Feat: add VLM-boosted DocX parser (#6307)

### What problem does this PR solve?

Add VLM-boosted DocX parser

### Type of change

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

deepdoc/parser/figure_parser.py

@@ -15,10 +15,19 @@
 #
 
 
+from PIL import Image
+
 from rag.app.picture import vision_llm_chunk as picture_vision_llm_chunk
 from rag.prompts import vision_llm_figure_describe_prompt
 
 
+def vision_figure_parser_figure_data_wraper(figures_data_without_positions):
+    return [(
+        (figure_data[1], [figure_data[0]]),
+        [(0, 0, 0, 0, 0)]
+    ) for figure_data in figures_data_without_positions if isinstance(figure_data[1], Image.Image)]
+
+
 class VisionFigureParser:
     def __init__(self, vision_model, figures_data, *args, **kwargs):
         self.vision_model = vision_model
@@ -33,14 +42,14 @@ class VisionFigureParser:
 
         for item in figures_data:
             # position
-            if len(item) == 2 and isinstance(item[1], list) and len(item[1]) == 1 and len(item[1][0]) == 5:
+            if len(item) == 2 and isinstance(item[1], list) and len(item[1]) == 1 and isinstance(item[1][0], tuple) and len(item[1][0]) == 5:
                 img_desc = item[0]
-                assert len(img_desc) == 2, "Should be (figure, [description])"
+                assert len(img_desc) == 2 and isinstance(img_desc[0], Image.Image) and isinstance(img_desc[1], list), "Should be (figure, [description])"
                 self.figures.append(img_desc[0])
                 self.descriptions.append(img_desc[1])
                 self.positions.append(item[1])
             else:
-                assert len(item) == 2 and isinstance(item, tuple), f"get {len(item)=}, {item=}"
+                assert len(item) == 2 and isinstance(item, tuple) and isinstance(item[1], list), f"get {len(item)=}, {item=}"
                 self.figures.append(item[0])
                 self.descriptions.append(item[1])
 

rag/app/naive.py

@@ -29,7 +29,7 @@ from tika import parser
 from api.db import LLMType
 from api.db.services.llm_service import LLMBundle
 from deepdoc.parser import DocxParser, ExcelParser, HtmlParser, JsonParser, MarkdownParser, PdfParser, TxtParser
-from deepdoc.parser.figure_parser import VisionFigureParser
+from deepdoc.parser.figure_parser import VisionFigureParser, vision_figure_parser_figure_data_wraper
 from deepdoc.parser.pdf_parser import PlainParser, VisionParser
 from rag.nlp import concat_img, find_codec, naive_merge, naive_merge_docx, rag_tokenizer, tokenize_chunks, tokenize_chunks_docx, tokenize_table
 from rag.utils import num_tokens_from_string
@@ -226,10 +226,27 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
     pdf_parser = None
     if re.search(r"\.docx$", filename, re.IGNORECASE):
         callback(0.1, "Start to parse.")
+
+        try:
+            vision_model = LLMBundle(kwargs["tenant_id"], LLMType.IMAGE2TEXT)
+            callback(0.15, "Visual model detected. Attempting to enhance figure extraction...")
+        except Exception:
+            vision_model = None
+
         sections, tables = Docx()(filename, binary)
-        res = tokenize_table(tables, doc, is_english)  # just for table
 
+        if vision_model:
+            figures_data = vision_figure_parser_figure_data_wraper(sections)
+            try:
+                docx_vision_parser = VisionFigureParser(vision_model=vision_model, figures_data=figures_data, **kwargs)
+                boosted_figures = docx_vision_parser(callback=callback)
+                tables.extend(boosted_figures)
+            except Exception as e:
+                callback(0.6, f"Visual model error: {e}. Skipping figure parsing enhancement.")
+
+        res = tokenize_table(tables, doc, is_english)
         callback(0.8, "Finish parsing.")
+
         st = timer()
 
         chunks, images = naive_merge_docx(