A company needs to deploy a chatbot to answer common questions from customers. The chatbot must base its answers on company documentation.
Which solution will meet these requirements with the LEAST development effort?
A.
Index company documents by using Amazon Kendra. Integrate the chatbot with Amazon Kendra by using the Amazon Kendra Query API operation to answer customer questions.
B.
Train a Bidirectional Attention Flow (BiDAF) network based on past customer questions and company documents. Deploy the model as a real-time Amazon SageMaker endpoint. Integrate the model with the chatbot by using the SageMaker Runtime InvokeEndpoint API operation to answer customer questions.
C.
Train an Amazon SageMaker Blazing Text model based on past customer questions and company documents. Deploy the model as a real-time SageMaker endpoint. Integrate the model with the chatbot by using the SageMaker Runtime InvokeEndpoint API operation to answer customer questions.
D.
Index company documents by using Amazon OpenSearch Service. Integrate the chatbot with OpenSearch Service by using the OpenSearch Service k-nearest neighbors (k-NN) Query API operation to answer customer questions.
A. Amazon Kendra is designed to search through various types of documents and provide relevant answers.
B. Training a BiDAF network requires expertise in deep learning and natural language processing. It would require substantial effort in data preparation, model training, and integration.
C. Amazon SageMaker Blazing Text is primarily used for text classification and word embeddings, not for extracting answers from company documents based on user queries.
D. Amazon OpenSearch Service is a search and analytics engine, but it's not tailored for extracting precise answers from documents. The k-NN Query API is used for similarity searches and isn't inherently designed to answer questions based on document content.
Amazon Kendra is a managed search service that helps you find answers to your questions from your content. It uses natural language processing and machine learning to understand the meaning of your questions and match them to the most relevant content.
A is correct
Amazon Kendra is an intelligent search service powered by machine learning. It can be used to index and search through company documents, making it a suitable solution for the chatbot to base its answers on.
Option A suggests indexing company documents using Amazon Kendra, which simplifies the process of searching and retrieving relevant information from the documentation.
Integrating the chatbot with Amazon Kendra using the Kendra Query API operation allows the chatbot to send customer questions to Kendra and receive relevant answers based on the indexed documents.
This solution requires minimal development effort as it leverages the built-in capabilities of Amazon Kendra and its integration with the chatbot.
Option B, training a Bidirectional Attention Flow (BiDAF) network, and option C, training a SageMaker Blazing Text model, both involve training custom models, which would require significant development effort, including data preparation, model training, and deployment.
A voting comment increases the vote count for the chosen answer by one.
Upvoting a comment with a selected answer will also increase the vote count towards that answer by one.
So if you see a comment that you already agree with, you can upvote it instead of posting a new comment.
seifskl
Highly Voted 6 months agoMickey321
Most Recent 8 months agokaike_reis
8 months, 1 week agoADVIT
9 months, 3 weeks agokukreti18
9 months, 3 weeks ago