> ## 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.

# LanceDB CLI

> CLI commands for LanceDB vector store

# LanceDB CLI

## Setup

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
pip install lancedb
```

No Docker needed - LanceDB runs embedded.

## Quick Start

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# Test connection
praisonai persistence doctor \
  --knowledge-path "./lancedb_data"

# Run with knowledge store
praisonai persistence run \
  --knowledge-backend lancedb \
  --knowledge-path "./lancedb_data" \
  "Search my documents"
```

## Commands

### Doctor

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
praisonai persistence doctor \
  --knowledge-backend lancedb \
  --knowledge-path "./lancedb_data"
```

### Run with Knowledge

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
praisonai persistence run \
  --knowledge-backend lancedb \
  --knowledge-path "./lancedb_data" \
  --session-id my-session \
  "What do my documents say?"
```

## Python Test

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
python3 -c "
import lancedb
db = lancedb.connect('/tmp/lancedb_test')
print('LanceDB OK:', lancedb.__version__)
"
```

## Notes

* Embedded database - no server needed
* Supports local and cloud storage
* Columnar format for fast queries