mem0ai--mem0/docs/components/embedders/models/together.mdx

---
title: Together
description: "Configure Together AI as an embedding provider in Mem0 with support for 1024-dimensional embedding models."
---

To use Together embedding models, set the `TOGETHER_API_KEY` environment variable. You can obtain the Together API key from the [Together Platform](https://api.together.ai/settings/projects/~current/api-keys).

### Usage

<Note> The `embedding_model_dims` parameter for `vector_store` should be set to `1024` for Together embedder. </Note>

<Warning>
**Breaking default change.** The default Together embedding model is now `intfloat/multilingual-e5-large-instruct` (**1024-dim**), replacing the previous default `togethercomputer/m2-bert-80M-8k-retrieval` (**768-dim**). If you created a self-hosted vector store with the old default, its collection is 768-dim and will reject the new 1024-dim vectors **recreate/reindex the collection at 1024 dimensions** after upgrading. To defer the change, pin the previous values explicitly (`model="togethercomputer/m2-bert-80M-8k-retrieval"`, `embedding_dims=768`) note Together no longer lists this model among its recommended embeddings, so reindexing at 1024 is the durable path.
</Warning>

<CodeGroup>
```python Python
import os
from mem0 import Memory

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

config = {
    "embedder": {
        "provider": "together",
        "config": {
            "model": "intfloat/multilingual-e5-large-instruct"
        }
    }
}

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")
```

```typescript TypeScript
import { Memory } from 'mem0ai/oss';

const config = {
  embedder: {
    provider: 'together',
    config: {
      apiKey: process.env.TOGETHER_API_KEY || '',
      model: 'intfloat/multilingual-e5-large-instruct',
      embeddingDims: 1024,
    },
  },
};

const memory = new Memory(config);
await memory.add("I'm visiting Paris", { userId: "john" });
```

</CodeGroup>

### Config

Here are the parameters available for configuring Together embedder:

<Tabs>
<Tab title="Python">
| Parameter | Description | Default Value |
| --- | --- | --- |
| `model` | The name of the embedding model to use | `intfloat/multilingual-e5-large-instruct` |
| `embedding_dims` | Dimensions of the embedding model | `1024` |
| `api_key` | The Together API key | `None` |
</Tab>
<Tab title="TypeScript">
| Parameter | Description | Default Value |
| --- | --- | --- |
| `model` | The name of the embedding model to use | `intfloat/multilingual-e5-large-instruct` |
| `embeddingDims` | Dimensions of the embedding model for vector store configuration | `1024` |
| `apiKey` | The Together API key | `TOGETHER_API_KEY` |
| `baseURL` | Base URL for an OpenAI-compatible Together endpoint | `https://api.together.ai/v1` |
</Tab>
</Tabs>