555e282cc4
pi-agent-plugin checks / lint (push) Has been cancelled
pi-agent-plugin checks / test (20) (push) Has been cancelled
pi-agent-plugin checks / test (22) (push) Has been cancelled
pi-agent-plugin checks / build (push) Has been cancelled
TypeScript SDK CI / check_changes (push) Has been cancelled
TypeScript SDK CI / changelog_check (push) Has been cancelled
ci / changelog_check (push) Has been cancelled
ci / check_changes (push) Has been cancelled
ci / build_mem0 (3.10) (push) Has been cancelled
ci / build_mem0 (3.11) (push) Has been cancelled
ci / build_mem0 (3.12) (push) Has been cancelled
CLI Node CI / lint (push) Has been cancelled
CLI Node CI / test (20) (push) Has been cancelled
CLI Node CI / test (22) (push) Has been cancelled
CLI Node CI / build (push) Has been cancelled
CLI Python CI / lint (push) Has been cancelled
CLI Python CI / test (3.10) (push) Has been cancelled
CLI Python CI / test (3.11) (push) Has been cancelled
CLI Python CI / test (3.12) (push) Has been cancelled
CLI Python CI / build (push) Has been cancelled
openclaw checks / lint (push) Has been cancelled
openclaw checks / test (20) (push) Has been cancelled
openclaw checks / test (22) (push) Has been cancelled
openclaw checks / build (push) Has been cancelled
opencode-plugin checks / build (push) Has been cancelled
TypeScript SDK CI / build_ts_sdk (20) (push) Has been cancelled
TypeScript SDK CI / build_ts_sdk (22) (push) Has been cancelled
TypeScript SDK CI / integration_ts_sdk (20) (push) Has been cancelled
TypeScript SDK CI / integration_ts_sdk (22) (push) Has been cancelled
68 lines
2.3 KiB
Plaintext
68 lines
2.3 KiB
Plaintext
---
|
|
title: AWS Bedrock
|
|
description: "Configure AWS Bedrock as an embedding provider in Mem0 with IAM credentials and boto3 authentication."
|
|
---
|
|
|
|
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](https://us-east-1.console.aws.amazon.com/bedrock/home?region=us-east-1#/modelaccess)
|
|
- Authenticate the boto3 client using a method described in the [AWS documentation](https://boto3.amazonaws.com/v1/documentation/api/latest/guide/credentials.html)
|
|
- 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` |
|
|
| `aws_region` | AWS region for the Bedrock client | `us-west-2` |
|
|
| `aws_access_key_id` | AWS access key ID for authentication | `None` |
|
|
| `aws_secret_access_key` | AWS secret access key for authentication | `None` |
|
|
| `aws_session_token` | AWS session token for temporary credentials | `None` |
|
|
</Tab>
|
|
</Tabs>
|