RAG Systems from Scratch

1. 1

   Building a RAG Pipeline from Scratch with Python (2026)

   Build a complete RAG pipeline from scratch with Python. No frameworks, no black boxes — just plain Python code you actually understand.

   September 1, 2026
2. 2

   Evaluating RAG Systems: Metrics That Actually Matter

   Learn how to evaluate RAG systems with the right metrics. Precision recall faithfulness and relevance benchmarks that actually improve your pipeline.

   September 1, 2026
3. 3

   Query Expansion and Rewriting for Better RAG Retrieval

   Query expansion and rewriting for RAG: LLM query rewriting, MultiQueryRetriever, HyDE, query decomposition, and step-back prompting — measured with RAGAS.

   September 24, 2026
4. 4

   HyDE Explained: Hypothetical Document Embeddings for RAG

   HyDE explained: Hypothetical Document Embeddings close the query-document gap with LangChain HypotheticalDocumentEmbedder, custom prompts, LlamaIndex transforms, and RAGAS measurement.

   September 23, 2026
5. 5

   Parent-Child Chunking: Advanced Document Splitting for RAG

   Parent-child chunking tutorial for RAG: small-to-big retrieval with LlamaIndex HierarchicalNodeParser, AutoMergingRetriever, and LangChain ParentDocumentRetriever.

   September 24, 2026
6. 6

   Contextual Compression in RAG: Retrieve Less, Answer Better

   Contextual compression RAG tutorial with LangChain: LLMChainExtractor, EmbeddingsFilter, reranker pipelines, and measuring gains with RAGAS context precision.

   September 24, 2026
7. 7

   Agentic RAG: Combining AI Agents with Retrieval

   Agentic RAG tutorial: build grade-and-retry retrieval loops with LangGraph, Corrective RAG (CRAG), LlamaIndex ReActAgent, and production guardrails for cost and latency.

   September 24, 2026
8. 8

   GraphRAG Explained: Knowledge Graphs Meet Retrieval-Augmented Generation

   GraphRAG explained: knowledge graphs for multi-hop and global RAG queries with Microsoft GraphRAG, Neo4j + LlamaIndex, community summarization, and hybrid agentic routing.

   September 24, 2026
9. 9

   Caching Strategies for RAG: Reduce Latency and API Costs

   Four RAG caching layers explained: embedding cache, retrieval cache, semantic response cache, and prompt caching, with threshold tuning and hit-rate monitoring.

   September 25, 2026
10. 10

    Scaling RAG to Millions of Documents: Architecture Patterns

    Six architecture patterns for scaling RAG to millions of documents: hybrid retrieval, chunking, reranking, index sharding, incremental ingestion, and caching.

    September 25, 2026
11. 11

    RAGAS Tutorial: Automated Evaluation for RAG Pipelines

    RAGAS tutorial: evaluate RAG pipelines with faithfulness, answer relevancy, context precision, and context recall metrics using LLM-as-a-judge and synthetic testsets.

    September 24, 2026

Want more paths? Browse all series or pick a topic.