantized) AS compressed_size,
+    ruvector_dim(original) * 4 AS original_size,
+    ROUND(100.0 * octet_length(scalar_quantized) / (ruvector_dim(original) * 4), 2) AS compression_ratio
+FROM benchmark_quantized
+LIMIT 100;
+
+-- ============================================================================
+-- Test 8: Binary Quantization + Hamming (Target: ~85ms)
+-- ============================================================================
+\echo '=== Test 8: Binary Quantization Search ==='
+
+EXPLAIN ANALYZE
+WITH query_binary AS (
+    SELECT ruvector_binary_quantize(ruvector_random(128)) AS q
+)
+SELECT
+    bq.id,
+    bench_hamming_distance(bq.binary_quantized, query_binary.q) AS hamming_dist
+FROM benchmark_quantized bq, query_binary
+ORDER BY hamming_dist
+LIMIT 20;
+
+-- ============================================================================
+-- Summary
+-- ============================================================================
+\echo '=== Benchmark Summary ==='
+SELECT
+    'benchmark_vectors' AS table_name,
+    COUNT(*) AS row_count,
+    pg_size_pretty(pg_relation_size('benchmark_vectors')) AS table_size,
+    pg_size_pretty(pg_indexes_size('benchmark_vectors')) AS index_size
+FROM benchmark_vectors
+UNION ALL
+SELECT
+    'benchmark_documents',
+    COUNT(*),
+    pg_size_pretty(pg_relation_size('benchmark_documents')),
+    pg_size_pretty(pg_indexes_size('benchmark_documents'))
+FROM benchmark_documents
+UNION ALL
+SELECT
+    'benchmark_nodes',
+    COUNT(*),
+    pg_size_pretty(pg_relation_size('benchmark_nodes')),
+    pg_size_pretty(pg_indexes_size('benchmark_nodes'))
+FROM benchmark_nodes
+UNION ALL
+SELECT
+    'benchmark_edges',
+    COUNT(*),
+    pg_size_pretty(pg_relation_size('benchmark_edges')),
+    pg_size_pretty(pg_indexes_size('benchmark_edges'))
+FROM benchmark_edges
+UNION ALL
+SELECT
+    'benchmark_quantized',
+    COUNT(*),
+    pg_size_pretty(pg_relation_size('benchmark_quantized')),
+    pg_size_pretty(pg_indexes_size('benchmark_quantized'))
+FROM benchmark_quantized;
+
+\timing off
--- a/vendor/ruvector/npm/packages/postgres-cli/benchmarks/ruvector_benchmark_optimized.sql
+++ b/vendor/ruvector/npm/packages/postgres-cli/benchmarks/ruvector_benchmark_optimized.sql
@@ -0,0 +1,145 @@
+-- RuVector Optimized Benchmark Setup
+-- Performance-optimized schema with indexes and parallel-safe functions
+
+-- Enable extension
+CREATE EXTENSION IF NOT EXISTS ruvector;
+
+-- ============================================================================
+-- Optimized Vector Table with HNSW Index
+-- ============================================================================
+DROP TABLE IF EXISTS benchmark_vectors CASCADE;
+CREATE TABLE benchmark_vectors (
+    id SERIAL PRIMARY KEY,
+    embedding ruvector,
+    category TEXT,
+    created_at TIMESTAMPTZ DEFAULT NOW()
+);
+
+-- Insert test vectors (1000 random 128-dim vectors)
+INSERT INTO benchmark_vectors (embedding, category)
+SELECT
+    ruvector_random(128),
+    'category_' || (random() * 10)::int
+FROM generate_series(1, 1000);
+
+-- Create HNSW index for fast similarity search
+-- m=16: connections per layer, ef_construction=100: build-time accuracy
+CREATE INDEX IF NOT EXISTS idx_vectors_hnsw
+ON benchmark_vectors USING hnsw (embedding ruvector_cosine_ops)
+WITH (m = 16, ef_construction = 100);
+
+-- ============================================================================
+-- Optimized Full-Text Search with GIN Index
+-- ============================================================================
+DROP TABLE IF EXISTS benchmark_documents CASCADE;
+CREATE TABLE benchmark_documents (
+    id SERIAL PRIMARY KEY,
+    content TEXT,
+    content_tsvector TSVECTOR GENERATED ALWAYS AS (to_tsvector('english', content)) STORED,
+    sparse_embedding TEXT,
+    created_at TIMESTAMPTZ DEFAULT NOW()
+);
+
+-- Insert test documents
+INSERT INTO benchmark_documents (content, sparse_embedding)
+SELECT
+    'Document ' || i || ' contains words like vector database similarity search embedding neural network',
+    ruvector_sparse_from_dense(ARRAY[random(), 0, random(), 0, random(), 0, random(), 0]::float4[])
+FROM generate_series(1, 500) i;
+
+-- GIN index for full-text search
+CREATE INDEX IF NOT EXISTS idx_documents_fts
+ON benchmark_documents USING gin (content_tsvector);
+
+-- ============================================================================
+-- Optimized Graph Tables with B-tree Indexes
+-- ============================================================================
+DROP TABLE IF EXISTS benchmark_edges CASCADE;
+DROP TABLE IF EXISTS benchmark_nodes CASCADE;
+
+CREATE TABLE benchmark_nodes (
+    id SERIAL PRIMARY KEY,
+    features ruvector,
+    node_type TEXT
+);
+
+CREATE TABLE benchmark_edges (
+    id SERIAL PRIMARY KEY,
+    source_id INT REFERENCES benchmark_nodes(id),
+    target_id INT REFERENCES benchmark_nodes(id),
+    edge_type TEXT,
+    weight FLOAT DEFAULT 1.0
+);
+
+-- Insert test graph data
+INSERT INTO benchmark_nodes (features, node_type)
+SELECT
+    ruvector_random(64),
+    'type_' || (random() * 5)::int
+FROM generate_series(1, 200);
+
+INSERT INTO benchmark_edges (source_id, target_id, edge_type, weight)
+SELECT
+    (random() * 199 + 1)::int,
+    (random() * 199 + 1)::int,
+    'edge_' || (random() * 3)::int,
+    random()
+FROM generate_series(1, 1000);
+
+-- B-tree indexes for fast edge lookups
+CREATE INDEX IF NOT EXISTS idx_edges_source ON benchmark_edges(source_id);
+CREATE INDEX IF NOT EXISTS idx_edges_target ON benchmark_edges(target_id);
+CREATE INDEX IF NOT EXISTS idx_edges_source_target ON benchmark_edges(source_id, target_id);
+
+-- ============================================================================
+-- Optimized Quantization Tables
+-- ============================================================================
+DROP TABLE IF EXISTS benchmark_quantized CASCADE;
+CREATE TABLE benchmark_quantized (
+    id SERIAL PRIMARY KEY,
+    original ruvector,
+    binary_quantized BIT VARYING,
+    scalar_quantized BYTEA
+);
+
+-- Insert and quantize vectors
+INSERT INTO benchmark_quantized (original, binary_quantized, scalar_quantized)
+SELECT
+    v.embedding,
+    ruvector_binary_quantize(v.embedding),
+    ruvector_scalar_quantize(v.embedding, 8)
+FROM benchmark_vectors v
+LIMIT 500;
+
+-- ============================================================================
+-- Parallel-Safe Helper Functions
+-- ============================================================================
+
+-- Parallel-safe cosine distance function
+CREATE OR REPLACE FUNCTION bench_cosine_distance(a ruvector, b ruvector)
+RETURNS float8 AS $$
+    SELECT ruvector_distance(a, b, 'cosine')
+$$ LANGUAGE SQL IMMUTABLE PARALLEL SAFE;
+
+-- Parallel-safe Hamming distance using bit_count
+CREATE OR REPLACE FUNCTION bench_hamming_distance(a BIT VARYING, b BIT VARYING)
+RETURNS int AS $$
+    SELECT bit_count(a # b)::int
+$$ LANGUAGE SQL IMMUTABLE PARALLEL SAFE;
+
+-- Parallel-safe sparse dot product
+CREATE OR REPLACE FUNCTION bench_sparse_dot(a TEXT, b TEXT)
+RETURNS float8 AS $$
+    SELECT ruvector_sparse_distance(a, b, 'cosine')
+$$ LANGUAGE SQL IMMUTABLE PARALLEL SAFE;
+
+-- ============================================================================
+-- Statistics Update
+-- ============================================================================
+ANALYZE benchmark_vectors;
+ANALYZE benchmark_documents;
+ANALYZE benchmark_nodes;
+ANALYZE benchmark_edges;
+ANALYZE benchmark_quantized;
+
+SELECT 'Optimized benchmark setup complete' AS status;