Kartik
51 lines
1.5 KiB
Plaintext
51 lines
1.5 KiB
Plaintext
---
|
|
title: "FastEmbed"
|
|
description: "Configure FastEmbed as an embedding provider in Mem0 to generate embeddings locally using ONNX-based models without a GPU."
|
|
---
|
|
|
|
You can use FastEmbed to run embedding models locally in Mem0. FastEmbed is an ONNX-based embedding library that runs efficiently on CPU without requiring a GPU or an external API key.
|
|
|
|
### Installation
|
|
|
|
```bash
|
|
pip install fastembed
|
|
```
|
|
|
|
### Usage
|
|
|
|
<CodeGroup>
|
|
```python Python
|
|
import os
|
|
from mem0 import Memory
|
|
|
|
os.environ["OPENAI_API_KEY"] = "your_api_key" # For LLM
|
|
|
|
config = {
|
|
"embedder": {
|
|
"provider": "fastembed",
|
|
"config": {
|
|
"model": "thenlper/gte-large"
|
|
}
|
|
}
|
|
}
|
|
|
|
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="john")
|
|
```
|
|
</CodeGroup>
|
|
|
|
### Config
|
|
|
|
Here are the parameters available for configuring FastEmbed embedder:
|
|
|
|
| Parameter | Description | Default Value |
|
|
| --- | --- | --- |
|
|
| `model` | The name of the FastEmbed model to use | `thenlper/gte-large` |
|
|
| `embedding_dims` | Dimensions of the embedding model (auto-derived from the model if not set) | `None` |
|