Building RAG-Based LLM Applications with Meditron, Mistral, and Azure

عدد الدروس : 57 عدد ساعات الدورة : 31:48:33 شهادة معتمدة : نعم التسجيل في الدورة للحصول على شهادة

للحصول على شهادة

  • 1- التسجيل
  • 2- مشاهدة الكورس كاملا
  • 3- متابعة نسبة اكتمال الكورس تدريجيا
  • 4- بعد الانتهاء تظهر الشهادة في الملف الشخصي الخاص بك
A comprehensive course on creating Retrieval-Augmented Generation (RAG) apps using medical, financial, and general-purpose LLMs with no/low code solutions.

قائمة الدروس

عن الدورة

This course provides a hands-on guide to building RAG-based applications using a variety of large language models (LLMs) across multiple domains, including healthcare, finance, law, and enterprise solutions. It is designed for developers, AI engineers, and enthusiasts looking to deploy LLM-powered chatbots and applications quickly and efficiently.

Learners start with domain-specific RAG apps, such as oncology chatbots powered by Meditron 7B, and financial assistant chatbots using Intel’s Neural Chat LLM. The course demonstrates how to use no-code tools like LlamaIndex Create Llama and low-code platforms like Dialogflow CX and Vertex AI to accelerate development.

Advanced techniques include integrating vector databases like Qdrant, Weaviate, and ChromaDB, building Mistral 7B and Zephyr 7B RAG pipelines, implementing re-ranking and merger retrievers for long-context queries, and creating private knowledge apps. The course also covers deploying end-to-end applications on Azure, GCP, and FastAPI, along with specialized use cases such as LawGPT, Veterinary chatbots, and private StackOverflow-style knowledge apps.

By the end of the course, learners will be able to design, build, and deploy robust, domain-specific RAG apps using state-of-the-art LLMs, vector databases, and modern retrieval techniques.