LangChain: Azure AI Gets a Fresh Start & Smarter CI Workflows
The LangChain team shipped version 1.2.13 with a significant Azure AI Foundry integration update, moving away from deprecated classes to newer, more consistent APIs. Meanwhile, Mason Daugherty enhanced the project's CI workflows with smarter PR labeling and more nuanced auto-closing behavior, making life easier for both contributors and maintainers.
Duration: PT3M55S
Episode overview
This episode is a short developer briefing from LangChain.
It explains recent repository work in plain language.
- Show: LangChain
- Published: 2026-03-20T10:04:33Z
- Audio duration: PT3M55S
Transcript excerpt
This excerpt keeps the crawler page concise. Listen to the episode or use the RSS feed for the full update.
Hey there, developers! Welcome back to another episode of the LangChain podcast. I'm your host, and wow, do we have some satisfying updates to dig into today from March 19th. You know that feeling when you're cleaning up your codebase and everything just starts clicking into place? That's exactly the vibe I'm…
Let's start with the big story - Santiago, known as santiagxf on GitHub, just delivered a really clean fix for Azure AI Foundry integration. This is one of those changes that might not seem flashy on the surface, but it's exactly the kind of maintenance work that keeps a project healthy and moving forward.
Here's what happened: The team had some deprecated Azure AI classes hanging around - you know how it goes, new APIs come out, but the old ones stick around for a while. Santiago went through both the classic and v1 versions of LangChain and updated everything to use the newer, more consistent classes. We're talking…
What I love about this change is that it's not just a find-and-replace job. Santiago made sure the provider mappings were consistent across the entire codebase. If you're working with Azure AI Foundry, your chat models and embeddings are now using the same…
Now,…
Fi…