Inspect boundaries
Track source paragraph word spans through every chunk.
Practical AI · EDITION 1.0.0
Debug Chunking and Context Selection
Inspect word provenance, candidate ranking, context budgets and annotated evidence coverage in a deterministic local lab.
By Sanjaay Gowda T S · For python developers debugging document retrieval and context construction.
You need: Python lists, dictionaries and functions; Basic document retrieval concepts
Runtime and hardware details
Python 3.10 or later and a terminal. The supplied project runs locally and uses the Python standard library.
No model, API key, cloud account or network calls are used by the companion.
Python lists, dictionaries and functions; Basic document retrieval concepts.
Full setup and scope ↓$2.99USD · one-time purchase
Prepared with AI assistance. Independent human technical, editorial and assistive-technology reader review remains pending. Automated checks and agent review are not certification.
PDF + EPUB + companion project. Any applicable tax is shown at checkout. Single-reader ebook terms; companion code is MIT licensed.
TRY THE FREE SAMPLE
See how the guide teaches.
Read 7 sample pages to explore the introduction, first chapter and teaching approach before you choose the complete edition.
Read free sample PDF · No checkout required
WHAT YOU WILL LEARN
Understand each part.
Inspect every boundary.
Separate ranking and selection
Explain why a retrieved candidate may never reach context.
Preserve needed evidence
Evaluate rules, exceptions and controlled configuration changes.
INSIDE THE BOOK
9 focused chapters.
- Define the missing-context problem
- Make source boundaries inspectable
- Build chunks with word provenance
- Rank candidates before packing context
- Budget context without silent truncation
- Evaluate rules and exceptions together
- Compare chunk configurations
- Diagnose retrieval and selection separately
- Handoff an evidence-preserving design
Your download includes
- 21-page tagged PDF with linked contents
- Reflowable EPUB for ebook readers
- Local Python project, fictional input, recorded expected JSON output and 12 companion tests
- 3 explanatory diagrams
- 9 chapters with exercises and worked answers
Before you begin
Python 3.10 or later and a terminal. The supplied project runs locally and uses the Python standard library.
No model, API key, cloud account or network calls are used by the companion.
Learning prerequisites: Python lists, dictionaries and functions; Basic document retrieval concepts.
Prepared with AI assistance. Independent human technical, editorial and assistive-technology reader review is pending.
The included examples are synthetic teaching material. Model access, software subscriptions, hosting, ongoing updates and consulting are not included.
CLEAR EXPECTATIONS
Before you buy.
What will I build?
Inspect word provenance, candidate ranking, context budgets and annotated evidence coverage in a deterministic local lab. The local companion uses fictional teaching fixtures. Project limits: Uses whitespace-word chunks, ASCII lexical matching and a word-count context budget. It is not multilingual search, a tokenizer/model integration or a permission-aware ingestion system.
What was tested?
The 12 companion tests passed on the packaged project. The supplied fictional fixture produced its recorded expected JSON output. EPUBCheck reported no errors or warnings; DAISY Ace and PDF/UA automated checks passed. These local teaching checks are not production accuracy claims or certification. Independent human technical, editorial and assistive-technology reader review remains pending.
How do I get the files?
Complete the secure Lemon Squeezy checkout to access the PDF, EPUB and companion ZIP. Keep your receipt and download access private. This is a one-time purchase of edition 1.0.0; ongoing updates and consulting are not included.
Can I share the book or the companion code?
The full ebook is licensed to one reader. The labelled free sample may be shared unchanged. The companion project is MIT licensed and may be adapted or shared with its licence notice. See the exact ebook terms.
Find exactly where a rule or exception disappears.
One book. A complete learning project. Evidence you can inspect.
AI-assisted · Independent human review pending
$2.99USDBuy ebook