To use AWS Bedrock embedding models, you need to have the appropriate AWS credentials and permissions. The embeddings implementation relies on the boto3 library.

Setup

Ensure you have model access from the AWS Bedrock Console
Authenticate the boto3 client using a method described in the AWS documentation

Set up environment variables for authentication:

bash

export AWS_REGION=us-east-1
export AWS_ACCESS_KEY_ID=your-access-key
export AWS_SECRET_ACCESS_KEY=your-secret-key

Usage

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

For LLM if needed

os.environ["OPENAI_API_KEY"] = "your-openai-api-key"

AWS credentials

os.environ["AWS_REGION"] = "us-west-2" os.environ["AWS_ACCESS_KEY_ID"] = "your-access-key" os.environ["AWS_SECRET_ACCESS_KEY"] = "your-secret-key"

config = { "embedder": { "provider": "aws_bedrock", "config": { "model": "amazon.titan-embed-text-v2:0" } } }

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")

</CodeGroup>

### Config

Here are the parameters available for configuring AWS Bedrock embedder:

<Tabs>
<Tab title="Python">
| Parameter | Description | Default Value |
| --- | --- | --- |
| `model` | The name of the embedding model to use | `amazon.titan-embed-text-v1` |
</Tab>
</Tabs>