article thumbnail

From concept to reality: Navigating the Journey of RAG from proof of concept to production

AWS Machine Learning Blog

The brand might be willing to absorb the higher costs of using a more powerful and expensive FMs to achieve the highest-quality classifications, because misclassifications could lead to customer dissatisfaction and damage the brands reputation. Consider another use case of generating personalized product descriptions for an ecommerce site.

article thumbnail

Use custom metadata created by Amazon Comprehend to intelligently process insurance claims using Amazon Kendra

AWS Machine Learning Blog

The insurance provider receives payout claims from the beneficiary’s attorney for different insurance types, such as home, auto, and life insurance. Amazon Comprehend custom classification API is used to organize your documents into categories (classes) that you define. Custom classification is a two-step process.

Metadata 125
professionals

Sign Up for our Newsletter

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

article thumbnail

Transforming IT operations and application modernization with artificial intelligence

IBM Journey to AI blog

Existing sales and service engineers can use language-based generative AI to augment their skills and easily find contextual or industrial knowledge to help them deliver better customer experiences or solve problems faster. Besides their conventional programming skills, engineers can now add “prompt engineer” to their skill set.

article thumbnail

Build an image-to-text generative AI application using multimodality models on Amazon SageMaker

AWS Machine Learning Blog

CLIP model CLIP is a multi-modal vision and language model, which can be used for image-text similarity and for zero-shot image classification. This is where the power of auto-tagging and attribute generation comes into its own. Moreover, auto-generated tags or attributes can substantially improve product recommendation algorithms.

article thumbnail

Building Generative AI prompt chaining workflows with human in the loop

AWS Machine Learning Blog

They’re capable of performing a wide variety of general tasks with a high degree of accuracy based on input prompts. LLMs are specifically focused on language-based tasks such as summarization, text generation, classification, open-ended conversation, and information extraction. Prompt engineering is an iterative process.

article thumbnail

Evaluate the reliability of Retrieval Augmented Generation applications using Amazon Bedrock

AWS Machine Learning Blog

Additionally, evaluation can identify potential biases, hallucinations, inconsistencies, or factual errors that may arise from the integration of external sources or from sub-optimal prompt engineering. In this case, the model choice needs to be revisited or further prompt engineering needs to be done.

article thumbnail

Improved ML model deployment using Amazon SageMaker Inference Recommender

AWS Machine Learning Blog

We train an XGBoost model for a classification task on a credit card fraud dataset. Model Framework XGBoost Model Size 10 MB End-to-End Latency 100 milliseconds Invocations per Second 500 (30,000 per minute) ML Task Binary Classification Input Payload 10 KB We use a synthetically created credit card fraud dataset.

ML 101