Refa: improve image table context (#12244)

### What problem does this PR solve?

Improve image table context.

Current strategy in attach_media_context:

- Order by position when possible: if any chunk has page/position info,
sort by (page, top, left), otherwise keep original order.
- Apply only to media chunks: images use image_context_size, tables use
table_context_size.
- Primary matching: on the same page, choose a text chunk whose vertical
span overlaps the media, then pick the one with the closest vertical
midpoint.
- Fallback matching: if no overlap on that page, choose the nearest text
chunk on the same page (page-head uses the next text; page-tail uses the
previous text).
- Context extraction: inside the chosen text chunk, find a mid-sentence
boundary near the text midpoint, then take context_size tokens split
before/after (total budget).
- No multi-chunk stitching: context comes from a single text chunk to
avoid mixing unrelated segments.

### Type of change

- [x] Refactoring

---------

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>

web/src/interfaces/database/document.ts

@@ -44,6 +44,9 @@ export interface IParserConfig {
   raptor?: Raptor;
   graphrag?: GraphRag;
   image_context_window?: number;
+  image_table_context_window?: number;
+  image_context_size?: number;
+  table_context_size?: number;
   mineru_parse_method?: 'auto' | 'txt' | 'ocr';
   mineru_formula_enable?: boolean;
   mineru_table_enable?: boolean;

web/src/interfaces/request/document.ts

@@ -8,6 +8,9 @@ export interface IChangeParserConfigRequestBody {
   auto_questions?: number;
   html4excel?: boolean;
   toc_extraction?: boolean;
+  image_table_context_window?: number;
+  image_context_size?: number;
+  table_context_size?: number;
 }
 
 export interface IChangeParserRequestBody {