使用 Amazon Bedrock 和 Haystack 进行基于 PDF 的问答

pip install opensearch-haystack amazon-bedrock-haystack pypdf

import boto3
from botocore import UNSIGNED
from botocore.config import Config
s3 = boto3.client('s3', config=Config(signature_version=UNSIGNED))

# Download the PDF file from our s3 bucket to `/content/bedrock-documentation.pdf` directory
s3.download_file('core-engineering', 'public/blog-posts/bedrock-documentation.pdf', '/content/bedrock-documentation.pdf') #

docker pull opensearchproject/opensearch:2.11.0
docker run -p 9200:9200 -p 9600:9600 -e "discovery.type=single-node" -e "OPENSEARCH_JAVA_OPTS=-Xms1024m -Xmx1024m" opensearchproject/opensearch:2.11.0

from pathlib import Path

from haystack import Pipeline
from haystack.components.converters import PyPDFToDocument
from haystack.components.preprocessors import DocumentCleaner, DocumentSplitter
from haystack.components.writers import DocumentWriter
from haystack.document_stores.types import DuplicatePolicy
from haystack_integrations.document_stores.opensearch import OpenSearchDocumentStore

## Initialize the OpenSearchDocumentStore
document_store = OpenSearchDocumentStore(hosts="https://:9200", use_ssl=True, verify_certs=False, http_auth=("admin", "admin"))

## Create pipeline components
converter = PyPDFToDocument()
cleaner = DocumentCleaner()
splitter = DocumentSplitter(split_by="sentence", split_length=10, split_overlap=2)
writer = DocumentWriter(document_store=document_store, policy=DuplicatePolicy.SKIP)

## Add components to the pipeline
indexing_pipeline = Pipeline()
indexing_pipeline.add_component("converter", converter)
indexing_pipeline.add_component("cleaner", cleaner)
indexing_pipeline.add_component("splitter", splitter)
indexing_pipeline.add_component("writer", writer)

## Connect the components to each other
indexing_pipeline.connect("converter", "cleaner")
indexing_pipeline.connect("cleaner", "splitter")
indexing_pipeline.connect("splitter", "writer")

indexing_pipeline.run({"converter": {"sources": [Path("/content/bedrock-documentation.pdf")]}})

from haystack.components.builders import PromptBuilder
from haystack.pipeline import Pipeline
from amazon_bedrock_haystack.generators.amazon_bedrock import AmazonBedrockGenerator
from haystack_integrations.components.retrievers.opensearch import OpenSearchBM25Retriever

## Create pipeline components
retriever = OpenSearchBM25Retriever(document_store=document_store, top_k=15)

## Set the AWS credentials as environment variables
os.environ["AWS_ACCESS_KEY_ID"] = "aws_access_key_id"
os.environ["AWS_SECRET_ACCESS_KEY"] = "aws_secret"
os.environ["AWS_REGION_NAME"] = "aws_region_name"

## Initialize the AmazonBedrockGenerator with an Amazon Bedrock model
generator = AmazonBedrockGenerator(model='amazon.titan-text-express-v1', max_length=500)
template = """
{% for document in documents %}
    {{ document.content }}
{% endfor %}

Please answer the question based on the given information from Amazon Bedrock documentation.

{{question}}
"""
prompt_builder = PromptBuilder(template=template)

## Add components to the pipeline
rag_pipeline = Pipeline()
rag_pipeline.add_component("retriever", retriever)
rag_pipeline.add_component("prompt_builder", prompt_builder)
rag_pipeline.add_component("llm", generator)

## Connect components to each other
rag_pipeline.connect("retriever", "prompt_builder.documents")
rag_pipeline.connect("prompt_builder", "llm")

question = "What is Amazon Bedrock??"
response = rag_pipeline.run({"retriever": {"query": question}, "prompt_builder": {"question": question}})

print(response["llm"]["replies"][0])

Amazon Bedrock is a fully managed service that makes high-performing foundation models (FMs) from leading AI startups and Amazon available for your use through a unified API. You can choose from a wide range of foundation models to find the model that is best suited for your use case. Amazon Bedrock also offers a broad set of capabilities to build generative AI applications with security, privacy, and responsible AI. Using Amazon Bedrock, you can easily experiment with and evaluate top foundation models for your use cases, privately customize them with your data using techniques such as fine-tuning and Retrieval Augmented Generation (RAG), and build agents that execute tasks using your enterprise systems and data sources.
With Amazon Bedrock's serverless experience, you can get started quickly, privately customize foundation models with your own data, and easily and securely integrate and deploy them into your applications using AWS tools without having to manage any infrastructure.