In this “Azure Cosmos DB for AI Engineers” blog post, you will learn how AI Engineers can use Azure Cosmos DB to support their AI solutions, focusing on storing and analyzing unstructured or semi-structured data.
AI Engineers design and implement intelligent apps and agents that simulate human perception using cognitive services, machine learning, and knowledge mining. Typical scenarios are anomaly detection, language understanding, text mining, search, among others. Let’s see why Azure Cosmos DB is the perfect database for AI Architectures on Azure.
Azure Cosmos DB and Azure Cognitive Services
Cognitive Services bring AI within reach of every developer—without requiring machine-learning expertise. All it takes is an API call to embed the ability to see, hear, speak, search, understand, and accelerate decision-making into your apps.
All those APIs return JSON documents, a native format for Azure Cosmos DB. AI applications may store those results in raw format just adding a unique ID, what is required for all documents in Azure Cosmos DB. There are three main reasons why you would save the results from Cognitive Services.
- Reuse, avoiding the cost and the latency processing over and over the same data. An example is sentiment analysis, you don’t need to submit the same review to the text analytics API more than once.
- Historic, for any kind compliance about data lineage.
- Advanced analytics, that now is supported for Azure Cosmos DB analytical store through Azure Synapse Link. An example would be an IoT scenario, where you are use Anomaly Detector API and save the anomalies for reporting, analytics, etc.
Check out our video on IoT Anomaly Detection with Jupyter Notebooks support, using Python and Cognitive Services.
#ai #analytics #tips and tricks #azure search #bots #cognitive services #htap #python
