AWS Bedrock Integration

Route your AWS Bedrock traffic through Rivaro for runtime enforcement. InvokeModel and Converse API styles, AWS SigV4 authentication, and streaming.

Authentication

Bedrock is different from other providers: there is no API key header. Authentication uses AWS SigV4 request signing, which your AWS SDK handles automatically.

note

Your AWS SDK signs the request, then sends it through the Rivaro proxy. Rivaro passes all AWS signature headers through to Bedrock unchanged.

SDK Configuration

Python (boto3)

import boto3
from botocore.config import Config

bedrock = boto3.client(
    'bedrock-runtime',
    region_name='us-east-1',
    endpoint_url='https://your-org.rivaro.ai',
    config=Config(
        inject_host_prefix=False
    )
)

# Add X-Detection-Key via event system
def add_detection_key(params, **kwargs):
    params['headers']['X-Detection-Key'] = 'detect_live_your_key_here'

bedrock.meta.events.register('before-sign.bedrock-runtime.*', add_detection_key)

curl

# Note: AWS SigV4 signing is complex via curl.
# Use the AWS SDK for production. This example shows the URL structure.

curl https://your-org.rivaro.ai/model/anthropic.claude-3-sonnet-20240229-v1:0/invoke \
  -H "Content-Type: application/json" \
  -H "X-Detection-Key: detect_live_your_key_here" \
  -H "Authorization: AWS4-HMAC-SHA256 ..." \
  -H "X-Amz-Date: 20260221T100000Z" \
  -d '{
    "anthropic_version": "bedrock-2023-05-31",
    "messages": [{"role": "user", "content": "Hello"}],
    "max_tokens": 1024
  }'

Supported Endpoints

InvokeModel API (model-specific)

Endpoint	Method	Description
/model/{modelId}/invoke	POST	Invoke a model (non-streaming)
/model/{modelId}/invoke-with-response-stream	POST	Invoke with streaming

The request and response body format depends on the model. Common formats:

• Claude: Anthropic Messages format (messages, max_tokens)
• Llama / Mistral: Model-specific JSON
• Titan: Amazon Titan format

Converse API (standardized)

Endpoint	Method	Description
/converse	POST	Standardized conversation API
/converse-stream	POST	Standardized streaming conversation

The Converse API provides a unified request/response format across all Bedrock models, including support for tool use and vision.

InvokeModel vs Converse

Feature	InvokeModel	Converse
Request format	Model-specific	Standardized
Tool calling	Model-specific	Unified
Vision support	Model-specific	Unified
Streaming	/invoke-with-response-stream	/converse-stream
Recommendation	Legacy / specific needs	Preferred for new integrations

Converse Example

response = bedrock.converse(
    modelId='anthropic.claude-3-sonnet-20240229-v1:0',
    messages=[{
        'role': 'user',
        'content': [{'text': 'What is quantum computing?'}]
    }],
    inferenceConfig={
        'maxTokens': 1024,
        'temperature': 0.7
    }
)

print(response['output']['message']['content'][0]['text'])

Streaming

Bedrock streaming works through both API styles. The stream format varies by model family when using InvokeModel, but is standardized with Converse.

Enforcement follows the same pattern as other providers: content is forwarded in real time, detection runs on the accumulated response after the stream completes.

Completion markers by model format

Format	Completion marker
Claude	"stop_reason":"end_turn"
Llama / Mistral	"stop_reason":"stop"
Titan	"completionReason":"FINISH"
Converse	"stopReason":"end_turn"

Blocked Requests

When Rivaro blocks a request, the response format depends on the model format configured in the AppContext:

Claude format:

{
  "content": [{"type": "text", "text": "Content blocked due to policy violations"}],
  "stop_reason": "content_filtered"
}

Converse format:

{
  "output": {
    "message": {
      "content": [{"text": "Content blocked due to policy violations"}]
    }
  },
  "stopReason": "content_filtered"
}

AppContext Configuration

When creating an AppContext for Bedrock, the configuration map supports:

Key	Description
bedrockModelId	Full Bedrock model ARN (e.g. anthropic.claude-3-sonnet-20240229-v1:0)
bedrockModelFormat	Request/response format: claude, llama, mistral, titan, or converse

Required Headers

Header	Required	Description
X-Detection-Key	Yes	Your Rivaro detection key
Authorization	Yes	AWS SigV4 signature (set by AWS SDK)
X-Amz-Date	Yes	Request timestamp (set by AWS SDK)
X-Amz-Security-Token	Conditional	Session token (if using temporary credentials)
Content-Type	Yes	application/json

Next steps

• Error Handling — Handle Rivaro-specific errors
• Understanding Detections — What Rivaro scans for
• API Reference — Full endpoint reference