Description
Hands-On AI: Build a RAG Model from Scratch with Open Source is a course on how to develop a retrieval-augmented (RAG) model from scratch using open source tools, published by LinkedIn Online Academy. This is a hands-on course that focuses on teaching you how to develop a retrieval-augmented (RAG) model from scratch using open source tools. The course covers all the essential components, including data retrieval, embedding generation, vector databases, and integration with large language models. You will learn how to connect a retriever to a generator, optimize query results, and enhance model performance for real-world AI applications such as chatbots, document assistants, and knowledge-based systems.
This course provides a complete, hands-on approach to building RAG systems using open source frameworks, guiding individuals through data preprocessing, embedding creation, and vector database setup. This course explains how to effectively retrieve relevant context and feed it into language models for accurate, context-aware answers. Students will explore advanced concepts such as rapid optimization, model evaluation, and performance tuning, and gain the skills necessary to design scalable AI systems for information retrieval and question answering. By the end, learners will understand both the theory and practical workflow of building a RAG pipeline from data to deployment using open technologies.
What you will learn in Hands-On AI: Build a RAG Model from Scratch with Open Source:
- Generative AI
- Retrieval-Augmentative Generation (RAG)
- Artificial Intelligence (AI)
- Large Language Models (LLM)
- and …
Course specifications
Publisher: LinkedIn
Instructors: Dr. Alaa Moussawi
Language: English
Level: Advanced
Number of Lessons: 24
Duration: 2h 21m
Course topics
Hands-On AI: Build a RAG Model from Scratch with Open Source Prerequisites
None
Pictures
Hands-On AI: Build a RAG Model from Scratch with Open Source introduction video
Installation guide
After Extract, watch with your favorite Player.
English subtitle
Quality: 720p
Downloadly link
Rapidgator link
File password (s): www.downloadly.ir
Size
301 MB
