Latest
-

Microsoft-Decision-1 in a Document Processing Pipeline
This article explores how Microsoft Decision-1 helps classify ambiguous sources in a document processing pipeline, combining bounded model decisions with deterministic validation, explicit confidence thresholds, and safe fallback paths to keep applications in control. Read more
-

Decoupling Data and Logic: Using Fabric Data Agents and Foundry to Automate Presentation Generation
Discover how to build production-grade agentic platforms that unify fluid, non-deterministic insights with rigid, deterministic deliverables. This article details an enterprise architecture combining Microsoft Fabric… Read more
-

Beyond the Alert: Building Self-Healing Pipelines with Azure SRE Agent and GitHub Copilot
Shift from reactive monitoring to agentic reliability. Build a self-healing pipeline using Azure SRE Agent for autonomous investigation and GitHub Copilot for remediation. This post… Read more
-

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… 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
Archives
-

Effortlessly Add Traces to Your LangChain Agent with LangSmith
After developing your LangChain Agent or LLM application, ensuring its ongoing performance is crucial. LangSmith provides seamless trace capabilities, bridging the gap between prototypes and production-grade applications. This article demonstrates how to implement LangSmith tracing to monitor and optimize your agent’s behavior effectively. Read more
-

Semantic Kernel Python Vector Search with Cosmos DB for MongoDB
This article serves as a fundamental guide for utilizing Semantic Kernel and Python with Azure Cosmos DB for MongoDB. It covers setting up Python, and loading data into Azure Cosmos DB. The process facilitates seamless Semantic Kernel integration and offers powerful language capabilities for developers. Read more
-

Empower your AI Agent with Azure Cosmos DB
This article explores the implementation of a LangChain Agent using Azure Cosmos DB for MongoDB vCore to handle traveler inquiries and bookings. The project provides detailed instructions for setting up the environment and loading travel data, aiming to empower developers to integrate similar agents into their solutions. Read more
-

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