Mistral AI

To use mistral's models, please obtain the Mistral AI api key from their console. Set the MISTRAL_API_KEY environment variable to use the model as given below in the example.

Usage

os.environ["OPENAI_API_KEY"] = "your-api-key" # used for embedding model os.environ["MISTRAL_API_KEY"] = "your-api-key"

config = { "llm": { "provider": "litellm", "config": { "model": "open-mixtral-8x7b", "temperature": 0.1, "max_tokens": 2000, } } }

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 = {
  llm: {
    provider: 'mistral',
    config: {
      apiKey: process.env.MISTRAL_API_KEY || '',
      model: 'mistral-tiny-latest', // Or 'mistral-small-latest', 'mistral-medium-latest', etc.
      temperature: 0.1,
      maxTokens: 2000,
    },
  },
};

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

All available parameters for the litellm config are present in Master List of All Params in Config.