Create helper.py

helper.py

@@ -0,0 +1,93 @@
+from docling.document_converter import DocumentConverter
+from paddleocr import PaddleOCR
+from pdf2image import convert_from_path
+import numpy as np
+
+def process_text(res):
+    page_texts = {}
+    texts = res.get('texts')
+    for item in texts:
+        for prov in item['prov']:
+            page_no = prov['page_no']
+            text = item['text']
+            page_key = f'{page_no}'
+            if page_key not in page_texts:
+                page_texts[page_key] = text
+            else:
+                page_texts[page_key] += ' ' + text
+    return page_texts
+
+def get_table_text(grids):
+    table_text = "Here is a Table : \n"
+    for row in grids:
+        for col in row:
+            val = col.get('text')
+            table_text+=f'{val} ,'
+        table_text+='\n'
+    return table_text
+def process_tables(res , page_texts : dict = {}):
+    try:
+        tables = res.get('tables', [])
+        if not isinstance(tables, list):
+            raise ValueError("Expected 'tables' to be a list.")
+
+        for table in tables:
+            try:
+                # Ensure 'prov' exists and has the necessary structure
+                prov = table.get('prov', [])
+                if not prov or not isinstance(prov, list):
+                    raise ValueError("Missing or invalid 'prov' structure in table.")
+                page_no = str(prov[0].get('page_no'))
+                if not page_no:
+                    raise ValueError("Missing or invalid 'page_no' in 'prov'.")
+                # Ensure 'data' and 'grid' exist
+                data = table.get('data', {})
+                grids = data.get('grid', [])
+                if not isinstance(grids, list):
+                    raise ValueError("Missing or invalid 'grid' structure in 'data'.")
+                # Process grid data into text
+                text = get_table_text(grids)  # Ensure `get_table_text` is well-defined
+                if not isinstance(text, str):
+                    raise ValueError("get_table_text did not return a string.")
+                # Add text to page_texts
+                if page_no not in page_texts:
+                    page_texts[page_no] = text
+                else:
+                    page_texts[page_no] += '\n' + text
+                print(f"Processed page {page_no}")
+            except Exception as table_error:
+                print(f"Error processing table: {table_error}")
+        return page_texts
+    except Exception as e:
+        print(f"Error processing tables: {e}")
+        return page_texts
+
+def process_docs(doc_path):
+    """
+    Process the uploaded PDF document using LlamaParse and PaddleOCR.
+
+    Args:
+        doc_path (str): Path to the uploaded PDF document.
+
+    Returns:
+        query_engine_llama, query_engine_paddle, images: Query engines for LlamaParse and PaddleOCR, and a list of extracted images.
+    """
+
+    ## Paddle OCR
+    ocr = PaddleOCR(use_angle_cls=True, lang='en', use_gpu=True)
+    images_pdf = convert_from_path(doc_path, 300)
+    documents2 = []
+    for image in images_pdf:
+        result = ocr.ocr(np.array(image), cls=True)
+        text = "\n".join([line[1][0] for line in result[0]])
+        documents2.append(text)
+    docs2 = documents2
+    
+    ## Docling
+    converter = DocumentConverter()
+    result = converter.convert(doc_path)
+    res = result.document.export_to_dict()
+    docs3 = process_text(res)
+    docs3 = process_tables(res,docs3)
+
+    return docs2,docs3