Description
“RAG with Local LLMs: Ollama, LangChain & ChromaDB” is a course on Retrieval-Augmented Generation (RAG) applications using Large Language Models, published by the online academy Udemy. You will learn how RAG systems combine document retrieval with language generation to produce more relevant, context-aware responses based on your own data. The course introduces Ollama for running local language models, LangChain for orchestrating retrieval and generation workflows, and ChromaDB for storing and searching vector embeddings. You will thoroughly explore key concepts such as document loading, text splitting, embedding generation, vector databases, semantic search, retrieval pipelines, and prompt engineering. Through hands-on, step-by-step implementation, you will discover how to connect your documents to an AI model, retrieve relevant information, and generate accurate, context-based responses.
You will also gain a deeper understanding of how local AI solutions can enhance privacy, customization, and control over your applications. Whether you are a Python developer, an AI enthusiast, or an aspiring machine learning engineer, this course provides a solid, practical foundation for building RAG applications using local language models and open-source tools. Throughout the course, you will explore advanced techniques—such as evaluating retrieval quality, comparing various search methods (including BM25 and re-ranking), and building an interactive document-based Q&A application. This will provide a deeper understanding of the practical applications of these technologies and prepare you to develop real-world, professional projects in this field. The course offers a clear progression from fundamental concepts to the implementation of a complete RAG (Retrieval-Augmented Generation) system.
What you will learn in (English)RAG with Local LLMs: Ollama LangChain & ChromaDB:
- Run local generation and embedding models with Ollama and call them from Python.
- Explain sentence embeddings and calculate cosine similarity with NumPy.
- Extract, clean and split text while preserving context and source metadata.
- Build and update a persistent ChromaDB document index.
- Compose a retriever, prompt, local LLM and parser with LangChain and LCEL.
- and …
Course specifications
Publisher: Udemy
Instructors: 達也 山本
Language: English
Level: Introductory to Advanced
Number of Lessons: 62
Duration: 1 hour and 39 minutes
Course topics
(English)RAG with Local LLMs: Ollama LangChain & ChromaDB Prerequisites
Basic Python: variables, functions, imports and running a script.
Comfort with a terminal and installing development tools.
Python 3.12, Ollama and a computer suitable for local models; 16 GB RAM or more is recommended.
Allow at least 15 GB of free disk space, with additional space for optional models and your own documents.
An internet connection for initial package and model downloads. No paid cloud LLM API key is required.
Pictures
(English)RAG with Local LLMs: Ollama LangChain & ChromaDB introduction video
Installation guide
After Extract, watch with your favorite Player.
English subtitle
Quality: 1080p
Downloadly link
Rapidgator link
File password (s): www.downloadly.ir
Size
220 MB