Retrieval and RAG
RAG Pipelines, Retrieval and Monitoring
Explore RAG pipelines, document chunking, retrieval techniques and monitoring with LangSmith.
A small sample of 30,000+ courses curated from around the world, all available to DoJo members.
A free 30-minute conversation with Ted about your goals.
Already a member? Open this course (opens in a new tab)
Course topics
Retrieval and RAG
- RAG strategies
- Document chunking
- LangSmith monitoring
You check the sources
Find your fit
Is this a useful starting point?
For learners with Python, programming and command-line experience and an initial LLM application project.
- Starting point
- Intermediate
- Course length
- 5 total hours
- Lessons
- 62 lectures
Course by Sandra L. Sorel, Ligency
Course last updated: 12/2024
Requirements
- Basics web development and programming skills (1-2 xp)
- Python programming Language (1-2 xp)
- Basic command line operations
- Latest version of Python (3.7+)
- A Code Editor (recommanded : Visual Studio Code)
- One first experience with building LLM-driven applications
What is included
- 5 hours on-demand video
- 14 articles
- 35 downloadable resources
- Access on mobile
- Certificate of completion
DoJo membership: A$250 per month per seat, excluding GST. Includes fortnightly group support and a private member community.
Explore the lessons
Course curriculum.
7 sections • 62 lectures • 4h 55m total length
Introduction5 lectures • 19min
- Skills & Project requirements03:14
- Development Environment Setup & Course Files03:55
- Download the Starter Project00:16
- Integrate OpenAI into a Web Project (Quickstart)05:50
- Integrate OpenAI into a Web Project (Quickstart) : send first API request05:54
RAG : from Native (101) to Advanced - Pre-Indexing, Re-Ranking, Summarization19 lectures • 1hr 27min
- Introduction01:22
- OpenAI Setup & Configuration : step-by-step Guide00:20
- Starter project : Installation & Setup04:36
- Retrieval QA Integration (FAISS)04:17
- How to instantiate a ChatOpenAI model ?00:21
- Retrieval QA integration : Retriever and Generate components09:52
- Vector Stores (LangChain) & Embeddings explained00:33
- The Main Building Blocks02:50
- Build an End-2-End RAG Pipeline (ChromaDB)08:38
- Split Documents into Chunks00:21
- Build an End-2-End RAG Pipeline (ChromaDB) - Part 209:48
- Interactive playground (Google Colab) : Instructions00:14
- Interactive playground (Google Colab): With or Without RAG08:43
- Basic RAG Assessment 3 questions
- Advanced Techniques to Enhance the RAG pipeline05:00
- Download the Course Materials00:36
- [Part 1/4]-Advanced RAG : Query Translation and Enhancement (Decomposition)09:50
- [Part 2/4]-Advanced RAG : Query Decomposition and Enhancement - Answer queries09:42
- [Part 3/4] - Advanced RAG : Query Decomposition and Enhancement - Optimized Answ04:11
- [Part 4/4]-Advanced RAG : Query Decomposition and Enhancement05:36
Advanced RAG techniques & strategies12 lectures • 1hr 1min
- Introduction00:49
- Presentation & Setup00:22
- [Part 1/2] - Advanced RAG : multi-querying, retrieve and consolidate results09:32
- [Part 2/2] - Advanced RAG : multi-querying and generate accurate answers05:54
- Advanced RAG : RAG-Fusion00:06
- [Part 1/2] - Advanced RAG Fusion - multi-querying and reranking results04:51
- [Part 2/2] - Advanced RAG Fusion - generate context-aware responses04:56
- Advanced RAG : Corrective RAG (CRAG)00:07
- [Part 1/4] - Advanced RAG : Corrective RAG08:08
- [Part 2/4] - Advanced RAG : Corrective RAG - Retrieval Evaluator08:02
- [Part 3/4] - Advanced RAG : Corrective RAG - Rewrite & web tool08:05
- [Part 4/4] - Advanced RAG : Corrective RAG - generate response10:34
- Advanced RAG Quiz 3 questions
Optimized RAG : Document Transformers & Chunking Strategies10 lectures • 55min
- Section intro : Smart Text Division with LangChain02:00
- Level 1 - Split documents by Character vs. Recursively07:04
- Understanding the CharacterTextSplitter Parameters (Online tool : ChunkViz)00:02
- Level 2 - Split documents by character vs. recursively05:53
- Levels 3 - Document specific splitting : split code and markup06:56
- Levels 3 - Document-specific splitting : Code Splitting (Python)08:48
- Levels 3 - Document-specific splitting : PDF (unstructured.io)09:00
- Levels 3 - Document-specific splitting : extract and process elements from PDF d06:03
- Other Types of TextSplitters01:26
- Levels 4 & 5- Semantic Chunking (Embeddings-based) & Agentic approach07:57
- Text Splitters Quiz 1 question
LangSmith: Debug, Test, and Monitor LLM Applications3 lectures • 15min
- Introduction00:57
- RAG Implementation Tracing & Testing09:46
- Integrating LangSmith into your workflow04:33
From Native, to Advanced to Agentic RAG (LangGraph)8 lectures • 41min
- Introduction01:09
- Getting Started : Agent-based Workflow with LangGraph07:52
- Getting Started : Compile and Run the App (with Streamlit)07:47
- Agentic RAG : Build a Multi-agent Workflow as Graph00:26
- Define the Nodes10:28
- Define the Edges02:14
- Build the Workflow with Langraph03:32
- Compile and Run the Workflow07:32
Enhanced RAG quality - Conventional vs. Structured RAG (unstructured.io, GPT-4)5 lectures • 17min
- INTRO - Semi-structured RAG : to manage multiple data sources and content01:40
- Extract elements from PDF : tables, images...04:55
- Describe images with GPT-4 Vision07:57
- Process data sources into documents, index, retrieve and generate with LLM01:37
- [BONUS] - To Continue Your Learning Journey00:37
From learning to practice
Try this next.
Compare chunking or retrieval choices and inspect their effect on a sample RAG response.
A useful next step
Choose where to start.
Talk through your goals in a free 30-minute discovery call with Ted. Bring a task you want to improve and the tools you already use.
Book a discovery callExplore DoJo membership