Jason Haley

Ramblings from an Independent Consultant

Introducing Agentic RAG Python Sample - IT Support Ticket Search

Introducing Agentic RAG Python Sample – IT Support Ticket Search A Python sample demonstrating how to build an agentic, multi-agent RAG system using Microsoft’s Agent Framework I finally finished up the code for the Agentic RAG sample that has been a long time in the making … it will answer all the question types I’ve been after for awhile now: These were inspired by the https://github.com/amazon-science/mintaka project that I discovered a long time ago. The final project is a real-world, practical example of an Agentic Retrieval-Augmented Generation (RAG) application built in Python using Microsoft’s Agent Framework. If you’ve been curious about what agentic RAG actually looks like in code — not just diagrams and theory — this repo is meant to be a hands-on starting point. …

Hands-on Agent Framework Workshop Jan 2026

Yesterday Bill Wilder, Udai Ramachandran and I held the first In-person, hands-on, all-day, free. Agent Framework Dev Day in BURLINGTON MA for the year. This year, we targeted both .NET and python developers (last year we only focused on .NET). My presentation and labs focused on implementing Agentic RAG with Agent Framework. Talk: Agentic RAG NOTE: The repository has moved to the new Agent Framework Dev Day github. About the Lab This year I tried to stay away from the instructional labs that just turns into a treasure hunt, copy paste set of instructions … though not completely. This year I created notebooks to cover the fundamentals, then a hands on exercise that had some instructions and excercises - plus the solution to the exercises. Notebooks: The Ingestion Phase (.NET) …

My Session at Boston Code Camp 39

This past Saturday was Boston Code Camp 39 (fall edition). For those of you who don’t know, the Boston Code Camp is the one that started it all (back in 2004) - see wikipedia for more info … at this point it may also be the last remaining one (not sure.). I got to visit with many old friends that I mostly just see at Code Camp these days … many of which I met at a code camp some time in the past 20+ years. I did not get to attend any sessions due to taking the time to catch up with people instead. I presented a “lessons learned” session, which was well attended and very interactive. I had a lot of really good questions regarding RAG, chunking, etc. Lessons Learned from a Year of Building Copilot Agents & RAG Applications The presentation was a split …

Hands-on Boston AgentCon Workshop

This past Saturday, I held my latest hands on workshop: From Static Files to Smart Agents: Unlocking Document Intelligence at AgentCon Boston. I ended up with around 30 attendees. There was quite a bit of interaction, with some real practical questions being asked about RAG and GenAI applications. Hand-on-Lab: From Static Files to Smart Agents: Unlocking Document Intelligence The repository is located at: https://github.com/JasonHaley/agentcon-boston-workshop What is it? The end result (which is the “completed” branch of the repo), is a Chainlit application designed to provide four use cases: Compare a clause between two contracts and get detail and risk analysis of the clause Analyze a clause that is in one contract but not the other Compare two complete contracts Create a …

Microsoft Build 2025: Azure AI Search

Microsoft Build 2025: Azure AI Search If you use Azure AI Search for your RAG applications, you are going to be excited about the new features that were just announced at Microsoft Build 2025. If you want a video that provides a good overview, I’d recommend watching Pablo Castro’s talk Knowledge Retrieval: RAG for enterprise agents with Azure AI Search, he did a great job highlighting most of the new features. Agentic Retrieval (new feature) From the documentation site: “… agentic retrieval is a new parallel query processing architecture that incorporates user conversation history and Azure OpenAI models to plan, retrieve and synthesize queries for improved results. It produces high-quality grounding data for custom chat and generative AI solutions that include agents.” This …

Custom AI Search Skill to Convert Markdown Tables to JSON

Custom Azure AI Search Skill to Convert Markdown Tables to JSON I was recently asked what options there are for handling large tables in PDFs, when ingesting files for a RAG application. The question was concerning a retrieval system that was having a problem identifying relevant data in some tables. The problem seemed to be due to the headings not being in the same chunk as the data - so the data doesn’t have any context to indicate its meaning. This blog by Lu Zhang (Microsoft) - A Heuristic Method of Merging Cross-Page Tables based on Document Intelligence Layout Model describes how to identify and merge tables using the Azure AI Document Intelligence Layout Model, she also provides working code to do it on GitHub. She goes over how to get the tables, locate them and figure out …