Qdrant - Mem0

Qdrant

Qdrant is an open-source vector search engine. It is designed to work with large-scale datasets and provides a high-performance search engine for vector data.

Usage

Python

import os
from mem0 import Memory

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

config = {
    "vector_store": {
        "provider": "qdrant",
        "config": {
            "collection_name": "test",
            "host": "localhost",
            "port": 6333,
        }
    }
}

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

import { Memory } from 'mem0ai/oss';

const config = {
  vectorStore: {
    provider: 'qdrant',
    config: {
      collectionName: 'memories',
      dimension: 1536,
      host: 'localhost',
      port: 6333,
    },
  },
};

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" } });

Config

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