End-to-End RAG Agent Development with DeepSeek-R1 and Ollama

Learn to build a Retrieval-Augmented Generation (RAG) application using DeepSeek-R1 and Ollama in this 13-minute tutorial video. Explore the implementation of OllamaEmbedding with in-memory vector store while working with DeepSeek-R1, a powerful 671 billion parameter model released in January 2025. Discover how this model, based on DeepSeek-V3, competes with OpenAI's o1 model in advanced reasoning tasks while maintaining cost efficiency and offering an impressive 128,000 token context length. Follow along with the provided GitHub repository to create your own RAG system that leverages these cutting-edge AI technologies for enhanced information retrieval and generation capabilities.