Inferensi menggunakan Converse API

Bid text ang dipetakan ke string yang menentukan prompt. Bid text ang ditafsirkan bersama bidang lain yang ditentukan dalam hal yang sama ContentBlock.

Berikut ini menunjukkan objek Pesan dengan content array yang hanya berisi teks ContentBlock:

{
    "role": "user",
    "content": [
        {
            "text": "string"
        }
    ]
}

imageLapangan dipetakan ke ImageBlock. Lewati byte mentah, dikodekan dalam base64, untuk gambar di bytes lapangan. Jika Anda menggunakan AWS SDK, Anda tidak perlu menyandikan byte di base64.

Jika Anda mengecualikan text bidang, model menjelaskan gambar.

Berikut ini menunjukkan contoh objek Pesan dengan content array yang hanya berisi gambar ContentBlock:

{
    "role": "user",
    "content": [
        {
            "image": {
                "format": "png",
                "source": {
                    "bytes": "image in bytes"
                }
            }
        }
    ]
}

Anda juga dapat menentukan URI Amazon S3 alih-alih meneruskan byte langsung di badan permintaan. Berikut ini menunjukkan Message objek sampel dengan array konten yang berisi sumber yang dilewatkan melalui URI Amazon S3.

{
    "role": "user",
    "content": [
        {
            "image": {
                "format": "png",
                "source": {
                    "s3Location": {
                        "uri": "s3://amzn-s3-demo-bucket/myImage",
                        "bucketOwner": "111122223333"
                    }
                }
            }
        }
    ]
}

documentLapangan dipetakan ke DocumentBlock. Jika Anda menyertakan aDocumentBlock, periksa apakah permintaan Anda sesuai dengan batasan berikut:

Saat menggunakan dokumen, Anda dapat mengaktifkan citations tag, yang akan memberikan kutipan spesifik dokumen dalam respons panggilan API. Lihat DocumentBlock API untuk detail selengkapnya.

Berikut ini menunjukkan contoh objek Pesan dengan content array yang hanya berisi dokumen ContentBlock dan teks yang menyertainya yang diperlukan ContentBlock.

{
    "role": "user",
    "content": [
        {
            "text": "string"
        },
        {
            "document": {
                "format": "pdf",
                "name": "MyDocument",
                "source": {
                    "bytes": "document in bytes"
                }
            }
        }
    ]
}

Anda juga dapat menentukan URI Amazon S3 alih-alih meneruskan byte langsung di badan permintaan. Berikut ini menunjukkan Message objek sampel dengan array konten yang berisi sumber yang dilewatkan melalui URI Amazon S3.

{
    "role": "user",
    "content": [
        {
            "text": "string"
        },
        {
            "document": {
                "format": "pdf",
                "name": "MyDocument",
                "source": {
                    "s3Location": {
                      "uri": "s3://amzn-s3-demo-bucket/myDocument",
                      "bucketOwner": "111122223333"
                    }
                }
            }
        }
    ]
}

Bid video ang memetakan ke VideoBlock objek. Lewati byte mentah di bytes bidang, dikodekan dalam base64. Jika Anda menggunakan AWS SDK, Anda tidak perlu menyandikan byte di base64.

Jika Anda tidak menyertakan text bidang, model akan menjelaskan video tersebut.

Berikut ini menunjukkan contoh objek Pesan dengan content array yang hanya berisi video ContentBlock.

{
    "role": "user",
    "content": [
        {
            "video": {
                "format": "mp4",
                "source": {
                    "bytes": "video in bytes"
                }
            }
        }
    ]
}

Anda juga dapat menentukan URI Amazon S3 alih-alih meneruskan byte langsung di badan permintaan. Berikut ini menunjukkan Message objek sampel dengan array konten yang berisi sumber yang dilewatkan melalui URI Amazon S3.

{
    "role": "user",
    "content": [
        {
            "video": {
                "format": "mp4",
                "source": {
                    "s3Location": {
                        "uri": "s3://amzn-s3-demo-bucket/myVideo",
                        "bucketOwner": "111122223333"
                    }
                }
            }
        }
    ]
}

Anda dapat menambahkan checkpoint cache sebagai blok dalam pesan di samping prompt yang menyertainya dengan menggunakan cachePoint bidang untuk menggunakan cache prompt. Prompt caching adalah fitur yang memungkinkan Anda mulai melakukan cache konteks percakapan untuk mencapai penghematan biaya dan latensi. Untuk informasi selengkapnya, lihat Caching cepat untuk inferensi model yang lebih cepat.

Berikut ini menunjukkan contoh objek Pesan dengan content array yang berisi dokumen ContentBlock dan teks yang menyertainya ContentBlock, serta CachePoint yang menambahkan dokumen dan konten teks ke cache.

{
    "role": "user",
    "content": [
        {
            "text": "string"
        },
        {
            "document": {
                "format": "pdf",
                "name": "string",
                "source": {
                    "bytes": "document in bytes"
                }
            }
        },
        {
            "cachePoint": {
                "type": "default"
            }
        }
    ]
}

Bid guardContent ang memetakan ke GuardrailConverseContentBlock objek. Anda dapat menggunakan bidang ini untuk menargetkan input yang akan dievaluasi oleh pagar pembatas yang ditentukan di guardrailConfig bidang. Jika Anda tidak menentukan bidang ini, pagar pembatas mengevaluasi semua pesan di badan permintaan. Anda dapat meneruskan jenis konten berikut dalamGuardBlock:

Untuk informasi lebih lanjut tentang menggunakan pagar pembatas, lihat. Mendeteksi dan memfilter konten berbahaya dengan menggunakan Amazon Bedrock Guardrails

reasoningContentLapangan dipetakan ke a ReasoningContentBlock. Blok ini berisi konten mengenai alasan yang dilakukan oleh model untuk menghasilkan respons yang menyertainyaContentBlock.

Berikut ini menunjukkan Message objek dengan content array yang hanya berisi ReasoningContentBlock a dan teks yang menyertainyaContentBlock.

{
    "role": "user",
    "content": [
        {
            "text": "string"
        },
        {
            "reasoningContent": {
                "reasoningText": {
                    "text": "string",
                    "signature": "string"
                }
                "redactedContent": "base64-encoded binary data object"
            }
        }
    ]
}

Ini ReasoningContentBlock berisi alasan yang digunakan untuk menghasilkan konten yang menyertainya di reasoningText lapangan, selain konten apa pun dalam alasan yang dienkripsi oleh penyedia model untuk alasan kepercayaan dan keamanan di redactedContent lapangan.

Di dalam reasoningText bidang, text bidang menggambarkan alasannya. Bid signature ang ini adalah hash dari semua pesan dalam percakapan dan merupakan perlindungan terhadap gangguan penalaran yang digunakan oleh model. Anda harus menyertakan tanda tangan dan semua pesan sebelumnya dalam Converse permintaan berikutnya. Jika salah satu pesan diubah, respons akan menimbulkan kesalahan.

Berisi informasi tentang alat untuk model yang akan digunakan. Untuk informasi selengkapnya, lihat Menggunakan alat untuk menyelesaikan respons model Amazon Bedrock.

Berisi informasi tentang hasil dari model menggunakan alat. Untuk informasi selengkapnya, lihat Menggunakan alat untuk menyelesaikan respons model Amazon Bedrock.

Contoh ini menunjukkan cara memanggil Converse operasi dengan Anthropic Claude 3 Sonnet model. Contoh menunjukkan cara mengirim teks input, parameter inferensi, dan parameter tambahan yang unik untuk model. Kode memulai percakapan dengan meminta model untuk membuat daftar lagu. Kemudian melanjutkan percakapan dengan meminta bahwa lagu-lagu itu oleh artis dari Inggris.

# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
# SPDX-License-Identifier: Apache-2.0
"""
Shows how to use the <noloc>Converse</noloc> API with Anthropic Claude 3 Sonnet (on demand).
"""

import logging
import boto3

from botocore.exceptions import ClientError


logger = logging.getLogger(__name__)
logging.basicConfig(level=logging.INFO)


def generate_conversation(bedrock_client,
                          model_id,
                          system_prompts,
                          messages):
    """
    Sends messages to a model.
    Args:
        bedrock_client: The Boto3 Bedrock runtime client.
        model_id (str): The model ID to use.
        system_prompts (JSON) : The system prompts for the model to use.
        messages (JSON) : The messages to send to the model.

    Returns:
        response (JSON): The conversation that the model generated.

    """

    logger.info("Generating message with model %s", model_id)

    # Inference parameters to use.
    temperature = 0.5
    top_k = 200

    # Base inference parameters to use.
    inference_config = {"temperature": temperature}
    # Additional inference parameters to use.
    additional_model_fields = {"top_k": top_k}

    # Send the message.
    response = bedrock_client.converse(
        modelId=model_id,
        messages=messages,
        system=system_prompts,
        inferenceConfig=inference_config,
        additionalModelRequestFields=additional_model_fields
    )

    # Log token usage.
    token_usage = response['usage']
    logger.info("Input tokens: %s", token_usage['inputTokens'])
    logger.info("Output tokens: %s", token_usage['outputTokens'])
    logger.info("Total tokens: %s", token_usage['totalTokens'])
    logger.info("Stop reason: %s", response['stopReason'])

    return response

def main():
    """
    Entrypoint for Anthropic Claude 3 Sonnet example.
    """

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

    model_id = "anthropic.claude-3-sonnet-20240229-v1:0"

    # Setup the system prompts and messages to send to the model.
    system_prompts = [{"text": "You are an app that creates playlists for a radio station that plays rock and pop music. Only return song names and the artist."}]
    message_1 = {
        "role": "user",
        "content": [{"text": "Create a list of 3 pop songs."}]
    }
    message_2 = {
        "role": "user",
        "content": [{"text": "Make sure the songs are by artists from the United Kingdom."}]
    }
    messages = []

    try:

        bedrock_client = boto3.client(service_name='bedrock-runtime')

        # Start the conversation with the 1st message.
        messages.append(message_1)
        response = generate_conversation(
            bedrock_client, model_id, system_prompts, messages)

        # Add the response message to the conversation.
        output_message = response['output']['message']
        messages.append(output_message)

        # Continue the conversation with the 2nd message.
        messages.append(message_2)
        response = generate_conversation(
            bedrock_client, model_id, system_prompts, messages)

        output_message = response['output']['message']
        messages.append(output_message)

        # Show the complete conversation.
        for message in messages:
            print(f"Role: {message['role']}")
            for content in message['content']:
                print(f"Text: {content['text']}")
            print()

    except ClientError as err:
        message = err.response['Error']['Message']
        logger.error("A client error occurred: %s", message)
        print(f"A client error occured: {message}")

    else:
        print(
            f"Finished generating text with model {model_id}.")


if __name__ == "__main__":
    main()

Contoh ini menunjukkan cara mengirim gambar sebagai bagian dari pesan dan meminta agar model menggambarkan gambar. Contohnya menggunakan Converse operasi dan Anthropic Claude 3 Sonnet model.

# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
# SPDX-License-Identifier: Apache-2.0
"""
Shows how to send an image with the <noloc>Converse</noloc> API with an accompanying text prompt to Anthropic Claude 3 Sonnet (on demand).
"""

import logging
import boto3


from botocore.exceptions import ClientError


logger = logging.getLogger(__name__)
logging.basicConfig(level=logging.INFO)


def generate_conversation(bedrock_client,
                          model_id,
                          input_text,
                          input_image):
    """
    Sends a message to a model.
    Args:
        bedrock_client: The Boto3 Bedrock runtime client.
        model_id (str): The model ID to use.
        input text : The text prompt accompanying the image.
        input_image : The path to the input image.

    Returns:
        response (JSON): The conversation that the model generated.

    """

    logger.info("Generating message with model %s", model_id)

    # Get image extension and read in image as bytes
    image_ext = input_image.split(".")[-1]
    with open(input_image, "rb") as f:
        image = f.read()

    message = {
        "role": "user",
        "content": [
            {
                "text": input_text
            },
            {
                "image": {
                    "format": image_ext,
                    "source": {
                        "bytes": image
                    }
                }
            }
        ]
    }

    messages = [message]

    # Send the message.
    response = bedrock_client.converse(
        modelId=model_id,
        messages=messages
    )

    return response


def main():
    """
    Entrypoint for Anthropic Claude 3 Sonnet example.
    """

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

    model_id = "anthropic.claude-3-sonnet-20240229-v1:0"
    input_text = "What's in this image?"
    input_image = "path/to/image"

    try:

        bedrock_client = boto3.client(service_name="bedrock-runtime")

        response = generate_conversation(
            bedrock_client, model_id, input_text, input_image)

        output_message = response['output']['message']

        print(f"Role: {output_message['role']}")

        for content in output_message['content']:
            print(f"Text: {content['text']}")

        token_usage = response['usage']
        print(f"Input tokens:  {token_usage['inputTokens']}")
        print(f"Output tokens:  {token_usage['outputTokens']}")
        print(f"Total tokens:  {token_usage['totalTokens']}")
        print(f"Stop reason: {response['stopReason']}")

    except ClientError as err:
        message = err.response['Error']['Message']
        logger.error("A client error occurred: %s", message)
        print(f"A client error occured: {message}")

    else:
        print(
            f"Finished generating text with model {model_id}.")


if __name__ == "__main__":
    main()

Contoh ini menunjukkan cara mengirim dokumen sebagai bagian dari pesan dan meminta agar model menjelaskan isi dokumen. Contohnya menggunakan Converse operasi dan Anthropic Claude 3 Sonnet model.

# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
# SPDX-License-Identifier: Apache-2.0
"""
Shows how to send an document as part of a message to Anthropic Claude 3 Sonnet (on demand).
"""

import logging
import boto3


from botocore.exceptions import ClientError


logger = logging.getLogger(__name__)
logging.basicConfig(level=logging.INFO)


def generate_message(bedrock_client,
                     model_id,
                     input_text,
                     input_document_path):
    """
    Sends a message to a model.
    Args:
        bedrock_client: The Boto3 Bedrock runtime client.
        model_id (str): The model ID to use.
        input text : The input message.
        input_document_path : The path to the input document.

    Returns:
        response (JSON): The conversation that the model generated.

    """

    logger.info("Generating message with model %s", model_id)

    # Get format from path and read the path
    input_document_format = input_document_path.split(".")[-1]
    with open(input_document_path, 'rb') as input_document_file:
        input_document = input_document_file.read()

    # Message to send.
    message = {
        "role": "user",
        "content": [
            {
                "text": input_text
            },
            {
                "document": {
                    "name": "MyDocument",
                    "format": input_document_format,
                    "source": {
                        "bytes": input_document
                    }
                }
            }
        ]
    }

    messages = [message]

    # Send the message.
    response = bedrock_client.converse(
        modelId=model_id,
        messages=messages
    )

    return response


def main():
    """
    Entrypoint for Anthropic Claude 3 Sonnet example.
    """

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

    model_id = "anthropic.claude-3-sonnet-20240229-v1:0"
    input_text = "What's in this document?"
    input_document_path = "path/to/document"

    try:

        bedrock_client = boto3.client(service_name="bedrock-runtime")


        response = generate_message(
            bedrock_client, model_id, input_text, input_document_path)

        output_message = response['output']['message']

        print(f"Role: {output_message['role']}")

        for content in output_message['content']:
            print(f"Text: {content['text']}")

        token_usage = response['usage']
        print(f"Input tokens:  {token_usage['inputTokens']}")
        print(f"Output tokens:  {token_usage['outputTokens']}")
        print(f"Total tokens:  {token_usage['totalTokens']}")
        print(f"Stop reason: {response['stopReason']}")

    except ClientError as err:
        message = err.response['Error']['Message']
        logger.error("A client error occurred: %s", message)
        print(f"A client error occured: {message}")

    else:
        print(
            f"Finished generating text with model {model_id}.")


if __name__ == "__main__":
    main()

Contoh ini menunjukkan cara memanggil ConverseStream operasi dengan Anthropic Claude 3 Sonnet model. Contoh menunjukkan cara mengirim teks input, parameter inferensi, dan parameter tambahan yang unik untuk model.

# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
# SPDX-License-Identifier: Apache-2.0
"""
Shows how to use the <noloc>Converse</noloc> API to stream a response from Anthropic Claude 3 Sonnet (on demand).
"""

import logging
import boto3


from botocore.exceptions import ClientError


logger = logging.getLogger(__name__)
logging.basicConfig(level=logging.INFO)


def stream_conversation(bedrock_client,
                    model_id,
                    messages,
                    system_prompts,
                    inference_config,
                    additional_model_fields):
    """
    Sends messages to a model and streams the response.
    Args:
        bedrock_client: The Boto3 Bedrock runtime client.
        model_id (str): The model ID to use.
        messages (JSON) : The messages to send.
        system_prompts (JSON) : The system prompts to send.
        inference_config (JSON) : The inference configuration to use.
        additional_model_fields (JSON) : Additional model fields to use.

    Returns:
        Nothing.

    """

    logger.info("Streaming messages with model %s", model_id)

    response = bedrock_client.converse_stream(
        modelId=model_id,
        messages=messages,
        system=system_prompts,
        inferenceConfig=inference_config,
        additionalModelRequestFields=additional_model_fields
    )

    stream = response.get('stream')
    if stream:
        for event in stream:

            if 'messageStart' in event:
                print(f"\nRole: {event['messageStart']['role']}")

            if 'contentBlockDelta' in event:
                print(event['contentBlockDelta']['delta']['text'], end="")

            if 'messageStop' in event:
                print(f"\nStop reason: {event['messageStop']['stopReason']}")

            if 'metadata' in event:
                metadata = event['metadata']
                if 'usage' in metadata:
                    print("\nToken usage")
                    print(f"Input tokens: {metadata['usage']['inputTokens']}")
                    print(
                        f":Output tokens: {metadata['usage']['outputTokens']}")
                    print(f":Total tokens: {metadata['usage']['totalTokens']}")
                if 'metrics' in event['metadata']:
                    print(
                        f"Latency: {metadata['metrics']['latencyMs']} milliseconds")


def main():
    """
    Entrypoint for streaming message API response example.
    """

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

    model_id = "anthropic.claude-3-sonnet-20240229-v1:0"
    system_prompt = """You are an app that creates playlists for a radio station
      that plays rock and pop music. Only return song names and the artist."""

    # Message to send to the model.
    input_text = "Create a list of 3 pop songs."

    message = {
        "role": "user",
        "content": [{"text": input_text}]
    }
    messages = [message]
    
    # System prompts.
    system_prompts = [{"text" : system_prompt}]

    # inference parameters to use.
    temperature = 0.5
    top_k = 200
    # Base inference parameters.
    inference_config = {
        "temperature": temperature
    }
    # Additional model inference parameters.
    additional_model_fields = {"top_k": top_k}

    try:
        bedrock_client = boto3.client(service_name='bedrock-runtime')

        stream_conversation(bedrock_client, model_id, messages,
                        system_prompts, inference_config, additional_model_fields)

    except ClientError as err:
        message = err.response['Error']['Message']
        logger.error("A client error occurred: %s", message)
        print("A client error occured: " +
              format(message))

    else:
        print(
            f"Finished streaming messages with model {model_id}.")


if __name__ == "__main__":
    main()

Contoh ini menunjukkan cara mengirim video sebagai bagian dari pesan dan meminta agar model menjelaskan video tersebut. Contohnya menggunakan Converse operasi dan Amazon Nova Pro model.

# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
# SPDX-License-Identifier: Apache-2.0
"""
Shows how to send a video with the <noloc>Converse</noloc> API to Amazon Nova Pro (on demand).
"""

import logging
import boto3


from botocore.exceptions import ClientError


logger = logging.getLogger(__name__)
logging.basicConfig(level=logging.INFO)


def generate_conversation(bedrock_client,
                          model_id,
                          input_text,
                          input_video):
    """
    Sends a message to a model.
    Args:
        bedrock_client: The Boto3 Bedrock runtime client.
        model_id (str): The model ID to use.
        input text : The input message.
        input_video : The input video.

    Returns:
        response (JSON): The conversation that the model generated.

    """

    logger.info("Generating message with model %s", model_id)

    # Message to send.

    with open(input_video, "rb") as f:
        video = f.read()

    message = {
        "role": "user",
        "content": [
            {
                "text": input_text
            },
            {
                    "video": {
                        "format": 'mp4',
                        "source": {
                            "bytes": video
                        }
                    }
            }
        ]
    }

    messages = [message]

    # Send the message.
    response = bedrock_client.converse(
        modelId=model_id,
        messages=messages
    )

    return response


def main():
    """
    Entrypoint for Amazon Nova Pro example.
    """

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

    model_id = "amazon.nova-pro-v1:0"
    input_text = "What's in this video?"
    input_video = "path/to/video"

    try:

        bedrock_client = boto3.client(service_name="bedrock-runtime")

        response = generate_conversation(
            bedrock_client, model_id, input_text, input_video)

        output_message = response['output']['message']

        print(f"Role: {output_message['role']}")

        for content in output_message['content']:
            print(f"Text: {content['text']}")

        token_usage = response['usage']
        print(f"Input tokens:  {token_usage['inputTokens']}")
        print(f"Output tokens:  {token_usage['outputTokens']}")
        print(f"Total tokens:  {token_usage['totalTokens']}")
        print(f"Stop reason: {response['stopReason']}")

    except ClientError as err:
        message = err.response['Error']['Message']
        logger.error("A client error occurred: %s", message)
        print(f"A client error occured: {message}")

    else:
        print(
            f"Finished generating text with model {model_id}.")


if __name__ == "__main__":
    main()