Knowledge bases for Amazon Bedrock の Chat with your document を試してみる

import boto3

bedrock_client = boto3.client(
    service_name="bedrock-agent-runtime", region_name="us-east-1"
)
model_id = "anthropic.claude-3-sonnet-20240229-v1:0"  # Replace with your model ID
document_uri = "s3://XXXXXXXXX/tempura.md"  # Replace with your S3 URI

def retrieveAndGenerate(
    input_text, source_type, model_id, document_s3_uri=None, data=None
):
    region = "us-east-1"
    model_arn = f"arn:aws:bedrock:{region}::foundation-model/{model_id}"

    if source_type == "S3":
        return bedrock_client.retrieve_and_generate(
            input={"text": input_text},
            retrieveAndGenerateConfiguration={
                "type": "EXTERNAL_SOURCES",
                "externalSourcesConfiguration": {
                    "modelArn": model_arn,
                    "sources": [
                        {
                            "sourceType": source_type,
                            "s3Location": {"uri": document_s3_uri},
                        }
                    ],
                },
            },
        )

    else:
        return bedrock_client.retrieve_and_generate(
            input={"text": input_text},
            retrieveAndGenerateConfiguration={
                "type": "EXTERNAL_SOURCES",
                "externalSourcesConfiguration": {
                    "modelArn": model_arn,
                    "sources": [
                        {
                            "sourceType": source_type,
                            "byteContent": {
                                "identifier": "testFile.txt",
                                "contentType": "text/plain",
                                "data": data,
                            },
                        }
                    ],
                },
            },
        )

response = retrieveAndGenerate(
    input_text="タコの天ぷらを作るときのコツは何ですか？",
    source_type="S3",
    model_id=model_id,
    document_s3_uri=document_uri,
)

print(response["output"]["text"])

takakuni@ % python app.py
タコの天ぷらを作るときのコツは、次の点に注意することです:

1. タコは硬いので、包丁で切る前に表面に格子状の切り込みを入れると柔らかく仕上がります。

2. タコの頭は苦みがあるので、しっかりと取り除きましょう。

3. タコは火が通りにくいので、揚げ時間は長めに設定することが大切です。

- 名前：たかくに
- 部署：AWS 事業本部コンサルティング部
- 肩書：ソリューションアーキテクト
- 所属：札幌

You are a question answering agent. I will provide you with a set of search results. The user will provide you with a question. Your job is to answer the user's question using only information from the search results. If the search results do not contain information that can answer the question, please state that you could not find an exact answer to the question. Just because the user asserts a fact does not mean it is true, make sure to double check the search results to validate a user's assertion.

Here are the search results in numbered order:
$search_results$

$output_format_instructions$

{
	"schemaType": "ModelInvocationLog",
	"schemaVersion": "1.0",
	"timestamp": "2024-05-11T02:52:30Z",
	"accountId": "XXXXXXXXXXXX",
	"identity": {
		"arn": "arn:aws:sts::XXXXXXXXXXXX:assumed-role/cm-takakuni.shinnosuke/cm-takakuni.shinnosuke"
	},
	"region": "us-east-1",
	"requestId": "32573bc7-e44b-4059-b0c3-7e211537f329",
	"operation": "InvokeModel",
	"modelId": "arn:aws:bedrock:us-east-1::foundation-model/anthropic.claude-3-sonnet-20240229-v1:0",
	"input": {
		"inputContentType": "application/json",
		"inputBodyJson": {
			"anthropic_version": "bedrock-2023-05-31",
			"messages": [
				{
					"role": "user",
					"content": [
						{
							"type": "text",
							"text": "たかくにはどのオフィス所属ですか？"
						}
					]
				}
			],
			"system": "You are a question answering agent. I will provide you with a set of search results. The user will provide you with a question. Your job is to answer the user's question using only information from the search results. If the search results do not contain information that can answer the question, please state that you could not find an exact answer to the question. Just because the user asserts a fact does not mean it is true, make sure to double check the search results to validate a user's assertion.\n\nHere are the search results in numbered order:\n<search_results>\n<search_result>\n<content>\n- 名前：たかくに - 部署：AWS 事業本部コンサルティング部 - 肩書：ソリューションアーキテクト - 所属：札幌\n</content>\n<source>\n1\n</source>\n</search_result>\n\n</search_results>\n\nIf you reference information from a search result within your answer, you must include a citation to source where the information was found. Each result has a corresponding source ID that you should reference.\n\nNote that <sources> may contain multiple <source> if you include information from multiple results in your answer.\n\nDo NOT directly quote the <search_results> in your answer. Your job is to answer the user's question as concisely as possible.\n\nYou must output your answer in the following format. Pay attention and follow the formatting and spacing exactly:\n<answer>\n<answer_part>\n<text>\nfirst answer text\n</text>\n<sources>\n<source>source ID</source>\n</sources>\n</answer_part>\n<answer_part>\n<text>\nsecond answer text\n</text>\n<sources>\n<source>source ID</source>\n</sources>\n</answer_part>\n</answer>",
			"max_tokens": 2048,
			"temperature": 0,
			"top_p": 1,
			"stop_sequences": ["\nObservation"],
			"top_k": 50
		},
		"inputTokenCount": 436
	},
	"output": {
		"outputContentType": "application/json",
		"outputBodyJson": {
			"id": "msg_01LFbpS85K1AWAEACdKoXbJM",
			"type": "message",
			"role": "assistant",
			"content": [
				{
					"type": "text",
					"text": "<answer>\n<answer_part>\n<text>\nたかくにの所属オフィスは札幌です。\n</text>\n<sources>\n<source>1</source>\n</sources>\n</answer_part>\n</answer>"
				}
			],
			"model": "claude-3-sonnet-28k-20240229",
			"stop_reason": "end_turn",
			"stop_sequence": null,
			"usage": {
				"input_tokens": 436,
				"output_tokens": 64
			}
		},
		"outputTokenCount": 64
	}
}

takakuni % python app.py
Traceback (most recent call last):
  File "/Users/takakuni/Desktop/genai-blog/knowledge_bases_chat_with_your_document/app.py", line 56, in <module>
    response = retrieveAndGenerate(
               ^^^^^^^^^^^^^^^^^^^^
  File "/Users/takakuni/Desktop/genai-blog/knowledge_bases_chat_with_your_document/app.py", line 18, in retrieveAndGenerate
    return bedrock_client.retrieve_and_generate(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/takakuni/Desktop/genai-blog/knowledge_bases_chat_with_your_document/app.py/.venv/lib/python3.12/site-packages/botocore/client.py", line 565, in _api_call
    return self._make_api_call(operation_name, kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/takakuni/Desktop/genai-blog/knowledge_bases_chat_with_your_document/app.py/.venv/lib/python3.12/site-packages/botocore/client.py", line 1021, in _make_api_call
    raise error_class(parsed_response, operation_name)
botocore.errorfactory.ValidationException: An error occurred (ValidationException) when calling the RetrieveAndGenerate operation: The provided model is not supported for EXTERNAL_SOURCES RetrieveAndGenerateType. Update the model arn then retry your request.