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

​
Installation

pip install redis redisvl

Redis Stack using Docker:

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

​
Usage

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 a 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"})

​
Config

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

ParameterDescriptionDefault Value
collection_nameThe name of the collection to store the vectorsmem0
embedding_model_dimsDimensions of the embedding model1536
redis_urlThe URL of the Redis serverNone