article thumbnail

How DPG Media uses Amazon Bedrock and Amazon Transcribe to enhance video metadata with AI-powered pipelines

AWS Machine Learning Blog

With a growing library of long-form video content, DPG Media recognizes the importance of efficiently managing and enhancing video metadata such as actor information, genre, summary of episodes, the mood of the video, and more. Video data analysis with AI wasn’t required for generating detailed, accurate, and high-quality metadata.

Metadata 117
article thumbnail

Accelerating insurance policy reviews with generative AI: Verisk’s Mozart companion

Flipboard

Along with each document slice, we store the metadata associated with it using an internal Metadata API, which provides document characteristics like document type, jurisdiction, version number, and effective dates. This process has been implemented as a periodic job to keep the vector database updated with new documents.

professionals

Sign Up for our Newsletter

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

article thumbnail

How Backstage streamlines software development and increases efficiency

IBM Journey to AI blog

GitOps for repo data Backstage allows developers and teams to express the metadata about their projects from yaml files. This potential stems from their role as force-multipliers in the technology sector, emphasizing the importance of leveraging existing software engineering talent effectively to spur economic growth and innovation.

article thumbnail

How to build a decision tree model in IBM Db2

IBM Journey to AI blog

Here are some of the key tables: FLIGHT_DECTREE_MODEL: this table contains metadata about the model. Examples of metadata include depth of the tree, strategy for handling missing values, and the number of leaf nodes in the tree. Software engineering for machine learning: A case study. Amershi, S., Nagappan, N.,

article thumbnail

Amazon Personalize launches new recipes supporting larger item catalogs with lower latency

AWS Machine Learning Blog

Return item metadata in inference responses – The new recipes enable item metadata by default without extra charge, allowing you to return metadata such as genres, descriptions, and availability in inference responses. If you use Amazon Personalize with generative AI, you can also feed the metadata into prompts.

Metadata 118
article thumbnail

Read graphs, diagrams, tables, and scanned pages using multimodal prompts in Amazon Bedrock

AWS Machine Learning Blog

However, we’re not limited to using generative AI for only software engineering. You can also read diagrams and images from engineering, architecture, and healthcare. As you can see, the LLM acts as your advisor now for questions related to this architecture. For this example, we use a process diagram taken from Wikipedia.

LLM 104
article thumbnail

Build a dynamic, role-based AI agent using Amazon Bedrock inline agents

AWS Machine Learning Blog

For this demo, weve implemented metadata filtering to retrieve only the appropriate level of documents based on the users access level, further enhancing efficiency and security. The role information is also used to configure metadata filtering in the knowledge bases to generate relevant responses. Nitin Eusebius is a Sr.