Amazon Bedrock Runtime examples using SDK for Python (Boto3) - AWS SDK Code Examples

There are more AWS SDK examples available in the AWS Doc SDK Examples GitHub repo.

Amazon Bedrock Runtime examples using SDK for Python (Boto3)

The following code examples show you how to perform actions and implement common scenarios by using the AWS SDK for Python (Boto3) with Amazon Bedrock Runtime.

Actions are code excerpts from larger programs and must be run in context. While actions show you how to call individual service functions, you can see actions in context in their related scenarios and cross-service examples.

Scenarios are code examples that show you how to accomplish a specific task by calling multiple functions within the same service.

Each example includes a link to GitHub, where you can find instructions on how to set up and run the code in context.

AI21 Labs Jurassic-2

The following code example shows how to send a text message to AI21 Labs Jurassic-2, using Bedrock's Converse API.

SDK for Python (Boto3)
Note

There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository.

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)
  • For API details, see Converse in AWS SDK for Python (Boto3) API Reference.

The following code example shows how to send a text message to AI21 Labs Jurassic-2, using the Invoke Model API.

SDK for Python (Boto3)
Note

There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository.

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)
  • For API details, see InvokeModel in AWS SDK for Python (Boto3) API Reference.

Amazon Titan Image Generator

The following code example shows how to invoke Amazon Titan Image on Amazon Bedrock to generate an image.

SDK for Python (Boto3)
Note

There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository.

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}")
  • For API details, see InvokeModel in AWS SDK for Python (Boto3) API Reference.

Amazon Titan Text

The following code example shows how to send a text message to Amazon Titan Text, using Bedrock's Converse API.

SDK for Python (Boto3)
Note

There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository.

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)
  • For API details, see Converse in AWS SDK for Python (Boto3) API Reference.

The following code example shows how to send a text message to Amazon Titan Text, using Bedrock's Converse API and process the response stream in real-time.

SDK for Python (Boto3)
Note

There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository.

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)
  • For API details, see ConverseStream in AWS SDK for Python (Boto3) API Reference.

The following code example shows how to send a text message to Amazon Titan Text, using the Invoke Model API.

SDK for Python (Boto3)
Note

There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository.

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)
  • For API details, see InvokeModel in AWS SDK for Python (Boto3) API Reference.

The following code example shows how to send a text message to Amazon Titan Text models, using the Invoke Model API, and print the response stream.

SDK for Python (Boto3)
Note

There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository.

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="")

Amazon Titan Text Embeddings

The following code example shows how to:

  • Get started creating your first embedding.

  • Create embeddings configuring the number of dimensions and normalization (V2 only).

SDK for Python (Boto3)
Note

There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository.

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)
  • For API details, see InvokeModel in AWS SDK for Python (Boto3) API Reference.

Anthropic Claude

The following code example shows how to send a text message to Anthropic Claude, using Bedrock's Converse API.

SDK for Python (Boto3)
Note

There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository.

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)
  • For API details, see Converse in AWS SDK for Python (Boto3) API Reference.

The following code example shows how to send a text message to Anthropic Claude, using Bedrock's Converse API and process the response stream in real-time.

SDK for Python (Boto3)
Note

There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository.

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)
  • For API details, see ConverseStream in AWS SDK for Python (Boto3) API Reference.

The following code example shows how to send a text message to Anthropic Claude, using the Invoke Model API.

SDK for Python (Boto3)
Note

There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository.

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)
  • For API details, see InvokeModel in AWS SDK for Python (Boto3) API Reference.

The following code example shows how to send a text message to Anthropic Claude models, using the Invoke Model API, and print the response stream.

SDK for Python (Boto3)
Note

There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository.

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 following code example shows how to build a typical interaction between an application, a generative AI model, and connected tools or APIs to mediate interactions between the AI and the outside world. It uses the example of connecting an external weather API to the AI model so it can provide real-time weather information based on user input.

SDK for Python (Boto3)
Note

There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository.

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)}
  • For API details, see Converse in AWS SDK for Python (Boto3) API Reference.

Cohere Command

The following code example shows how to send a text message to Cohere Command, using Bedrock's Converse API.

SDK for Python (Boto3)
Note

There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository.

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)
  • For API details, see Converse in AWS SDK for Python (Boto3) API Reference.

The following code example shows how to send a text message to Cohere Command, using Bedrock's Converse API and process the response stream in real-time.

SDK for Python (Boto3)
Note

There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository.

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)
  • For API details, see ConverseStream in AWS SDK for Python (Boto3) API Reference.

The following code example shows how to send a text message to Cohere Command R and R+, using the Invoke Model API.

SDK for Python (Boto3)
Note

There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository.

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)
  • For API details, see InvokeModel in AWS SDK for Python (Boto3) API Reference.

The following code example shows how to send a text message to Cohere Command, using the Invoke Model API.

SDK for Python (Boto3)
Note

There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository.

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)
  • For API details, see InvokeModel in AWS SDK for Python (Boto3) API Reference.

The following code example shows how to send a text message to Cohere Command, using the Invoke Model API with a response stream.

SDK for Python (Boto3)
Note

There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository.

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)
  • For API details, see InvokeModel in AWS SDK for Python (Boto3) API Reference.

The following code example shows how to send a text message to Cohere Command, using the Invoke Model API with a response stream.

SDK for Python (Boto3)
Note

There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository.

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)
  • For API details, see InvokeModel in AWS SDK for Python (Boto3) API Reference.

The following code example shows how to build a typical interaction between an application, a generative AI model, and connected tools or APIs to mediate interactions between the AI and the outside world. It uses the example of connecting an external weather API to the AI model so it can provide real-time weather information based on user input.

SDK for Python (Boto3)
Note

There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository.

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)}
  • For API details, see Converse in AWS SDK for Python (Boto3) API Reference.

Meta Llama

The following code example shows how to send a text message to Meta Llama, using Bedrock's Converse API.

SDK for Python (Boto3)
Note

There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository.

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)
  • For API details, see Converse in AWS SDK for Python (Boto3) API Reference.

The following code example shows how to send a text message to Meta Llama, using Bedrock's Converse API and process the response stream in real-time.

SDK for Python (Boto3)
Note

There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository.

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)
  • For API details, see ConverseStream in AWS SDK for Python (Boto3) API Reference.

The following code example shows how to send a text message to Meta Llama 2, using the Invoke Model API.

SDK for Python (Boto3)
Note

There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository.

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)
  • For API details, see InvokeModel in AWS SDK for Python (Boto3) API Reference.

The following code example shows how to send a text message to Meta Llama 3, using the Invoke Model API.

SDK for Python (Boto3)
Note

There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository.

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)
  • For API details, see InvokeModel in AWS SDK for Python (Boto3) API Reference.

The following code example shows how to send a text message to Meta Llama 2, using the Invoke Model API, and print the response stream.

SDK for Python (Boto3)
Note

There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository.

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)

The following code example shows how to send a text message to Meta Llama 3, using the Invoke Model API, and print the response stream.

SDK for Python (Boto3)
Note

There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository.

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)

Mistral AI

The following code example shows how to send a text message to Mistral, using Bedrock's Converse API.

SDK for Python (Boto3)
Note

There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository.

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)
  • For API details, see Converse in AWS SDK for Python (Boto3) API Reference.

The following code example shows how to send a text message to Mistral, using Bedrock's Converse API and process the response stream in real-time.

SDK for Python (Boto3)
Note

There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository.

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)
  • For API details, see ConverseStream in AWS SDK for Python (Boto3) API Reference.

The following code example shows how to send a text message to Mistral models, using the Invoke Model API.

SDK for Python (Boto3)
Note

There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository.

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)
  • For API details, see InvokeModel in AWS SDK for Python (Boto3) API Reference.

The following code example shows how to send a text message to Mistral AI models, using the Invoke Model API, and print the response stream.

SDK for Python (Boto3)
Note

There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository.

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)

Scenarios

The following code example shows how to create playgrounds to interact with Amazon Bedrock foundation models through different modalities.

SDK for Python (Boto3)

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:

  • A text playground.

  • A chat playground.

  • An image playground.

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.

Services used in this example
  • Amazon Bedrock Runtime

The following code example shows how to build and orchestrate generative AI applications with Amazon Bedrock and Step Functions.

SDK for Python (Boto3)

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:

  • Write an analysis of a given novel for a literature blog. This example illustrates a simple, sequential chain of prompts.

  • Generate a short story about a given topic. This example illustrates how the AI can iteratively process a list of items that it previously generated.

  • Create an itinerary for a weekend vacation to a given destination. This example illustrates how to parallelize multiple distinct prompts.

  • Pitch movie ideas to a human user acting as a movie producer. This example illustrates how to parallelize the same prompt with different inference parameters, how to backtrack to a previous step in the chain, and how to include human input as part of the workflow.

  • Plan a meal based on ingredients the user has at hand. This example illustrates how prompt chains can incorporate two distinct AI conversations, with two AI personas engaging in a debate with each other to improve the final outcome.

  • Find and summarize today's highest trending GitHub repository. This example illustrates chaining multiple AI agents that interact with external APIs.

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

Services used in this example
  • Amazon Bedrock

  • Amazon Bedrock Runtime

  • Agents for Amazon Bedrock

  • Agents for Amazon Bedrock Runtime

  • Step Functions

Stable Diffusion

The following code example shows how to invoke Stability.ai Stable Diffusion XL on Amazon Bedrock to generate an image.

SDK for Python (Boto3)
Note

There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository.

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}")
  • For API details, see InvokeModel in AWS SDK for Python (Boto3) API Reference.