Feat: PDF vision figure parser supports reading context (#12416)

### What problem does this PR solve?

PDF vision figure parser supports reading context.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

rag/app/paper.py

@@ -166,6 +166,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
             pdf_parser = Pdf()
             paper = pdf_parser(filename if not binary else binary,
                                from_page=from_page, to_page=to_page, callback=callback)
+            sections = paper.get("sections", [])
         else:
             kwargs.pop("parse_method", None)
             kwargs.pop("mineru_llm_name", None)
@@ -192,7 +193,12 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
             }
 
         tbls = paper["tables"]
-        tbls = vision_figure_parser_pdf_wrapper(tbls=tbls, callback=callback, **kwargs)
+        tbls = vision_figure_parser_pdf_wrapper(
+            tbls=tbls,
+            sections=sections,
+            callback=callback,
+            **kwargs,
+        )
         paper["tables"] = tbls
     else:
         raise NotImplementedError("file type not supported yet(pdf supported)")