intermediate
8 min read
Build and Debug a Small RAG Pipeline
A clean pipeline that answers confidently and wrongly is not a mystery. It is a trace you have not read yet.
Read tutorialworkflow
Retrieval-Augmented Generation
Systems that retrieve external evidence and provide it to an LLM to support generated answers, including their pipeline, data lifecycle, and failure modes.
Tagged articles
Retrieval-Augmented Generation articles
30 articles in this tag.
intermediate
11 min read
Evaluate a RAG Reranking Stage Against Relevance Judgments
The reranker "feels" better. The top result looks more relevant than it did before. And yet you cannot say whether the stage earned its latency, because…
Read tutorial
intermediate
11 min read
How to Evaluate RAG Retrieval Before Blaming the LLM
Your RAG system just produced a confident, polished, and completely wrong answer. The natural instinct is to blame the model—swap the prompt, change the…
Read tutorial
intermediate
10 min read
Hybrid Retrieval Math: Combining Lexical and Vector Search
Two retrievers return two different top-5 lists for the same query. You merge them, and the merged order looks like it was decided by a coin flip. It…
Read tutorial
beginner
11 min read
What to Learn Before LLM Frameworks: A First-Principles Path
Frameworks change. The model underneath them doesn't. Learn the mechanism first, and every new tool becomes just another wrapper around something you…
Read tutorial
intermediate
7 min read
LLM Portfolio Project Ideas
A portfolio is not a trophy shelf. It is evidence of judgment — proof that you can pick a real problem, make the right tradeoffs, and ship something that…
Read tutorial
intermediate
12 min read
Practice Auditing Evidence for RAG Answer Claims
A citation is a pointer, not a proof. This drill teaches you to stop trusting the pointer and start reading the span.
Read tutorial
intermediate
9 min read
Practice Resolving Conflicting Sources in a RAG Answer
Retrieval worked. Three chunks came back, all relevant, all cited. Two of them disagree. Now what?
Read tutorial
intermediate
11 min read
Practice Reviewing Provenance in a RAG Knowledge Base
A citation chip proves a chunk was retrieved. It does not prove the chunk was ever authorized or trustworthy.
Read tutorial
intermediate
9 min read
Practice Propagating RAG Document Corrections and Deletions
A query returns a sentence the source no longer contains. The team blames the model. The model is innocent — the index is still holding a chunk that was…
Read tutorial
intermediate
13 min read
RAG and Agents Practice Exercises
You can explain RAG. You can sketch an agent loop. But when a real question lands on your desk, do you know whether to retrieve, route, or just answer?…
Read tutorial
intermediate
10 min read
RAG Answer Quality Evaluation: Faithfulness, Relevance, and Completeness
Your retriever finally returns the right documents. The chunks look relevant. The context window is full of plausible evidence. And the model still hands…
Read tutorial
intermediate
10 min read
RAG Chunking Explained: How to Split Documents Without Losing Meaning
You ask your RAG system a question. It retrieves a passage that is technically relevant and completely useless—a sentence fragment that starts mid-thought,…
Read tutorial
intermediate
10 min read
RAG Chunking Math: Calculate Chunk Counts, Overlap, and Token Use
A 1,500-token document with 512-token chunks and 15% overlap quietly becomes four chunks, and the same paragraph now lives in two of them. Nobody chose…
Read tutorial
intermediate
11 min read
Measure Citation Coverage and Support in RAG Answers
A citation marker is a promise. The sentence says this passage backs me up. Most RAG evaluations never check whether the promise holds — they check whether…
Read tutorial
intermediate
8 min read
RAG Citations and Grounded Answers: Linking Claims to Evidence
A citation is not proof. It is a pointer — and a pointer is only as trustworthy as the instruction that produced it and the check that verifies it.
Read tutorial
intermediate
9 min read
RAG Knowledge-Base Poisoning: When Retrieved Evidence Is Manipulated
A support chatbot answers a customer's question with total confidence. The answer cites a document from the company knowledge base. The only problem: the…
Read tutorial
intermediate
12 min read
The RAG Pipeline Explained: From Documents to Grounded Answers
You know RAG retrieves documents and feeds them to a language model. But if someone asked you what actually happens between a source PDF and a grounded…
Read tutorial
intermediate
10 min read
RAG Query Rewriting Explained: Helping Retrieval Ask the Right Question
Your knowledge base has the answer. You know it does. You wrote the documents, chunked them carefully, embedded them, and verified the chunks look right.…
Read tutorial
intermediate
11 min read
RAG Reranking Explained: Choosing the Best Evidence After Retrieval
Your retriever returns ten chunks. They all look topically related to your question. None of them actually answer it. The LLM dutifully composes a response…
Read tutorial
intermediate
11 min read
RAG Retrieval Metrics: Precision, Recall, Reciprocal Rank, and NDCG
Two retrievers return the same relevant chunk. One puts it at rank 1; the other buries it at rank 4. A single "accuracy" number calls them identical. The…
Read tutorial
intermediate
10 min read
Simple RAG Tutorial
Reading about RAG is easy. Building one is where the real learning happens—because the first pipeline you run will almost certainly fail in ways no diagram…
Read tutorial
intermediate
7 min read
RAG vs Plain LLMs
Most people assume RAG is a different kind of model—a smarter cousin of the plain LLM. It's not. RAG doesn't change the model at all. It changes what goes…
Read tutorial
intermediate
9 min read
The Candidate-Recall Ceiling in RAG Reranking
You swap in a stronger reranker. The top three results look sharper, the ordering feels smarter, and the demo lands. Then you measure recall and it barely…
Read tutorial
intermediate
11 min read
Test RAG Chunking Strategies on a Small Document Set
Retrieval misses rarely announce their cause. The answer was in the document, the query was reasonable, and the model still returned something useless. The…
Read tutorial
intermediate
10 min read
Test RAG Query Rewrites Against a Fixed Retrieval Task
You add a rewrite step. The demo answers the question. You feel clever. Then someone asks a slightly different question and the whole thing falls apart,…
Read tutorial
intermediate
11 min read
Test Metadata Filters in a Small Vector Search
A filter can be correct and still delete your best evidence. Here is how to watch it happen in twenty lines of NumPy.
Read tutorial
intermediate
10 min read
Vector Databases Explained: Where Semantic Search Finds Evidence
A vector database is not a fancy search box or a generic "database for AI." It is the retrieval engine that decides which evidence earns a seat on the…
Read tutorial
intermediate
9 min read
What Are Embeddings? How Meaning Becomes Searchable
You search your company's help docs for "how do I reset my password?" and get nothing useful. You know the answer is in there—you've read the page…
Read tutorial
intermediate
7 min read
What Is Retrieval-Augmented Generation (RAG)?
Most people assume an LLM knows everything. Ask it about your company's return policy, and it will confidently answer—even if that policy changed last week…
Read tutorial