Differences

This shows you the differences between two versions of the page.

--- ai-pdf-genration-english [2026/10/12 15:41] – misa
+++ ai-pdf-genration-english [2026/10/12 15:50] (current) – [2. How it works under the hood] misa
@@ Line 9: / Line 9: @@
 ===== 2. How it works under the hood =====
-^  Component                        ^    Role                                                         ^
+^  Component                        ^    Role                                                            ^
-| ''openpyxl'' / ''pandas'' (Python) | Reads the .xlsx: values, sheet structure, cell colors/legend     |
+| ''openpyxl'' / ''pandas'' (Python) | Reads the .xlsx: values, sheet structure, cell colors/legend      |
-| ''matplotlib''                     | Builds the charts (donut, bar charts, timelines) as image files
+| ''matplotlib''                     | Builds the charts (donut, bar charts, timelines) as image files   |
-| HTML/CSS + ''WeasyPrint''          | Lays out real A4 pages and renders them into the final PDF (cover,                footers, page x of y)|
+| HTML/CSS + ''WeasyPrint''          | Lays out real A4 pages and renders them into the final PDF (cover,                 footers, page x of y)                                                                                    |
-| ''pdftoppm'' (poppler)             | Renders PDF pages back to images so the AI can visually inspect its own output before handover|
+| ''pdftoppm'' (poppler)             | Renders PDF pages back to images so the AI can visually inspect its own output before handover                                                                               |
 The standard pipeline: **read → understand → summarize → build charts → build HTML report → render PDF → verify pages → iterate on feedback.**