Back to Mem0

Redis

docs/components/vectordbs/dbs/redis.mdx

2.0.12.8 KB
Original Source

Redis is a scalable, real-time database that can store, search, and analyze vector data.

Installation

bash
pip install redis redisvl

Redis Stack using Docker:

bash
docker run -d --name redis-stack -p 6379:6379 -p 8001:8001 redis/redis-stack:latest

Usage

<CodeGroup> ```python Python import os from mem0 import Memory

os.environ["OPENAI_API_KEY"] = "sk-xx"

config = { "vector_store": { "provider": "redis", "config": { "collection_name": "mem0", "embedding_model_dims": 1536, "redis_url": "redis://localhost:6379" } }, "version": "v1.1" }

m = Memory.from_config(config) messages = [ {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"}, {"role": "assistant", "content": "How about thriller movies? They can be quite engaging."}, {"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."}, {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."} ] m.add(messages, user_id="alice", metadata={"category": "movies"})


```typescript TypeScript
import { Memory } from 'mem0ai/oss';

const config = {
  vectorStore: {
    provider: 'redis',
    config: {
      collectionName: 'memories',
      embeddingModelDims: 1536,
      redisUrl: 'redis://localhost:6379',
      username: 'your-redis-username',
      password: 'your-redis-password',
    },
  },
};

const memory = new Memory(config);
const messages = [
    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
    {"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
    {"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
]
await memory.add(messages, { userId: "alice", metadata: { category: "movies" } });
</CodeGroup>

Config

Let's see the available parameters for the redis config:

<Tabs> <Tab title="Python"> | Parameter | Description | Default Value | | --- | --- | --- | | `collection_name` | The name of the collection to store the vectors | `mem0` | | `embedding_model_dims` | Dimensions of the embedding model | `1536` | | `redis_url` | The URL of the Redis server | `None` | </Tab> <Tab title="TypeScript"> | Parameter | Description | Default Value | | --- | --- | --- | | `collectionName` | The name of the collection to store the vectors | `mem0` | | `embeddingModelDims` | Dimensions of the embedding model | `1536` | | `redisUrl` | The URL of the Redis server | `None` | | `username` | Username for Redis connection | `None` | | `password` | Password for Redis connection | `None` | </Tab> </Tabs>