How to learn from tutorials
- Run tutorials with a tiny corpus first.
- Write down every setting you change.
- Compare retrieval before and after each change.
- Save failed questions as future evaluation cases.
Tutorials
Learn RAG by building, testing, and improving
Filter tutorials by level and topic. Each tutorial includes outcomes, prerequisites, step-by-step guidance, trusted official references, and next steps.
Beginner90-120 min video sources
Complete tutorial: build a trustworthy RAG knowledge assistant
A full end-to-end tutorial for planning, building, testing, and improving a RAG system without pretending API keys or production infrastructure are already solved.
Outcome: A working conceptual and implementation-ready blueprint for a source-grounded document Q&A assistant.
Dify or LangChaindocument parserembedding modelvector databaseevaluation checklist
Open tutorialBeginner45-75 min
Build a RAG chatbot with Dify
Use Dify as a visual platform for a knowledge-base-backed assistant.
Outcome: A Dify chatbot connected to a curated knowledge base with retrieval settings and source review.
Difyknowledge basemodel provider
Open tutorialIntermediate60-90 min
Build a local RAG prototype with Ollama and a vector database
A privacy-oriented learning path for running a small RAG prototype locally.
Outcome: A local prototype plan using local models plus Chroma or Qdrant.
OllamaChroma or Qdrantlocal embedding model
Open tutorialIntermediate45-90 min
Evaluate a RAG system
Build a practical evaluation loop for retrieval quality, answer faithfulness, and citations.
Outcome: A reusable evaluation checklist and first regression set.
RagasTruLensPhoenix / ArizeLangfuse
Open tutorialAdvanced45-75 min
Improve retrieval quality
Diagnose and improve weak search results before blaming the model.
Outcome: A practical improvement plan for chunking, metadata, hybrid search, and reranking.
vector databasererankerevaluation set
Open tutorialBeginner30-60 min
Add citations to RAG answers
Design answer traceability so users can verify claims quickly.
Outcome: A citation pattern that connects generated claims to source passages.
source metadataprompt templateUI source panel
Open tutorialBeginner45-75 min
Design a knowledge base for RAG
Information architecture for reliable retrieval.
Outcome: A governed knowledge-base plan with source authority, metadata, and update rules.
metadata schemadocument inventorysource policy
Open tutorial