AWS Bedrock

Large Language Model service implementation using Amazon Bedrock API

Overview

AWSBedrockLLMService provides access to Amazon’s foundation models including Anthropic Claude and Amazon Nova, with streaming responses, function calling, and multimodal capabilities through Amazon’s managed AI service for enterprise-grade LLM deployment.

AWS Bedrock LLM API Reference

Pipecat’s API methods for AWS Bedrock integration

Example Implementation

Complete example with function calling

AWS Bedrock Documentation

Official AWS Bedrock documentation and features

AWS Console

Access foundation models and manage IAM

Installation

To use AWS Bedrock services, install the required dependencies:

uv add "pipecat-ai[aws]"

Prerequisites

AWS Account Setup

Before using AWS Bedrock LLM services, you need:

1. AWS Account: Sign up at AWS Console
2. IAM User: Create an IAM user with Amazon Bedrock permissions
3. Model Access: Request access to foundation models in your AWS region
4. Credentials: Set up AWS access keys and region configuration

Required Environment Variables

• AWS_ACCESS_KEY_ID: Your AWS access key ID
• AWS_SECRET_ACCESS_KEY: Your AWS secret access key
• AWS_SESSION_TOKEN: Session token (if using temporary credentials)
• AWS_REGION: AWS region (defaults to “us-east-1”)

Configuration

model · str · default: "None" · deprecated

AWS Bedrock model identifier (e.g., "us.anthropic.claude-sonnet-4-5-20250929-v1:0", "us.amazon.nova-pro-v1:0"). Deprecated in v0.0.105. Use settings=AWSBedrockLLMService.Settings(...) instead.

aws_access_key · str · default: "None"

AWS access key ID. If None, falls back to environment variables and the default botocore credential chain (instance profiles, IRSA, ECS task roles, SSO, etc.).

aws_secret_key · str · default: "None"

AWS secret access key. Same fallback behaviour as aws_access_key.

aws_session_token · str · default: "None"

AWS session token for temporary credentials.

aws_region · str · default: "None"

AWS region for the Bedrock service. If None, uses the AWS_REGION environment variable, defaulting to "us-east-1".

settings · AWSBedrockLLMService.Settings · default: "None"

Runtime-configurable model settings. See Settings below.

params · InputParams · default: "None" · deprecated

Runtime-configurable model settings. See Settings below. Deprecated in v0.0.105. Use settings=AWSBedrockLLMService.Settings(...) instead.

stop_sequences · List[str] · default: "None" · deprecated

List of strings that stop generation when encountered. Deprecated in v0.0.105. Use settings=AWSBedrockLLMService.Settings(stop_sequences=...) instead.

client_config · botocore.config.Config · default: "None"

Custom botocore client configuration. If None, uses defaults with 5-minute connect/read timeouts and 3 retry attempts.

retry_timeout_secs · float · default: "5.0"

Request timeout in seconds. Used when retry_on_timeout is enabled to determine when to retry.

retry_on_timeout · bool · default: "False"

Whether to retry the request once if it times out. The retry attempt has no timeout limit.

Settings

Runtime-configurable settings passed via the settings constructor argument using AWSBedrockLLMService.Settings(...). These can be updated mid-conversation with LLMUpdateSettingsFrame. See Service Settings for details.

Parameter	Type	Default	Description
model	str	None	AWS Bedrock model identifier. (Inherited from base settings.)
system_instruction	str	None	System instruction/prompt for the model. (Inherited from base settings.)
max_tokens	int	NOT_GIVEN	Maximum number of tokens to generate.
temperature	float	NOT_GIVEN	Sampling temperature (0.0 to 1.0). Lower values are more focused, higher values are more creative.
top_p	float	NOT_GIVEN	Top-p (nucleus) sampling (0.0 to 1.0). Controls diversity of output.
top_k	int	NOT_GIVEN	Top-k sampling parameter.
seed	int	NOT_GIVEN	Random seed for deterministic outputs.
stop_sequences	List[str]	NOT_GIVEN	List of strings that stop generation when encountered.
latency	str	NOT_GIVEN	Performance mode: "standard" or "optimized".
enable_prompt_caching	bool	NOT_GIVEN	Whether to enable prompt caching by adding cachePoint markers to system prompts and tool definitions. Can reduce TTFT by up to 85% for multi-turn conversations. See AWS docs.
additional_model_request_fields	dict	NOT_GIVEN	Additional model-specific parameters passed directly to the API.

NOT_GIVEN values are omitted from the inference config, letting the Bedrock API use its own defaults. Only parameters that are explicitly set are included in the request. This avoids conflicts with models that don’t allow certain parameter combinations (e.g., temperature and top_p together).

Usage

Basic Setup

from pipecat.services.aws import AWSBedrockLLMService

llm = AWSBedrockLLMService(
    model="us.anthropic.claude-sonnet-4-5-20250929-v1:0",
    aws_access_key=os.getenv("AWS_ACCESS_KEY_ID"),
    aws_secret_key=os.getenv("AWS_SECRET_ACCESS_KEY"),
    aws_region=os.getenv("AWS_REGION", "us-east-1"),
)

With Custom Settings

from pipecat.services.aws import AWSBedrockLLMService

llm = AWSBedrockLLMService(
    model="us.amazon.nova-pro-v1:0",
    aws_access_key=os.getenv("AWS_ACCESS_KEY_ID"),
    aws_secret_key=os.getenv("AWS_SECRET_ACCESS_KEY"),
    aws_region="us-east-1",
    settings=AWSBedrockLLMService.Settings(
        max_tokens=2048,
        temperature=0.7,
        latency="optimized",
    ),
)

Updating Settings at Runtime

Model settings can be changed mid-conversation using LLMUpdateSettingsFrame:

from pipecat.frames.frames import LLMUpdateSettingsFrame
from pipecat.services.aws.llm import AWSBedrockLLMSettings

await worker.queue_frame(
    LLMUpdateSettingsFrame(
        delta=AWSBedrockLLMSettings(
            temperature=0.3,
            max_tokens=1024,
        )
    )
)

The InputParams / params= pattern is deprecated as of v0.0.105. Use Settings / settings= instead. See the Service Settings guide for migration details.

Notes

• Credential resolution: Credentials are resolved via a fallback chain: explicit parameters → environment variables (AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY) → botocore credential provider chain (instance profiles, IRSA, ECS task roles, SSO, credential files). Services running with IAM roles no longer need to export static credentials.
• No-op tool handling: AWS Bedrock requires at least one tool to be defined when tool content exists in the conversation. The service automatically adds a placeholder tool when needed to prevent API errors.
• Model-specific parameters: Some models (e.g., Claude Sonnet 4.5) don’t allow certain parameter combinations. The service only includes explicitly set parameters in the inference config to avoid conflicts.
• Retry behavior: When retry_on_timeout=True, the first attempt uses the retry_timeout_secs timeout. If it times out, a second attempt is made with no timeout limit.
• System instruction precedence: If both system_instruction (from the constructor) and a system message in the context are set, the constructor’s system_instruction takes precedence and a warning is logged.

Event Handlers

AWSBedrockLLMService supports the following event handlers, inherited from LLMService:

Event	Description
on_completion_timeout	Called when an LLM completion request times out
on_function_calls_started	Called when function calls are received and execution is about to start

@llm.event_handler("on_completion_timeout")
async def on_completion_timeout(service):
    print("LLM completion timed out")