## Documentation Index

Fetch the complete documentation index at: [/llms.txt](https://docs.mem0.ai/llms.txt)

Use this file to discover all available pages before exploring further.

To use Google AI embedding models, set the `GOOGLE_API_KEY` environment variables. You can obtain the Gemini API key from [here](https://aistudio.google.com/app/apikey).

### Usage

Python

TypeScript

```
import os
from mem0 import Memory

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

config = {
    "embedder": {
        "provider": "gemini",
        "config": {
            "model": "models/gemini-embedding-001",
        }
    }
}

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")
```

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

const config = {
  embedder: {
      provider: "google",
      config: {
        apiKey: process.env["GOOGLE_API_KEY"],
        model: "gemini-embedding-001",
        embeddingDims: 1536,
      },
    },
};

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: "john" });
```

### Config

Here are the parameters available for configuring Gemini embedder:

- Python

- TypeScript

| Parameter | Description | Default Value |
| --- | --- | --- |
| `model` | The name of the embedding model to use | `models/gemini-embedding-001` |
| `embedding_dims` | Dimensions of the embedding model | `768` |
| `api_key` | The Google API key | `None` |
| `output_dimensionality` | Output dimensionality for the embedding model (Gemini-specific; used when `embedding_dims` is not set) | `None` |

| Parameter | Description | Default Value |
| --- | --- | --- |
| `model` | The name of the embedding model to use | `gemini-embedding-001` |
| `embeddingDims` | Dimensions of the embedding model. When not set, uses the model’s native output dimensionality (3072 for `gemini-embedding-001`; MRL truncation to 768, 1536, or 3072 is supported) | `None` |
| `apiKey` | Google API key | `None` |