Latest
-
Designing Sequential Multi-Agent Pipelines with Microsoft Foundry
Multi-agent systems are increasingly built as structured workflows rather than single autonomous agents. This article explores a sequential multi-agent pipeline built with Microsoft Foundry, where specialized agents collaborate to validate marketing content using Azure AI Search, MCP tools, and CI/CD deployment patterns designed for production-ready AI systems. Read more
-
Optimizing AI Agents for Scale: Triage, Throttle Control, and Model Right-Sizing
FleetMind, an autonomous trucking platform, utilizes Microsoft Foundry to manage telemetry from fleets. At scale, invoking LLM reasoning for every event turned routine signals into… Read more
-
From Chatbots to Autonomous Agents: Building an Always-On Risk Platform
The article discusses the evolution of generative AI towards fully autonomous systems capable of continuous decision-making without human prompts. It highlights an autonomous risk platform… Read more
-
Deploying MCP Servers with Azure Container Apps
In this article, we explore how to deploy and run multiple Model Context Protocol (MCP) servers using Azure Container Apps. We’ll demonstrate how to enable… Read more
-
The Perfect AI Team: Azure Cosmos DB and Azure App Service
AI advancements are impressive, and their true impact emerges when seamlessly integrated into business processes. Azure Cosmos DB and Azure App Service create the perfect… Read more
Curated Materials
Issue 1 – June 2024
This guide provides essential tips and best practices for managing and optimizing partitioning in Azure Cosmos DB.
Guided Journey – July 2024
Azure Machine Learning
This guide provides a comprehensive walkthrough for using Azure Machine
Learning to build a classification model based on risk data pulled from Azure.
Archives
-
Improve LLM Performance Using Semantic Cache with Cosmos DB
Explore the advantages of leveraging Azure Cosmos DB Semantic Cache to boost LLM retrieval performance with OpenAI, resulting in cost savings and enhanced response times. This article offers a detailed walkthrough for seamlessly integrating the semantic cache into your current web application, showcasing its effects on LLM retrieval time, API expenses, and scalability. Read more
-
Azure Cosmos DB for MongoDB HNSW Vector Search
This article discusses leveraging the new HNSW Vector Index feature in Azure Cosmos DB for MongoDB vCore using Python and LangChain. It covers enabling the HNSW index, setting up Python, loading data, and conducting a vector search. Read more
-
LangChain RAG with React, FastAPI, Cosmos DB Vectors: Part 3
In Part 3, we focus on crafting a dynamic React web interface, the final step in our series. This installment marks the conclusion of our three-part journey, where we’ve achieved significant milestones, from loading vectors into Azure Cosmos DB for MongoDB vCore to developing our React UI. Read more
-
LangChain RAG with React, FastAPI, Cosmos DB Vector: Part 2
The LangChain RAG Pattern series, part 2, explores FastAPI interface creation for enhanced application functionality and user experience. It delves into leveraging FastAPI’s capabilities for efficient request handling and optimal performance, paving the way for a comprehensive LangChain RAG implementation. Read more
-
LangChain RAG with React, FastAPI, Cosmos DB Vector: Part 1
Discover the first installment of our LangChain RAG Pattern series, unraveling the integration of React, FastAPI, and Cosmos DB Vector Store. Learn to load documents and blobs for seamless application development. Read more
-
LangChain Vector Search with Cosmos DB for MongoDB
A comprehensive guide on using LangChain to set up a vector store and perform vector search on Azure Cosmos DB for MongoDB vCore using Python. Includes instructions on prerequisites, setting up Python, loading data into Cosmos DB, creating a search index, and executing a vector search query. Read more
-
Azure Prompt Flow with Vector Search
Learn how to create an Azure Machine Learning Prompt Flow to ask questions using a Weaviate vector database. Set up connections, create a Q&A flow, add a Weaviate Python Client, and run the workflow. Read more
-
Prompt Flow Connection to OpenAI
We will explore integrating Azure Machine Learning Prompt Flow with OpenAI to leverage advanced machine learning and innovative technologies. This article guides readers through creating an OpenAI API key, setting up the Prompt Flow connection, and using Azure’s infrastructure with OpenAI solutions. The walkthrough lays the foundation for harnessing combined potential, enhancing predictive modeling, and… Read more
-
Setting up Weaviate on Azure with Multi-Container App
I’ll walk you through the step-by-step process of setting up Weaviate on Azure using Docker Compose and Azure Multi-Container App. We’ll cover everything from creating a resource group and an App Service plan to configuring Docker Compose files, validating deployments, ensuring persistent storage, and providing hands-on instructions for conducting vector search with Weaviate. Additionally, I’ll… Read more
-
Faster R-CNN Unleashed: Crafting an End-to-End Solution for Damage Detection
Discover the potential of Faster R-CNN in computer vision with our latest article. Dive into the creation of a robust AI damage detection system, utilizing custom object detector models based on Faster R-CNN with PyTorch. Learn to identify and localize objects like shipping containers while minimizing false positives using synthetic data. Read more
Stochastic Coder 