> ## Documentation Index
> Fetch the complete documentation index at: https://praison.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# Redis
> Key-value store and caching with Redis
The Redis tool lets an agent read, write, and cache key-value data in Redis.
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph LR
subgraph "Redis"
User[User] --> Agent[Agent]
Agent --> Tool[RedisTool]
Tool --> DB[(Redis)]
DB --> Result[Value]
end
classDef input fill:#8B0000,stroke:#7C90A0,color:#fff
classDef process fill:#189AB4,stroke:#7C90A0,color:#fff
classDef output fill:#10B981,stroke:#7C90A0,color:#fff
class User,Agent input
class Tool,DB process
class Result output
```
## Overview
Redis tool allows you to interact with Redis for caching, key-value storage, and pub/sub messaging.
## Installation
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
pip install "praisonai[tools]"
```
## Environment Variables
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
export REDIS_HOST=localhost
export REDIS_PORT=6379
export REDIS_PASSWORD=your_password # Optional
```
## Quick Start
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonai_tools import RedisTool
# Initialize
redis = RedisTool(host="localhost", port=6379)
# Set and get values
redis.set("key", "value")
value = redis.get("key")
print(value)
```
Use the same tool with an agent — see **Usage with Agent** below, or pass env vars and options from the sections above.
## How It Works
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
sequenceDiagram
participant User
participant Agent
participant Redis as RedisTool
participant DB as Redis
User->>Agent: "Store user preferences"
Agent->>Redis: set(key, value)
Redis->>DB: SET
DB-->>Redis: OK
Redis-->>Agent: confirmation
Agent-->>User: final answer
```
## Usage with Agent
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import Agent
from praisonai_tools import RedisTool
redis = RedisTool(host="localhost", port=6379)
agent = Agent(
name="CacheManager",
instructions="You manage cached data using Redis.",
tools=[redis]
)
response = agent.chat("Store user preferences for user123")
print(response)
```
## Available Methods
### get(key)
Get a value by key.
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonai_tools import RedisTool
redis = RedisTool(host="localhost")
value = redis.get("user:123:name")
```
### set(key, value, ttl=None)
Set a key-value pair with optional TTL.
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
redis.set("session:abc", "data", ttl=3600) # Expires in 1 hour
```
### delete(key)
Delete a key.
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
redis.delete("old_key")
```
### keys(pattern)
Find keys matching a pattern.
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
keys = redis.keys("user:*")
```
### hget/hset
Hash operations.
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
redis.hset("user:123", "name", "Alice")
name = redis.hget("user:123", "name")
```
## Docker Setup
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
docker run -d --name redis \
-p 6379:6379 \
redis:7
```
## Common Errors
| Error | Cause | Solution |
| --------------------- | ----------------------- | ----------------------- |
| `redis not installed` | Missing dependency | Run `pip install redis` |
| `Connection refused` | Redis not running | Start Redis server |
| `NOAUTH` | Authentication required | Provide password |
## Best Practices
Read `REDIS_PASSWORD` from the environment instead of hard-coding it in the tool call.
`set(key, value, ttl=3600)` expires keys automatically. Use TTLs so agent-written cache entries do not grow unbounded.
Namespace keys (e.g. `user:123:name`) so agents can filter with `keys(pattern)` without scanning the whole store.
## Related Tools
NoSQL database
SQL database
Serverless Redis