---
title: Hugging Face
---

You can use embedding models from Huggingface to run Mem0 locally.

### Usage

```python
import os
from mem0 import Memory

os.environ["OPENAI_API_KEY"] = "your_api_key" # For LLM

config = {
    "embedder": {
        "provider": "huggingface",
        "config": {
            "model": "multi-qa-MiniLM-L6-cos-v1"
        }
    }
}

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="john")
```

### Config

Here are the parameters available for configuring Huggingface embedder:

| Parameter | Description | Default Value |
| --- | --- | --- |
| `model` | The name of the model to use | `multi-qa-MiniLM-L6-cos-v1` |
| `embedding_dims` | Dimensions of the embedding model | `selected_model_dimensions` |
| `model_kwargs` | Additional arguments for the model | `None` |