You can now run multiple repetitions of your experiment in LangSmith. This helps smooth out noise from variability introduced by your application or from your LLM-as-a-judge evaluator, so you can build confidence in the results of your experiment.
I just built an Insanely Complex RAG Flow with LangChain's LangGraph – You Won't Believe How Easy It Is
I've been working on an open source git repo for advanced RAG flows with LangChain 's LangGraph🦜🕸️, heavily inspired by the LangChain Cookbook by Lance Martin and
I am proud to share that my free AI psychotherapy app has achieved remarkable results: • 1.28M+ users on Android • 10k+ reviews • LangChain + OpenAI libraries • 8 minutes average usage time
This achievement shows that hard work and dedication truly pay off.
We've listened to your feedback and made major improvements to our docs. With the release of LangChain v0.2 today, we now have versioned docs, with clearer structure and consolidated content.
With dataset splits, it's now easier to run evaluations on a subset of your dataset in LangSmith. You can tag examples with different split names, edit and add to splits, and filter on your desired criteria.
We've added a series of templates and documentation showing off how to build generative UI applications using LangChain JS/TS & Next.js. These templates include: - 🌆 generative UI in Next.js - 🤖 streaming agent events - 🛠️ streaming tool calls and more!
🎉 Thrilled to announce that I'm joining the Langflow team! It's been an exciting journey collaborating with the LangFlow team since the early days of LangFlow (screenshot below from a webinar together on no-code LangChain), and now I'm officially joining the team.