Amazon Bedrock Runtime examples using SDK for Python (Boto3)

Send a text message to AI21 Labs Jurassic-2, using Bedrock's Converse API.

# Use the Conversation API to send a text message to AI21 Labs Jurassic-2.

import boto3
from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region you want to use.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Jurassic-2 Mid.
model_id = "ai21.j2-mid-v1"

# Start a conversation with the user message.
user_message = "Describe the purpose of a 'hello world' program in one line."
conversation = [
    {
        "role": "user",
        "content": [{"text": user_message}],
    }
]

try:
    # Send the message to the model, using a basic inference configuration.
    response = client.converse(
        modelId=model_id,
        messages=conversation,
        inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9},
    )

    # Extract and print the response text.
    response_text = response["output"]["message"]["content"][0]["text"]
    print(response_text)

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

Use the Invoke Model API to send a text message.

# Use the native inference API to send a text message to AI21 Labs Jurassic-2.

import boto3
import json

from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Jurassic-2 Mid.
model_id = "ai21.j2-mid-v1"

# Define the prompt for the model.
prompt = "Describe the purpose of a 'hello world' program in one line."

# Format the request payload using the model's native structure.
native_request = {
    "prompt": prompt,
    "maxTokens": 512,
    "temperature": 0.5,
}

# Convert the native request to JSON.
request = json.dumps(native_request)

try:
    # Invoke the model with the request.
    response = client.invoke_model(modelId=model_id, body=request)

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

# Decode the response body.
model_response = json.loads(response["body"].read())

# Extract and print the response text.
response_text = model_response["completions"][0]["data"]["text"]
print(response_text)

Create an image with the Amazon Titan Image Generator.

# Use the native inference API to create an image with Amazon Titan Image Generator

import base64
import boto3
import json
import os
import random

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Titan Image Generator G1.
model_id = "amazon.titan-image-generator-v1"

# Define the image generation prompt for the model.
prompt = "A stylized picture of a cute old steampunk robot."

# Generate a random seed.
seed = random.randint(0, 2147483647)

# Format the request payload using the model's native structure.
native_request = {
    "taskType": "TEXT_IMAGE",
    "textToImageParams": {"text": prompt},
    "imageGenerationConfig": {
        "numberOfImages": 1,
        "quality": "standard",
        "cfgScale": 8.0,
        "height": 512,
        "width": 512,
        "seed": seed,
    },
}

# Convert the native request to JSON.
request = json.dumps(native_request)

# Invoke the model with the request.
response = client.invoke_model(modelId=model_id, body=request)

# Decode the response body.
model_response = json.loads(response["body"].read())

# Extract the image data.
base64_image_data = model_response["images"][0]

# Save the generated image to a local folder.
i, output_dir = 1, "output"
if not os.path.exists(output_dir):
    os.makedirs(output_dir)
while os.path.exists(os.path.join(output_dir, f"titan_{i}.png")):
    i += 1

image_data = base64.b64decode(base64_image_data)

image_path = os.path.join(output_dir, f"titan_{i}.png")
with open(image_path, "wb") as file:
    file.write(image_data)

print(f"The generated image has been saved to {image_path}")

Send a text message to Amazon Titan Text, using Bedrock's Converse API.

# Use the Conversation API to send a text message to Amazon Titan Text.

import boto3
from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region you want to use.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Titan Text Premier.
model_id = "amazon.titan-text-premier-v1:0"

# Start a conversation with the user message.
user_message = "Describe the purpose of a 'hello world' program in one line."
conversation = [
    {
        "role": "user",
        "content": [{"text": user_message}],
    }
]

try:
    # Send the message to the model, using a basic inference configuration.
    response = client.converse(
        modelId=model_id,
        messages=conversation,
        inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9},
    )

    # Extract and print the response text.
    response_text = response["output"]["message"]["content"][0]["text"]
    print(response_text)

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

Send a text message to Amazon Titan Text, using Bedrock's Converse API and process the response stream in real-time.

# Use the Conversation API to send a text message to Amazon Titan Text
# and print the response stream.

import boto3
from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region you want to use.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Titan Text Premier.
model_id = "amazon.titan-text-premier-v1:0"

# Start a conversation with the user message.
user_message = "Describe the purpose of a 'hello world' program in one line."
conversation = [
    {
        "role": "user",
        "content": [{"text": user_message}],
    }
]

try:
    # Send the message to the model, using a basic inference configuration.
    streaming_response = client.converse_stream(
        modelId=model_id,
        messages=conversation,
        inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9},
    )

    # Extract and print the streamed response text in real-time.
    for chunk in streaming_response["stream"]:
        if "contentBlockDelta" in chunk:
            text = chunk["contentBlockDelta"]["delta"]["text"]
            print(text, end="")

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

Use the Invoke Model API to send a text message.

# Use the native inference API to send a text message to Amazon Titan Text.

import boto3
import json

from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Titan Text Premier.
model_id = "amazon.titan-text-premier-v1:0"

# Define the prompt for the model.
prompt = "Describe the purpose of a 'hello world' program in one line."

# Format the request payload using the model's native structure.
native_request = {
    "inputText": prompt,
    "textGenerationConfig": {
        "maxTokenCount": 512,
        "temperature": 0.5,
    },
}

# Convert the native request to JSON.
request = json.dumps(native_request)

try:
    # Invoke the model with the request.
    response = client.invoke_model(modelId=model_id, body=request)

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

# Decode the response body.
model_response = json.loads(response["body"].read())

# Extract and print the response text.
response_text = model_response["results"][0]["outputText"]
print(response_text)

Use the Invoke Model API to send a text message and process the response stream in real-time.

# Use the native inference API to send a text message to Amazon Titan Text
# and print the response stream.

import boto3
import json

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Titan Text Premier.
model_id = "amazon.titan-text-premier-v1:0"

# Define the prompt for the model.
prompt = "Describe the purpose of a 'hello world' program in one line."

# Format the request payload using the model's native structure.
native_request = {
    "inputText": prompt,
    "textGenerationConfig": {
        "maxTokenCount": 512,
        "temperature": 0.5,
    },
}

# Convert the native request to JSON.
request = json.dumps(native_request)

# Invoke the model with the request.
streaming_response = client.invoke_model_with_response_stream(
    modelId=model_id, body=request
)

# Extract and print the response text in real-time.
for event in streaming_response["body"]:
    chunk = json.loads(event["chunk"]["bytes"])
    if "outputText" in chunk:
        print(chunk["outputText"], end="")

Create your first embedding with Amazon Titan Text Embeddings.

# Generate and print an embedding with Amazon Titan Text Embeddings V2.

import boto3
import json

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Titan Text Embeddings V2.
model_id = "amazon.titan-embed-text-v2:0"

# The text to convert to an embedding.
input_text = "Please recommend books with a theme similar to the movie 'Inception'."

# Create the request for the model.
native_request = {"inputText": input_text}

# Convert the native request to JSON.
request = json.dumps(native_request)

# Invoke the model with the request.
response = client.invoke_model(modelId=model_id, body=request)

# Decode the model's native response body.
model_response = json.loads(response["body"].read())

# Extract and print the generated embedding and the input text token count.
embedding = model_response["embedding"]
input_token_count = model_response["inputTextTokenCount"]

print("\nYour input:")
print(input_text)
print(f"Number of input tokens: {input_token_count}")
print(f"Size of the generated embedding: {len(embedding)}")
print("Embedding:")
print(embedding)

Send a text message to Anthropic Claude, using Bedrock's Converse API.

# Use the Conversation API to send a text message to Anthropic Claude.

import boto3
from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region you want to use.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Claude 3 Haiku.
model_id = "anthropic.claude-3-haiku-20240307-v1:0"

# Start a conversation with the user message.
user_message = "Describe the purpose of a 'hello world' program in one line."
conversation = [
    {
        "role": "user",
        "content": [{"text": user_message}],
    }
]

try:
    # Send the message to the model, using a basic inference configuration.
    response = client.converse(
        modelId=model_id,
        messages=conversation,
        inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9},
    )

    # Extract and print the response text.
    response_text = response["output"]["message"]["content"][0]["text"]
    print(response_text)

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

Send a text message to Anthropic Claude, using Bedrock's Converse API and process the response stream in real-time.

# Use the Conversation API to send a text message to Anthropic Claude
# and print the response stream.

import boto3
from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region you want to use.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Claude 3 Haiku.
model_id = "anthropic.claude-3-haiku-20240307-v1:0"

# Start a conversation with the user message.
user_message = "Describe the purpose of a 'hello world' program in one line."
conversation = [
    {
        "role": "user",
        "content": [{"text": user_message}],
    }
]

try:
    # Send the message to the model, using a basic inference configuration.
    streaming_response = client.converse_stream(
        modelId=model_id,
        messages=conversation,
        inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9},
    )

    # Extract and print the streamed response text in real-time.
    for chunk in streaming_response["stream"]:
        if "contentBlockDelta" in chunk:
            text = chunk["contentBlockDelta"]["delta"]["text"]
            print(text, end="")

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

Use the Invoke Model API to send a text message.

# Use the native inference API to send a text message to Anthropic Claude.

import boto3
import json

from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Claude 3 Haiku.
model_id = "anthropic.claude-3-haiku-20240307-v1:0"

# Define the prompt for the model.
prompt = "Describe the purpose of a 'hello world' program in one line."

# Format the request payload using the model's native structure.
native_request = {
    "anthropic_version": "bedrock-2023-05-31",
    "max_tokens": 512,
    "temperature": 0.5,
    "messages": [
        {
            "role": "user",
            "content": [{"type": "text", "text": prompt}],
        }
    ],
}

# Convert the native request to JSON.
request = json.dumps(native_request)

try:
    # Invoke the model with the request.
    response = client.invoke_model(modelId=model_id, body=request)

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

# Decode the response body.
model_response = json.loads(response["body"].read())

# Extract and print the response text.
response_text = model_response["content"][0]["text"]
print(response_text)

Use the Invoke Model API to send a text message and process the response stream in real-time.

# Use the native inference API to send a text message to Anthropic Claude
# and print the response stream.

import boto3
import json

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Claude 3 Haiku.
model_id = "anthropic.claude-3-haiku-20240307-v1:0"

# Define the prompt for the model.
prompt = "Describe the purpose of a 'hello world' program in one line."

# Format the request payload using the model's native structure.
native_request = {
    "anthropic_version": "bedrock-2023-05-31",
    "max_tokens": 512,
    "temperature": 0.5,
    "messages": [
        {
            "role": "user",
            "content": [{"type": "text", "text": prompt}],
        }
    ],
}

# Convert the native request to JSON.
request = json.dumps(native_request)

# Invoke the model with the request.
streaming_response = client.invoke_model_with_response_stream(
    modelId=model_id, body=request
)

# Extract and print the response text in real-time.
for event in streaming_response["body"]:
    chunk = json.loads(event["chunk"]["bytes"])
    if chunk["type"] == "content_block_delta":
        print(chunk["delta"].get("text", ""), end="")

The primary execution script of the demo. This script orchestrates the conversation between the user, the Amazon Bedrock Converse API, and a weather tool.

# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
# SPDX-License-Identifier: Apache-2.0

"""
This demo illustrates a tool use scenario using Amazon Bedrock's Converse API and a weather tool.
The script interacts with a foundation model on Amazon Bedrock to provide weather information based on user
input. It uses the Open-Meteo API (https://open-meteo.com) to retrieve current weather data for a given location.
"""

import boto3
import logging
from enum import Enum

import utils.tool_use_print_utils as output
import weather_tool

logging.basicConfig(level=logging.INFO, format="%(message)s")

AWS_REGION = "us-east-1"


# For the most recent list of models supported by the Converse API's tool use functionality, visit:
# https://docs.aws.amazon.com/bedrock/latest/userguide/conversation-inference.html
class SupportedModels(Enum):
    CLAUDE_OPUS = "anthropic.claude-3-opus-20240229-v1:0"
    CLAUDE_SONNET = "anthropic.claude-3-sonnet-20240229-v1:0"
    CLAUDE_HAIKU = "anthropic.claude-3-haiku-20240307-v1:0"
    COHERE_COMMAND_R = "cohere.command-r-v1:0"
    COHERE_COMMAND_R_PLUS = "cohere.command-r-plus-v1:0"


# Set the model ID, e.g., Claude 3 Haiku.
MODEL_ID = SupportedModels.CLAUDE_HAIKU.value

SYSTEM_PROMPT = """
You are a weather assistant that provides current weather data for user-specified locations using only
the Weather_Tool, which expects latitude and longitude. Infer the coordinates from the location yourself.
If the user provides coordinates, infer the approximate location and refer to it in your response.
To use the tool, you strictly apply the provided tool specification.

- Explain your step-by-step process, and give brief updates before each step.
- Only use the Weather_Tool for data. Never guess or make up information. 
- Repeat the tool use for subsequent requests if necessary.
- If the tool errors, apologize, explain weather is unavailable, and suggest other options.
- Report temperatures in °C (°F) and wind in km/h (mph). Keep weather reports concise. Sparingly use
  emojis where appropriate.
- Only respond to weather queries. Remind off-topic users of your purpose. 
- Never claim to search online, access external data, or use tools besides Weather_Tool.
- Complete the entire process until you have all required data before sending the complete response.
"""

# The maximum number of recursive calls allowed in the tool_use_demo function.
# This helps prevent infinite loops and potential performance issues.
MAX_RECURSIONS = 5


class ToolUseDemo:
    """
    Demonstrates the tool use feature with the Amazon Bedrock Converse API.
    """

    def __init__(self):
        # Prepare the system prompt
        self.system_prompt = [{"text": SYSTEM_PROMPT}]

        # Prepare the tool configuration with the weather tool's specification
        self.tool_config = {"tools": [weather_tool.get_tool_spec()]}

        # Create a Bedrock Runtime client in the specified AWS Region.
        self.bedrockRuntimeClient = boto3.client(
            "bedrock-runtime", region_name=AWS_REGION
        )

    def run(self):
        """
        Starts the conversation with the user and handles the interaction with Bedrock.
        """
        # Print the greeting and a short user guide
        output.header()

        # Start with an emtpy conversation
        conversation = []

        # Get the first user input
        user_input = self._get_user_input()

        while user_input is not None:
            # Create a new message with the user input and append it to the conversation
            message = {"role": "user", "content": [{"text": user_input}]}
            conversation.append(message)

            # Send the conversation to Amazon Bedrock
            bedrock_response = self._send_conversation_to_bedrock(conversation)

            # Recursively handle the model's response until the model has returned
            # its final response or the recursion counter has reached 0
            self._process_model_response(
                bedrock_response, conversation, max_recursion=MAX_RECURSIONS
            )

            # Repeat the loop until the user decides to exit the application
            user_input = self._get_user_input()

        output.footer()

    def _send_conversation_to_bedrock(self, conversation):
        """
        Sends the conversation, the system prompt, and the tool spec to Amazon Bedrock, and returns the response.

        :param conversation: The conversation history including the next message to send.
        :return: The response from Amazon Bedrock.
        """
        output.call_to_bedrock(conversation)

        # Send the conversation, system prompt, and tool configuration, and return the response
        return self.bedrockRuntimeClient.converse(
            modelId=MODEL_ID,
            messages=conversation,
            system=self.system_prompt,
            toolConfig=self.tool_config,
        )

    def _process_model_response(
            self, model_response, conversation, max_recursion=MAX_RECURSIONS
    ):
        """
        Processes the response received via Amazon Bedrock and performs the necessary actions
        based on the stop reason.

        :param model_response: The model's response returned via Amazon Bedrock.
        :param conversation: The conversation history.
        :param max_recursion: The maximum number of recursive calls allowed.
        """

        if max_recursion <= 0:
            # Stop the process, the number of recursive calls could indicate an infinite loop
            logging.warning(
                "Warning: Maximum number of recursions reached. Please try again."
            )
            exit(1)

        # Append the model's response to the ongoing conversation
        message = model_response["output"]["message"]
        conversation.append(message)

        if model_response["stopReason"] == "tool_use":
            # If the stop reason is "tool_use", forward everything to the tool use handler
            self._handle_tool_use(message, conversation, max_recursion)

        if model_response["stopReason"] == "end_turn":
            # If the stop reason is "end_turn", print the model's response text, and finish the process
            output.model_response(message["content"][0]["text"])
            return

    def _handle_tool_use(
            self, model_response, conversation, max_recursion=MAX_RECURSIONS
    ):
        """
        Handles the tool use case by invoking the specified tool and sending the tool's response back to Bedrock.
        The tool response is appended to the conversation, and the conversation is sent back to Amazon Bedrock for further processing.

        :param model_response: The model's response containing the tool use request.
        :param conversation: The conversation history.
        :param max_recursion: The maximum number of recursive calls allowed.
        """

        # Initialize an empty list of tool results
        tool_results = []

        # The model's response can consist of multiple content blocks
        for content_block in model_response["content"]:
            if "text" in content_block:
                # If the content block contains text, print it to the console
                output.model_response(content_block["text"])

            if "toolUse" in content_block:
                # If the content block is a tool use request, forward it to the tool
                tool_response = self._invoke_tool(content_block["toolUse"])

                # Add the tool use ID and the tool's response to the list of results
                tool_results.append(
                    {
                        "toolResult": {
                            "toolUseId": (tool_response["toolUseId"]),
                            "content": [{"json": tool_response["content"]}],
                        }
                    }
                )

        # Embed the tool results in a new user message
        message = {"role": "user", "content": tool_results}

        # Append the new message to the ongoing conversation
        conversation.append(message)

        # Send the conversation to Amazon Bedrock
        response = self._send_conversation_to_bedrock(conversation)

        # Recursively handle the model's response until the model has returned
        # its final response or the recursion counter has reached 0
        self._process_model_response(response, conversation, max_recursion - 1)

    def _invoke_tool(self, payload):
        """
        Invokes the specified tool with the given payload and returns the tool's response.
        If the requested tool does not exist, an error message is returned.

        :param payload: The payload containing the tool name and input data.
        :return: The tool's response or an error message.
        """
        tool_name = payload["name"]

        if tool_name == "Weather_Tool":
            input_data = payload["input"]
            output.tool_use(tool_name, input_data)

            # Invoke the weather tool with the input data provided by
            response = weather_tool.fetch_weather_data(input_data)
        else:
            error_message = (
                f"The requested tool with name '{tool_name}' does not exist."
            )
            response = {"error": "true", "message": error_message}

        return {"toolUseId": payload["toolUseId"], "content": response}

    @staticmethod
    def _get_user_input(prompt="Your weather info request"):
        """
        Prompts the user for input and returns the user's response.
        Returns None if the user enters 'x' to exit.

        :param prompt: The prompt to display to the user.
        :return: The user's input or None if the user chooses to exit.
        """
        output.separator()
        user_input = input(f"{prompt} (x to exit): ")

        if user_input == "":
            prompt = "Please enter your weather info request, e.g. the name of a city"
            return ToolUseDemo._get_user_input(prompt)

        elif user_input.lower() == "x":
            return None

        else:
            return user_input


if __name__ == "__main__":
    tool_use_demo = ToolUseDemo()
    tool_use_demo.run()

The weather tool used by the demo. This script defines the tool specification and implements the logic to retrieve weather data using from the Open-Meteo API.

# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
# SPDX-License-Identifier: Apache-2.0

import requests
from requests.exceptions import RequestException


def get_tool_spec():
    """
    Returns the JSON Schema specification for the Weather tool. The tool specification
    defines the input schema and describes the tool's functionality.
    For more information, see https://json-schema.org/understanding-json-schema/reference.

    :return: The tool specification for the Weather tool.
    """
    return {
        "toolSpec": {
            "name": "Weather_Tool",
            "description": "Get the current weather for a given location, based on its WGS84 coordinates.",
            "inputSchema": {
                "json": {
                    "type": "object",
                    "properties": {
                        "latitude": {
                            "type": "string",
                            "description": "Geographical WGS84 latitude of the location.",
                        },
                        "longitude": {
                            "type": "string",
                            "description": "Geographical WGS84 longitude of the location.",
                        },
                    },
                    "required": ["latitude", "longitude"],
                }
            },
        }
    }


def fetch_weather_data(input_data):
    """
    Fetches weather data for the given latitude and longitude using the Open-Meteo API.
    Returns the weather data or an error message if the request fails.

    :param input_data: The input data containing the latitude and longitude.
    :return: The weather data or an error message.
    """
    endpoint = "https://api.open-meteo.com/v1/forecast"
    latitude = input_data.get("latitude")
    longitude = input_data.get("longitude", "")
    params = {"latitude": latitude, "longitude": longitude, "current_weather": True}

    try:
        response = requests.get(endpoint, params=params)
        weather_data = {"weather_data": response.json()}
        response.raise_for_status()
        return weather_data
    except RequestException as e:
        return e.response.json()
    except Exception as e:
        return {"error": type(e), "message": str(e)}

Send a text message to Cohere Command, using Bedrock's Converse API.

# Use the Conversation API to send a text message to Cohere Command.

import boto3
from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region you want to use.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Command R.
model_id = "cohere.command-r-v1:0"

# Start a conversation with the user message.
user_message = "Describe the purpose of a 'hello world' program in one line."
conversation = [
    {
        "role": "user",
        "content": [{"text": user_message}],
    }
]

try:
    # Send the message to the model, using a basic inference configuration.
    response = client.converse(
        modelId=model_id,
        messages=conversation,
        inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9},
    )

    # Extract and print the response text.
    response_text = response["output"]["message"]["content"][0]["text"]
    print(response_text)

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

Send a text message to Cohere Command, using Bedrock's Converse API and process the response stream in real-time.

# Use the Conversation API to send a text message to Cohere Command
# and print the response stream.

import boto3
from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region you want to use.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Command R.
model_id = "cohere.command-r-v1:0"

# Start a conversation with the user message.
user_message = "Describe the purpose of a 'hello world' program in one line."
conversation = [
    {
        "role": "user",
        "content": [{"text": user_message}],
    }
]

try:
    # Send the message to the model, using a basic inference configuration.
    streaming_response = client.converse_stream(
        modelId=model_id,
        messages=conversation,
        inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9},
    )

    # Extract and print the streamed response text in real-time.
    for chunk in streaming_response["stream"]:
        if "contentBlockDelta" in chunk:
            text = chunk["contentBlockDelta"]["delta"]["text"]
            print(text, end="")

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

Use the Invoke Model API to send a text message.

# Use the native inference API to send a text message to Cohere Command R and R+.

import boto3
import json

from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Command R.
model_id = "cohere.command-r-v1:0"

# Define the prompt for the model.
prompt = "Describe the purpose of a 'hello world' program in one line."

# Format the request payload using the model's native structure.
native_request = {
    "message": prompt,
    "max_tokens": 512,
    "temperature": 0.5,
}

# Convert the native request to JSON.
request = json.dumps(native_request)

try:
    # Invoke the model with the request.
    response = client.invoke_model(modelId=model_id, body=request)

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

# Decode the response body.
model_response = json.loads(response["body"].read())

# Extract and print the response text.
response_text = model_response["text"]
print(response_text)

Use the Invoke Model API to send a text message.

# Use the native inference API to send a text message to Cohere Command.

import boto3
import json

from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Command Light.
model_id = "cohere.command-light-text-v14"

# Define the prompt for the model.
prompt = "Describe the purpose of a 'hello world' program in one line."

# Format the request payload using the model's native structure.
native_request = {
    "prompt": prompt,
    "max_tokens": 512,
    "temperature": 0.5,
}

# Convert the native request to JSON.
request = json.dumps(native_request)

try:
    # Invoke the model with the request.
    response = client.invoke_model(modelId=model_id, body=request)

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

# Decode the response body.
model_response = json.loads(response["body"].read())

# Extract and print the response text.
response_text = model_response["generations"][0]["text"]
print(response_text)

Use the Invoke Model API to send a text message and process the response stream in real-time.

# Use the native inference API to send a text message to Cohere Command R and R+
# and print the response stream.

import boto3
import json

from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Command R.
model_id = "cohere.command-r-v1:0"

# Define the prompt for the model.
prompt = "Describe the purpose of a 'hello world' program in one line."

# Format the request payload using the model's native structure.
native_request = {
    "message": prompt,
    "max_tokens": 512,
    "temperature": 0.5,
}

# Convert the native request to JSON.
request = json.dumps(native_request)

try:
    # Invoke the model with the request.
    streaming_response = client.invoke_model_with_response_stream(
        modelId=model_id, body=request
    )

    # Extract and print the response text in real-time.
    for event in streaming_response["body"]:
        chunk = json.loads(event["chunk"]["bytes"])
        if "generations" in chunk:
            print(chunk["generations"][0]["text"], end="")

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

Use the Invoke Model API to send a text message and process the response stream in real-time.

# Use the native inference API to send a text message to Cohere Command
# and print the response stream.

import boto3
import json

from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Command Light.
model_id = "cohere.command-light-text-v14"

# Define the prompt for the model.
prompt = "Describe the purpose of a 'hello world' program in one line."

# Format the request payload using the model's native structure.
native_request = {
    "prompt": prompt,
    "max_tokens": 512,
    "temperature": 0.5,
}

# Convert the native request to JSON.
request = json.dumps(native_request)

try:
    # Invoke the model with the request.
    streaming_response = client.invoke_model_with_response_stream(
        modelId=model_id, body=request
    )

    # Extract and print the response text in real-time.
    for event in streaming_response["body"]:
        chunk = json.loads(event["chunk"]["bytes"])
        if "generations" in chunk:
            print(chunk["generations"][0]["text"], end="")

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

The primary execution script of the demo. This script orchestrates the conversation between the user, the Amazon Bedrock Converse API, and a weather tool.

# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
# SPDX-License-Identifier: Apache-2.0

"""
This demo illustrates a tool use scenario using Amazon Bedrock's Converse API and a weather tool.
The script interacts with a foundation model on Amazon Bedrock to provide weather information based on user
input. It uses the Open-Meteo API (https://open-meteo.com) to retrieve current weather data for a given location.
"""

import boto3
import logging
from enum import Enum

import utils.tool_use_print_utils as output
import weather_tool

logging.basicConfig(level=logging.INFO, format="%(message)s")

AWS_REGION = "us-east-1"


# For the most recent list of models supported by the Converse API's tool use functionality, visit:
# https://docs.aws.amazon.com/bedrock/latest/userguide/conversation-inference.html
class SupportedModels(Enum):
    CLAUDE_OPUS = "anthropic.claude-3-opus-20240229-v1:0"
    CLAUDE_SONNET = "anthropic.claude-3-sonnet-20240229-v1:0"
    CLAUDE_HAIKU = "anthropic.claude-3-haiku-20240307-v1:0"
    COHERE_COMMAND_R = "cohere.command-r-v1:0"
    COHERE_COMMAND_R_PLUS = "cohere.command-r-plus-v1:0"


# Set the model ID, e.g., Claude 3 Haiku.
MODEL_ID = SupportedModels.CLAUDE_HAIKU.value

SYSTEM_PROMPT = """
You are a weather assistant that provides current weather data for user-specified locations using only
the Weather_Tool, which expects latitude and longitude. Infer the coordinates from the location yourself.
If the user provides coordinates, infer the approximate location and refer to it in your response.
To use the tool, you strictly apply the provided tool specification.

- Explain your step-by-step process, and give brief updates before each step.
- Only use the Weather_Tool for data. Never guess or make up information. 
- Repeat the tool use for subsequent requests if necessary.
- If the tool errors, apologize, explain weather is unavailable, and suggest other options.
- Report temperatures in °C (°F) and wind in km/h (mph). Keep weather reports concise. Sparingly use
  emojis where appropriate.
- Only respond to weather queries. Remind off-topic users of your purpose. 
- Never claim to search online, access external data, or use tools besides Weather_Tool.
- Complete the entire process until you have all required data before sending the complete response.
"""

# The maximum number of recursive calls allowed in the tool_use_demo function.
# This helps prevent infinite loops and potential performance issues.
MAX_RECURSIONS = 5


class ToolUseDemo:
    """
    Demonstrates the tool use feature with the Amazon Bedrock Converse API.
    """

    def __init__(self):
        # Prepare the system prompt
        self.system_prompt = [{"text": SYSTEM_PROMPT}]

        # Prepare the tool configuration with the weather tool's specification
        self.tool_config = {"tools": [weather_tool.get_tool_spec()]}

        # Create a Bedrock Runtime client in the specified AWS Region.
        self.bedrockRuntimeClient = boto3.client(
            "bedrock-runtime", region_name=AWS_REGION
        )

    def run(self):
        """
        Starts the conversation with the user and handles the interaction with Bedrock.
        """
        # Print the greeting and a short user guide
        output.header()

        # Start with an emtpy conversation
        conversation = []

        # Get the first user input
        user_input = self._get_user_input()

        while user_input is not None:
            # Create a new message with the user input and append it to the conversation
            message = {"role": "user", "content": [{"text": user_input}]}
            conversation.append(message)

            # Send the conversation to Amazon Bedrock
            bedrock_response = self._send_conversation_to_bedrock(conversation)

            # Recursively handle the model's response until the model has returned
            # its final response or the recursion counter has reached 0
            self._process_model_response(
                bedrock_response, conversation, max_recursion=MAX_RECURSIONS
            )

            # Repeat the loop until the user decides to exit the application
            user_input = self._get_user_input()

        output.footer()

    def _send_conversation_to_bedrock(self, conversation):
        """
        Sends the conversation, the system prompt, and the tool spec to Amazon Bedrock, and returns the response.

        :param conversation: The conversation history including the next message to send.
        :return: The response from Amazon Bedrock.
        """
        output.call_to_bedrock(conversation)

        # Send the conversation, system prompt, and tool configuration, and return the response
        return self.bedrockRuntimeClient.converse(
            modelId=MODEL_ID,
            messages=conversation,
            system=self.system_prompt,
            toolConfig=self.tool_config,
        )

    def _process_model_response(
            self, model_response, conversation, max_recursion=MAX_RECURSIONS
    ):
        """
        Processes the response received via Amazon Bedrock and performs the necessary actions
        based on the stop reason.

        :param model_response: The model's response returned via Amazon Bedrock.
        :param conversation: The conversation history.
        :param max_recursion: The maximum number of recursive calls allowed.
        """

        if max_recursion <= 0:
            # Stop the process, the number of recursive calls could indicate an infinite loop
            logging.warning(
                "Warning: Maximum number of recursions reached. Please try again."
            )
            exit(1)

        # Append the model's response to the ongoing conversation
        message = model_response["output"]["message"]
        conversation.append(message)

        if model_response["stopReason"] == "tool_use":
            # If the stop reason is "tool_use", forward everything to the tool use handler
            self._handle_tool_use(message, conversation, max_recursion)

        if model_response["stopReason"] == "end_turn":
            # If the stop reason is "end_turn", print the model's response text, and finish the process
            output.model_response(message["content"][0]["text"])
            return

    def _handle_tool_use(
            self, model_response, conversation, max_recursion=MAX_RECURSIONS
    ):
        """
        Handles the tool use case by invoking the specified tool and sending the tool's response back to Bedrock.
        The tool response is appended to the conversation, and the conversation is sent back to Amazon Bedrock for further processing.

        :param model_response: The model's response containing the tool use request.
        :param conversation: The conversation history.
        :param max_recursion: The maximum number of recursive calls allowed.
        """

        # Initialize an empty list of tool results
        tool_results = []

        # The model's response can consist of multiple content blocks
        for content_block in model_response["content"]:
            if "text" in content_block:
                # If the content block contains text, print it to the console
                output.model_response(content_block["text"])

            if "toolUse" in content_block:
                # If the content block is a tool use request, forward it to the tool
                tool_response = self._invoke_tool(content_block["toolUse"])

                # Add the tool use ID and the tool's response to the list of results
                tool_results.append(
                    {
                        "toolResult": {
                            "toolUseId": (tool_response["toolUseId"]),
                            "content": [{"json": tool_response["content"]}],
                        }
                    }
                )

        # Embed the tool results in a new user message
        message = {"role": "user", "content": tool_results}

        # Append the new message to the ongoing conversation
        conversation.append(message)

        # Send the conversation to Amazon Bedrock
        response = self._send_conversation_to_bedrock(conversation)

        # Recursively handle the model's response until the model has returned
        # its final response or the recursion counter has reached 0
        self._process_model_response(response, conversation, max_recursion - 1)

    def _invoke_tool(self, payload):
        """
        Invokes the specified tool with the given payload and returns the tool's response.
        If the requested tool does not exist, an error message is returned.

        :param payload: The payload containing the tool name and input data.
        :return: The tool's response or an error message.
        """
        tool_name = payload["name"]

        if tool_name == "Weather_Tool":
            input_data = payload["input"]
            output.tool_use(tool_name, input_data)

            # Invoke the weather tool with the input data provided by
            response = weather_tool.fetch_weather_data(input_data)
        else:
            error_message = (
                f"The requested tool with name '{tool_name}' does not exist."
            )
            response = {"error": "true", "message": error_message}

        return {"toolUseId": payload["toolUseId"], "content": response}

    @staticmethod
    def _get_user_input(prompt="Your weather info request"):
        """
        Prompts the user for input and returns the user's response.
        Returns None if the user enters 'x' to exit.

        :param prompt: The prompt to display to the user.
        :return: The user's input or None if the user chooses to exit.
        """
        output.separator()
        user_input = input(f"{prompt} (x to exit): ")

        if user_input == "":
            prompt = "Please enter your weather info request, e.g. the name of a city"
            return ToolUseDemo._get_user_input(prompt)

        elif user_input.lower() == "x":
            return None

        else:
            return user_input


if __name__ == "__main__":
    tool_use_demo = ToolUseDemo()
    tool_use_demo.run()

The weather tool used by the demo. This script defines the tool specification and implements the logic to retrieve weather data using from the Open-Meteo API.

# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
# SPDX-License-Identifier: Apache-2.0

import requests
from requests.exceptions import RequestException


def get_tool_spec():
    """
    Returns the JSON Schema specification for the Weather tool. The tool specification
    defines the input schema and describes the tool's functionality.
    For more information, see https://json-schema.org/understanding-json-schema/reference.

    :return: The tool specification for the Weather tool.
    """
    return {
        "toolSpec": {
            "name": "Weather_Tool",
            "description": "Get the current weather for a given location, based on its WGS84 coordinates.",
            "inputSchema": {
                "json": {
                    "type": "object",
                    "properties": {
                        "latitude": {
                            "type": "string",
                            "description": "Geographical WGS84 latitude of the location.",
                        },
                        "longitude": {
                            "type": "string",
                            "description": "Geographical WGS84 longitude of the location.",
                        },
                    },
                    "required": ["latitude", "longitude"],
                }
            },
        }
    }


def fetch_weather_data(input_data):
    """
    Fetches weather data for the given latitude and longitude using the Open-Meteo API.
    Returns the weather data or an error message if the request fails.

    :param input_data: The input data containing the latitude and longitude.
    :return: The weather data or an error message.
    """
    endpoint = "https://api.open-meteo.com/v1/forecast"
    latitude = input_data.get("latitude")
    longitude = input_data.get("longitude", "")
    params = {"latitude": latitude, "longitude": longitude, "current_weather": True}

    try:
        response = requests.get(endpoint, params=params)
        weather_data = {"weather_data": response.json()}
        response.raise_for_status()
        return weather_data
    except RequestException as e:
        return e.response.json()
    except Exception as e:
        return {"error": type(e), "message": str(e)}

Send a text message to Meta Llama, using Bedrock's Converse API.

# Use the Conversation API to send a text message to Meta Llama.

import boto3
from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region you want to use.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Llama 3 8b Instruct.
model_id = "meta.llama3-8b-instruct-v1:0"

# Start a conversation with the user message.
user_message = "Describe the purpose of a 'hello world' program in one line."
conversation = [
    {
        "role": "user",
        "content": [{"text": user_message}],
    }
]

try:
    # Send the message to the model, using a basic inference configuration.
    response = client.converse(
        modelId=model_id,
        messages=conversation,
        inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9},
    )

    # Extract and print the response text.
    response_text = response["output"]["message"]["content"][0]["text"]
    print(response_text)

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

Send a text message to Meta Llama, using Bedrock's Converse API and process the response stream in real-time.

# Use the Conversation API to send a text message to Meta Llama
# and print the response stream.

import boto3
from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region you want to use.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Llama 3 8b Instruct.
model_id = "meta.llama3-8b-instruct-v1:0"

# Start a conversation with the user message.
user_message = "Describe the purpose of a 'hello world' program in one line."
conversation = [
    {
        "role": "user",
        "content": [{"text": user_message}],
    }
]

try:
    # Send the message to the model, using a basic inference configuration.
    streaming_response = client.converse_stream(
        modelId=model_id,
        messages=conversation,
        inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9},
    )

    # Extract and print the streamed response text in real-time.
    for chunk in streaming_response["stream"]:
        if "contentBlockDelta" in chunk:
            text = chunk["contentBlockDelta"]["delta"]["text"]
            print(text, end="")

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

Use the Invoke Model API to send a text message.

# Use the native inference API to send a text message to Meta Llama 2.

import boto3
import json

from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Llama 2 Chat 13B.
model_id = "meta.llama2-13b-chat-v1"

# Define the prompt for the model.
prompt = "Describe the purpose of a 'hello world' program in one line."

# Embed the prompt in Llama 2's instruction format.
formatted_prompt = f"<s>[INST] {prompt} [/INST]"

# Format the request payload using the model's native structure.
native_request = {
    "prompt": formatted_prompt,
    "max_gen_len": 512,
    "temperature": 0.5,
}

# Convert the native request to JSON.
request = json.dumps(native_request)

try:
    # Invoke the model with the request.
    response = client.invoke_model(modelId=model_id, body=request)

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

# Decode the response body.
model_response = json.loads(response["body"].read())

# Extract and print the response text.
response_text = model_response["generation"]
print(response_text)

Use the Invoke Model API to send a text message.

# Use the native inference API to send a text message to Meta Llama 3.

import boto3
import json

from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Llama 3 8b Instruct.
model_id = "meta.llama3-8b-instruct-v1:0"

# Define the prompt for the model.
prompt = "Describe the purpose of a 'hello world' program in one line."

# Embed the prompt in Llama 3's instruction format.
formatted_prompt = f"""
<|begin_of_text|>
<|start_header_id|>user<|end_header_id|>
{prompt}
<|eot_id|>
<|start_header_id|>assistant<|end_header_id|>
"""

# Format the request payload using the model's native structure.
native_request = {
    "prompt": formatted_prompt,
    "max_gen_len": 512,
    "temperature": 0.5,
}

# Convert the native request to JSON.
request = json.dumps(native_request)

try:
    # Invoke the model with the request.
    response = client.invoke_model(modelId=model_id, body=request)

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

# Decode the response body.
model_response = json.loads(response["body"].read())

# Extract and print the response text.
response_text = model_response["generation"]
print(response_text)

Use the Invoke Model API to send a text message and process the response stream in real-time.

# Use the native inference API to send a text message to Meta Llama 2
# and print the response stream.

import boto3
import json

from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Llama 2 Chat 13B.
model_id = "meta.llama2-13b-chat-v1"

# Define the prompt for the model.
prompt = "Describe the purpose of a 'hello world' program in one line."

# Embed the prompt in Llama 2's instruction format.
formatted_prompt = f"<s>[INST] {prompt} [/INST]"

# Format the request payload using the model's native structure.
native_request = {
    "prompt": formatted_prompt,
    "max_gen_len": 512,
    "temperature": 0.5,
}

# Convert the native request to JSON.
request = json.dumps(native_request)

try:
    # Invoke the model with the request.
    streaming_response = client.invoke_model_with_response_stream(
        modelId=model_id, body=request
    )

    # Extract and print the response text in real-time.
    for event in streaming_response["body"]:
        chunk = json.loads(event["chunk"]["bytes"])
        if "generation" in chunk:
            print(chunk["generation"], end="")

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

Use the Invoke Model API to send a text message and process the response stream in real-time.

# Use the native inference API to send a text message to Meta Llama 3
# and print the response stream.

import boto3
import json

from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Llama 3 8b Instruct.
model_id = "meta.llama3-8b-instruct-v1:0"

# Define the prompt for the model.
prompt = "Describe the purpose of a 'hello world' program in one line."

# Embed the prompt in Llama 3's instruction format.
formatted_prompt = f"""
<|begin_of_text|>
<|start_header_id|>user<|end_header_id|>
{prompt}
<|eot_id|>
<|start_header_id|>assistant<|end_header_id|>
"""

# Format the request payload using the model's native structure.
native_request = {
    "prompt": formatted_prompt,
    "max_gen_len": 512,
    "temperature": 0.5,
}

# Convert the native request to JSON.
request = json.dumps(native_request)

try:
    # Invoke the model with the request.
    streaming_response = client.invoke_model_with_response_stream(
        modelId=model_id, body=request
    )

    # Extract and print the response text in real-time.
    for event in streaming_response["body"]:
        chunk = json.loads(event["chunk"]["bytes"])
        if "generation" in chunk:
            print(chunk["generation"], end="")

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

Send a text message to Mistral, using Bedrock's Converse API.

# Use the Conversation API to send a text message to Mistral.

import boto3
from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region you want to use.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Mistral Large.
model_id = "mistral.mistral-large-2402-v1:0"

# Start a conversation with the user message.
user_message = "Describe the purpose of a 'hello world' program in one line."
conversation = [
    {
        "role": "user",
        "content": [{"text": user_message}],
    }
]

try:
    # Send the message to the model, using a basic inference configuration.
    response = client.converse(
        modelId=model_id,
        messages=conversation,
        inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9},
    )

    # Extract and print the response text.
    response_text = response["output"]["message"]["content"][0]["text"]
    print(response_text)

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

Send a text message to Mistral, using Bedrock's Converse API and process the response stream in real-time.

# Use the Conversation API to send a text message to Mistral
# and print the response stream.

import boto3
from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region you want to use.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Mistral Large.
model_id = "mistral.mistral-large-2402-v1:0"

# Start a conversation with the user message.
user_message = "Describe the purpose of a 'hello world' program in one line."
conversation = [
    {
        "role": "user",
        "content": [{"text": user_message}],
    }
]

try:
    # Send the message to the model, using a basic inference configuration.
    streaming_response = client.converse_stream(
        modelId=model_id,
        messages=conversation,
        inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9},
    )

    # Extract and print the streamed response text in real-time.
    for chunk in streaming_response["stream"]:
        if "contentBlockDelta" in chunk:
            text = chunk["contentBlockDelta"]["delta"]["text"]
            print(text, end="")

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

Use the Invoke Model API to send a text message.

# Use the native inference API to send a text message to Mistral.

import boto3
import json
from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Mistral Large.
model_id = "mistral.mistral-large-2402-v1:0"

# Define the prompt for the model.
prompt = "Describe the purpose of a 'hello world' program in one line."

# Embed the prompt in Mistral's instruction format.
formatted_prompt = f"<s>[INST] {prompt} [/INST]"

# Format the request payload using the model's native structure.
native_request = {
    "prompt": formatted_prompt,
    "max_tokens": 512,
    "temperature": 0.5,
}

# Convert the native request to JSON.
request = json.dumps(native_request)

try:
    # Invoke the model with the request.
    response = client.invoke_model(modelId=model_id, body=request)

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

# Decode the response body.
model_response = json.loads(response["body"].read())

# Extract and print the response text.
response_text = model_response["outputs"][0]["text"]
print(response_text)

Use the Invoke Model API to send a text message and process the response stream in real-time.

# Use the native inference API to send a text message to Mistral
# and print the response stream.

import boto3
import json

from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Mistral Large.
model_id = "mistral.mistral-large-2402-v1:0"

# Define the prompt for the model.
prompt = "Describe the purpose of a 'hello world' program in one line."

# Embed the prompt in Mistral's instruction format.
formatted_prompt = f"<s>[INST] {prompt} [/INST]"

# Format the request payload using the model's native structure.
native_request = {
    "prompt": formatted_prompt,
    "max_tokens": 512,
    "temperature": 0.5,
}

# Convert the native request to JSON.
request = json.dumps(native_request)

try:
    # Invoke the model with the request.
    streaming_response = client.invoke_model_with_response_stream(
        modelId=model_id, body=request
    )

    # Extract and print the response text in real-time.
    for event in streaming_response["body"]:
        chunk = json.loads(event["chunk"]["bytes"])
        if "outputs" in chunk:
            print(chunk["outputs"][0].get("text"), end="")

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}''. Reason: {e}")
    exit(1)

The Python Foundation Model (FM) Playground is a Python/FastAPI sample application that showcases how to use Amazon Bedrock with Python. This example shows how Python developers can use Amazon Bedrock to build generative AI-enabled applications. You can test and interact with Amazon Bedrock foundation models by using the following three playgrounds:

The example also lists and displays the foundation models you have access to, along with their characteristics. For source code and deployment instructions, see the project in GitHub.

The Amazon Bedrock Serverless Prompt Chaining scenario demonstrates how AWS Step Functions, Amazon Bedrock, and Agents for Amazon Bedrock can be used to build and orchestrate complex, serverless, and highly scalable generative AI applications. It contains the following working examples:

For complete source code and instructions to set up and run, see the full project on GitHub.

Create an image with Stable Diffusion.

# Use the native inference API to create an image with Stability.ai Stable Diffusion

import base64
import boto3
import json
import os
import random

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Stable Diffusion XL 1.
model_id = "stability.stable-diffusion-xl-v1"

# Define the image generation prompt for the model.
prompt = "A stylized picture of a cute old steampunk robot."

# Generate a random seed.
seed = random.randint(0, 4294967295)

# Format the request payload using the model's native structure.
native_request = {
    "text_prompts": [{"text": prompt}],
    "style_preset": "photographic",
    "seed": seed,
    "cfg_scale": 10,
    "steps": 30,
}

# Convert the native request to JSON.
request = json.dumps(native_request)

# Invoke the model with the request.
response = client.invoke_model(modelId=model_id, body=request)

# Decode the response body.
model_response = json.loads(response["body"].read())

# Extract the image data.
base64_image_data = model_response["artifacts"][0]["base64"]

# Save the generated image to a local folder.
i, output_dir = 1, "output"
if not os.path.exists(output_dir):
    os.makedirs(output_dir)
while os.path.exists(os.path.join(output_dir, f"stability_{i}.png")):
    i += 1

image_data = base64.b64decode(base64_image_data)

image_path = os.path.join(output_dir, f"stability_{i}.png")
with open(image_path, "wb") as file:
    file.write(image_data)

print(f"The generated image has been saved to {image_path}")