/4 min
Why Tables Are the #1 Silent Failure in Production RAG (and How I Fixed Mine)
Tables break RAG because flattening them destroys row/column relationships; keep them as HTML and attach headers to every row to fix it.
Tag
#rag
29 posts.
/2 min
Why RAG fails in production — and where
When RAG breaks, the model usually isn't the problem — retrieval is, about 73% of the time. Here's the real failure map and what to fix first.
/4 min
Why Payload Filtering Is Qdrant's Killer Feature (and How Filterable HNSW Actually Works)
Qdrant applies payload filters during HNSW graph traversal, not after — so filtered queries stay fast and always return a full top-k.
/2 min
Why I don't use LangChain in production RAG
Frameworks are great for a demo. In production, the abstraction you can't see into costs more than it saves.
/4 min
Why Dense Retrieval Fails on Acronyms, IDs, and Code (and How Hybrid Fixes It)
Vector search misses exact terms like SKUs and error codes because embeddings blur rare tokens; a sparse channel restores exact-match signal.
/3 min
When NOT to use RAG (RAG vs fine-tuning vs prompting)
RAG became the default reflex for every LLM problem. Often it's the wrong tool. A straight decision framework for RAG vs fine-tuning vs just prompting.
/4 min/reference
Separating Retrieval Failures From Generation Failures in RAG Evaluation
Score retrieval and generation separately: the pair of metrics localizes whether a bad RAG answer is a retriever or an LLM problem.
/4 min/reference
Self-RAG vs Corrective RAG (CRAG): Which Self-Correcting Pattern Should You Use?
CRAG fixes retrieval quality before generation; Self-RAG uses fine-tuned reflection tokens to critique its own output. Here's when to use each.
/3 min/reference
Reference-Free vs Reference-Based LLM Evaluation: When You Actually Need Ground Truth
Reference-based evals compare output to a known correct answer; reference-free evals score intrinsic properties like grounding without ground truth.
/2 min/reference
A reference architecture for production RAG
The stages every production RAG system needs — indexing, query-time retrieval, and always-on evaluation — and how to order them.
/3 min
OCR Confidence Scores: Using Them to Gate What Enters Your RAG Index
Use per-recognition OCR confidence as a metadata gate: drop, re-OCR, or flag low-confidence spans before they pollute your RAG index.
/2 min
The single most useful log line in a RAG system
If you log one thing in your RAG pipeline, log the final assembled prompt. It's the fastest path from 'bad answer' to root cause.
/3 min/reference
Metadata Is the Unsung Hero of RAG Accuracy: What to Extract and How to Filter
Attach structural, content, and contextual metadata to chunks, then use it for filtered multi-axis retrieval to sharpen RAG accuracy.
/3 min/reference
Layout-Aware vs VLM Parsing: When to Pay for a Vision Model to Read Your PDFs
Use VLM parsing for scanned, complex, or merged-cell PDFs; use layout parsers for clean digital docs to save cost and latency.
/4 min
Designing an Idempotent Document Ingestion Pipeline (Content Hashing, DLQs, Reprocessing)
Make a RAG ingestion pipeline idempotent by keying every stage on a SHA-256 content hash, isolating failures in DLQs, and reprocessing deterministically.
/4 min
Hybrid Search: When Pure Vector Embeddings Aren't Enough
Add sparse/keyword search to dense embeddings only when your eval shows lexical misses on IDs, rare terms, acronyms, code, or names.
/2 min/reference
Hybrid search for RAG: combining BM25 and dense vectors with RRF
Why you can't average keyword and vector scores — and how Reciprocal Rank Fusion combines them for an 8–15% accuracy gain.
/2 min/reference
How to reduce RAG hallucinations: a practical checklist
Most RAG hallucinations are retrieval bugs in disguise. A concrete checklist to cut them — grounding, retrieval quality, and faithfulness checks.
/2 min
How to debug a RAG pipeline that returns wrong answers
A step-by-step debug order for bad RAG answers — start with the assembled prompt, not the model. Most bugs are retrieval, not generation.
/4 min/reference
How to Choose an Embedding Model and Dimension for Your Vector Database
Pick an embedding model and dimension by trading MTEB quality against RAM, latency, and re-embedding cost — with a decision tree.
/3 min/reference
How to choose chunk size and overlap for RAG
Start at 512 tokens with light overlap, then tune by query type. A practical, benchmark-backed guide to chunk size for retrieval.
/3 min/reference
Corrective RAG (CRAG) Explained: Self-Healing Retrieval Without Fine-Tuning
Corrective RAG inserts a retrieval evaluator between vector search and the LLM that scores documents and routes to proceed, filter, or re-retrieve.
/4 min
From Cloud Qdrant RAG to On-Device RAG: What Actually Transfers and What Doesn't
Moving a production cloud RAG pipeline on-device: the shape transfers, but index scale, embedder size, and re-ranking budgets do not.
/4 min/reference
Cleaning Extracted Text Before Embedding: Headers, Footers, Hyphenation, and Noise
Strip repeating headers/footers, de-hyphenate line breaks, and normalize unicode before chunking so RAG embeddings stay clean.
/4 min/reference
Chunk Size and Overlap for RAG: A Reference with Sensible Defaults
Use structure-defined chunks first; when you must set a size, 256-512 tokens with 10-20% overlap is a sane default, then tune.
/4 min/reference
Building a Golden Dataset for RAG Evaluation From Your Production Traces
Mine failing production traces, store input plus retrieved chunks plus expected behavior, and version 50-100 focused cases in-repo.
/4 min
Building Agentic Search on Qdrant: A Production Architecture Walkthrough
How to build a production agentic search system on Qdrant: single-shot vector+filter tool calls, Postgres hydration, and progressive relaxation.
/3 min
On-Device OCR for RAG: Apple Vision vs Tesseract for macOS Document Pipelines
On macOS, Apple Vision beats Tesseract for RAG ingestion — faster, more accurate on real scans, free, offline. Tesseract wins on Linux CI.
/1 min/reference
RAG chunking strategies: a practical reference
The common chunking approaches for retrieval, when each one helps, and the tradeoffs — a quick reference you can come back to.