Vectorless RAG - Local Financial RAG Without Vector Database | Tree-Based Indexing with Ollama

Complete tutorial and source code (requires MLExpert Pro): https://www.mlexpert.io/academy/v1/ai-agents/vectorless-rag Do you really need embeddings and a vector database to create a RAG system? In this video, we'll build entirely local RAG that uses the document structure to choose sections of it for generating it's answer. We'll use Ollama, LangChain, and we'll skip on the embeddings and vector databases. Original paper: https://arxiv.org/abs/2401.18059 Tree index in LlamaIndex: https://developers.llamaindex.ai/python/framework/module_guides/indexing/index_guide/#tree-index PageIndex: https://github.com/VectifyAI/PageIndex AI Academy: https://mlexpert.io/ Work with me: https://mlexpert.io/consulting LinkedIn: https://www.linkedin.com/in/venelin-valkov/ Follow me on X: https://twitter.com/venelin_valkov Discord: https://discord.gg/UaNPxVD6tv Subscribe: http://bit.ly/venelin-subscribe GitHub repository: https://github.com/curiousily/AI-Bootcamp 👍 Don't Forget to Like, Comment, and Subscribe for More Tutorials! 00:00 - What is Vectorless RAG? 09:10 - Financial Document Review 09:49 - Code walkthrough 13:30 - RAG demo with 3 queries Join this channel to get access to the perks and support my work: https://www.youtube.com/channel/UCoW_WzQNJVAjxo4osNAxd_g/join #rag #ollama #langchain #vectordatabase