> ## Documentation Index
> Fetch the complete documentation index at: https://docs.praison.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# PGVector CLI

> CLI commands for PGVector vector store

# PGVector CLI

## Docker Setup

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
docker run -d --name pgvector \
  -e POSTGRES_PASSWORD=postgres \
  -p 5433:5432 \
  pgvector/pgvector:pg16
```

## Quick Start

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# Test connection
praisonai persistence doctor \
  --knowledge-url "postgresql://postgres:postgres@localhost:5433/postgres"

# Run with knowledge store
praisonai persistence run \
  --knowledge-backend pgvector \
  --knowledge-url "$PGVECTOR_URL" \
  "Search my documents"
```

## Commands

### Doctor

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
praisonai persistence doctor \
  --knowledge-url "postgresql://postgres:postgres@localhost:5433/postgres"
```

### Run with Knowledge

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
praisonai persistence run \
  --knowledge-backend pgvector \
  --knowledge-url "$PGVECTOR_URL" \
  --session-id my-session \
  "What do my documents say?"
```

## Python Test

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
python3 -c "
import psycopg2
conn = psycopg2.connect('postgresql://postgres:postgres@localhost:5433/postgres')
cur = conn.cursor()
cur.execute('CREATE EXTENSION IF NOT EXISTS vector')
conn.commit()
cur.execute('SELECT extversion FROM pg_extension WHERE extname = %s', ('vector',))
print('PGVector OK:', cur.fetchone()[0])
conn.close()
"
```

## Environment Variables

| Variable       | Description               |
| -------------- | ------------------------- |
| `PGVECTOR_URL` | PostgreSQL connection URL |