/images/avatar.png

Let's talk Azure

Why Cosmos DB is the ideal choice for AI-Powered Applications

1. About this blog Are you struggling to convert natural language into SQL or not getting the results and accuracy you hoped for? If you find yourself in either of these situations, you’re in the right place! 🚀. All of us today are in a hurry to get things done with LLM and promote it to production. But things doesn’t work in that way. We need to carefully design our system to make it less non-deterministic (it’s already quite non-deterministic 😉).

Leveraging LangChain Agents with Function Calling to Build DTDL's Autonomous Customer Care Assistant

1. About this blogWelcome to the final episode of this blog series. We are now prepared to work with our agent to develop an autonomous customer care solution. Here are the key takeaways from this blog: Working with Langchain agents 🤖 Understanding function calling concepts 🧠 2. Langchain AgentsLangchain is a open-source framework that simplifies the development of LLM applications. It is all about having set of tools and abstractions that makes it easy to integrate LLM into your workflows, connect them to external data sources and build complex applciations.

Leveraging Azure Cosmos DB for Efficient Data Retrieval in DTDL CustomerCare

1. About this blogWelcome back! In this blog, we’ll explore vector databases and their use cases in building LLM applications. Specifically, we will utilize Azure Cosmos DB for Mongo vCore as our vector database solution. By the end of this blog you should be aware on how to work with Azure Cosmos DB for Mongo vCore and make use of it’s vector search capability. 2. Vector database and embeddings Vector databaseA vector database is a special type of database that stores data as high-dimensional vectors.

Building the Backbone: Data Ingestion and IVF index creation for DTDL's Autonomous Assistant

1. About this blogWelcome back! In this blog, we will learn how to prepare data for our retrieval process. There are various approaches to this, but we’ll use Azure Document Intelligence to extract information from unstructured documents. By the end, you’ll know how to: Work with the Azure Document Intelligence Layout model 📄 Perform custom chunking and add metadata 📝 Vectorize data into embeddings 🔍 2. DataaaaThe nature of data can vary greatly and often includes unstructured formats such as PDFs, audio, video, and images.

Transforming Customer Care: An Introduction to DTDL's Autonomous Assistant

1. About this blogHello, and welcome to the first blog in my DTDL-CustomerCare Series! In this post, I’ll introduce the overall concept and architecture in more depth. But first, let me share how this project began. The idea of developing a chatbot for the customer care department came to me during some discussions with my current client, who expressed interest in this area. I started brainstorming and planning, but due to a busy few months both professionally and personally, I couldn’t dedicate enough time to it.

Redefining RAG: Azure Document Intelligence + Azure CosmosDB Mongo vCore

1. About this blogThis time, I’ll be developing an application designed for use within our FlyersSoft company, to improve workforce efficiency. Idea is to introduce CosmicTalent, an application designed to empower HR and managers in effectively navigating employee information. By leveraging CosmicTalent, users can efficiently filter and identify eligible employees based on specific task requirements. 🚀 Few key takeaways Advanatages of Azure CosmosDB Mongo vCore’s native vector search capabilities over Azure Vector Search.