Setup Progress:
- [ ] Docker environment running (docker-compose up -d)
- [ ] Connected to database (psql or Python)
- [ ] Extensions created (pgvector, pg_trgm)
- [ ] Table created with search_vector and embedding columns
- [ ] GIN index on search_vector created
- [ ] HNSW index on embedding created
- [ ] Test full-text query returns results
- [ ] Test vector query returns results

# docker-compose.yml
services:
  postgres:
    image: pgvector/pgvector:pg17
    environment:
      POSTGRES_PASSWORD: devpass
    ports: ["5432:5432"]
    volumes: [pgdata:/var/lib/postgresql/data]
volumes:
  pgdata:

docker-compose up -d

# Verify container is running:
docker-compose ps
# Expected: postgres service with status "Up"

CREATE EXTENSION vector;      -- pgvector for embeddings
CREATE EXTENSION pg_trgm;     -- Trigram for fuzzy search

-- Verify extensions installed:
SELECT extname, extversion FROM pg_extension 
WHERE extname IN ('vector', 'pg_trgm');
-- Expected: 2 rows with version numbers

CREATE TABLE documents (
    id BIGSERIAL PRIMARY KEY,
    title TEXT NOT NULL,
    content TEXT,
    embedding vector(1536),
    search_vector tsvector GENERATED ALWAYS AS (
        setweight(to_tsvector('english', coalesce(title, '')), 'A') ||
        setweight(to_tsvector('english', coalesce(content, '')), 'B')
    ) STORED
);

-- Create indexes
CREATE INDEX idx_docs_search ON documents USING GIN (search_vector);
CREATE INDEX idx_docs_embedding ON documents USING hnsw (embedding vector_cosine_ops);

-- Verify indexes created:
SELECT indexname FROM pg_indexes WHERE tablename = 'documents';
-- Expected: idx_docs_search, idx_docs_embedding, documents_pkey

import asyncpg

async def search(pool, query: str, embedding: list[float], limit: int = 10):
    return await pool.fetch("""
        SELECT id, title,
               ts_rank(search_vector, websearch_to_tsquery('english', $1)) AS text_rank,
               embedding <=> $2::vector AS vector_dist
        FROM documents
        WHERE search_vector @@ websearch_to_tsquery('english', $1)
        ORDER BY vector_dist
        LIMIT $3
    """, query, embedding, limit)

# Verify connection works:
# pool = await asyncpg.create_pool('postgresql://postgres:devpass@localhost/postgres')
# rows = await pool.fetch("SELECT 1 AS test")
# assert rows[0]['test'] == 1

Need search? ─┬─► Exact keyword match ──────► B-tree index + WHERE =
              │
              ├─► Full-text search (FTS) ───► tsvector + GIN + ts_rank
              │
              ├─► Relevance like Google ────► pg_search BM25 (ParadeDB)
              │
              ├─► Typo tolerance ───────────► pg_trgm + similarity()
              │
              ├─► Semantic/AI search ───────► pgvector + embeddings
              │
              └─► Hybrid (keywords + semantic) ► Combine tsvector + pgvector

Vector index? ─┬─► Dataset < 100K rows ────► No index (exact search OK)
               │
               ├─► Need best recall ────────► HNSW (slower build, fast query)
               │
               ├─► Fast index build ────────► IVFFlat (needs data first)
               │
               ├─► On AlloyDB ──────────────► ScaNN (Google optimized)
               │
               ├─► On Azure ────────────────► pg_diskann (32x less memory)
               │
               ├─► Billions of vectors ─────► VectorChord vchordrq (self-host)
               │
               └─► Dimensions > 2000 ───────► halfvec or binary quantization

Python lib? ──┬─► Sync, simple, stable ─────► psycopg2
              │
              ├─► Async + modern features ──► psycopg3
              │
              ├─► Max async performance ────► asyncpg
              │
              └─► ORM needed ───────────────► SQLAlchemy + asyncpg/psycopg

Column type? ─┬─► Scalar (int, text, timestamp) ─► B-tree (default)
              │
              ├─► JSONB ────────────────────────┬► GIN (general queries)
              │                                 └► GIN jsonb_path_ops (@> only)
              │
              ├─► Array ────────────────────────► GIN
              │
              ├─► tsvector ─────────────────────► GIN (or GiST for updates)
              │
              ├─► vector ───────────────────────► HNSW or IVFFlat
              │
              └─► Range / Geometric ────────────► GiST

CREATE INDEX ON docs USING hnsw (embedding vector_cosine_ops) WITH (m=16, ef_construction=100);
SET hnsw.ef_search = 100;  -- Before querying

-- Verify setting applied:
SHOW hnsw.ef_search;

CREATE INDEX ON docs USING ivfflat (embedding vector_l2_ops) WITH (lists=100);
SET ivfflat.probes = 10;

pip install -r scripts/requirements.txt  # Install dependencies first

python scripts/setup_extensions.py --host localhost --dbname mydb
python scripts/create_search_tables.py --host localhost --dbname mydb
python scripts/health_check.py --host localhost --dbname mydb