📢 New Blog Post: Build a GenAI-powered chatbot with Kedro + RAG Hey folks! We just published a new blog post showing how you can use Kedro to build structured, modular GenAI applications, with a focus on Retrieval-Augmented Generation (RAG). In this example, we used real questions from our Slack support channel to build a chatbot that can answer Kedro-related queries using LangChain, Deep Lake, and OpenAI models - all implemented with Kedro pipelines. ✨ What you’ll learn: • How to organize GenAI workflows using Kedro • Tricks for handling prompts, LLMs, and custom objects in a pipeline • How RAG compares to plain LLM output • What’s needed to take this toy project to production 📚 Read the post: https://kedro.org/blog/building-a-genai-powered-chatbot-using-kedro-and-langchain 💻 Source code: https://github.com/kedro-org/kedro-academy/tree/main/kedro-rag-chatbot youtube Demo Let us know what you think or if you want to try this out with your own knowledge base!