RAG/Local LLM

Join us for an exciting deep dive into the world of RAG (Retrieval-Augmented Generation) and Local LLMs (Large Language Models)! Whether you're new to the field or an experienced practitioner, this meetup is designed to explore the cutting-edge tools and strategies for deploying and leveraging local LLMs for retrieval-augmented workflows.

What We'll Cover

• Tech Stack Overview:
• Ollama: Streamline local LLM management and inference.
• OpenWebUI: Simplify and enhance the local LLM experience with a flexible UI.
• LangFlow: Design, debug, and visualize LLM pipelines with ease.
• QdrantDB: High-performance vector search for efficient document retrieval.
• How RAG Works:
  We'll break down the Retrieval-Augmented Generation process—combining vector-based retrieval with LLMs to generate context-aware, accurate, and efficient responses.
• Practical Applications:
  Learn how to use this stack for real-world use cases like custom chatbots, knowledge management, summarization, and more—all while keeping your data private and under your control.