Skip to course content
Free generative AI app course

Generative AI Application Development with Python

Module 08 Knowledge Check

5 questions. Pass mark 4 out of 5. Answer every question before checking the answer key below, then retry after reading the feedback.

1. Decoding an uploaded file with errors="ignore"…

2. Chunks should be split on…

3. An extracted record with a negative invoice amount…

4. Summarisation most often loses…

5. Citation quality should be measured by…

---

Answer Key and Explanations

Check these only after attempting every question.

1. B - converts a clear failure into silently mangled text

It succeeds on every input, which is what makes it dangerous.

2. B - sentence boundaries

A chunk retrieved alone has to make sense alone, which is stronger than merely fitting.

3. B - parses fine and needs a schema bound to catch

It becomes a row that will be reconciled against something real, and surfaces weeks later.

4. B - the qualifiers that bound it

The shorter summary reads better precisely because qualifiers are what make prose feel cluttered.

5. B - whether the cited chunk contains the claim

Presence is trivially satisfied by attaching an id to everything.

Practical Check

Apply this module to your own work: complete the module activity for *File Input, Summarisation and Extraction Workflows*, then write one sentence naming what your result shows and one naming what it does not.

Strong Answer Pattern

A strong answer names the task, the evidence used, the check performed, and the remaining limitation. It avoids "proved", "guaranteed", or "always" unless the evidence genuinely supports it.