Update

processor.py

@@ -2,44 +2,14 @@ import layoutparser as lp
 import pytesseract
 from pdf2image import convert_from_path
 from PIL import Image
-import json
 
-model = lp.Detectron2LayoutModel(
-    config_path="lp://PubLayNet/faster_rcnn_R_50_FPN_3x/config",
-    extra_config=["MODEL.ROI_HEADS.SCORE_THRESH_TEST", 0.8],
-    label_map={0: "Text", 1: "Title", 2: "List", 3: "Table", 4: "Figure"},
-)
-
-def load_images(uploaded_file):
-    if uploaded_file.name.endswith(".pdf"):
-        return convert_from_path(uploaded_file)
-    else:
-        return [Image.open(uploaded_file)]
+def convert_pdf_to_images(pdf_path):
+    return convert_from_path(pdf_path)
 
 def analyze_layout(image):
-    layout = model.detect(image)
-    return layout
-
-def extract_text_from_blocks(image, layout):
-    blocks = []
-    for block in layout:
-        cropped = block.crop_image(image)
-        text = pytesseract.image_to_string(cropped)
-        blocks.append({
-            "type": block.type,
-            "text": text.strip(),
-            "coords": block.coordinates
-        })
-    return blocks
-
-def rule_based_kv_extraction(blocks):
-    data = {}
-    for b in blocks:
-        t = b["text"].lower()
-        if "invoice" in t and "number" in t:
-            data["Invoice Number"] = b["text"]
-        elif "total" in t:
-            data["Total Amount"] = b["text"]
-        elif "customer" in t:
-            data["Customer Name"] = b["text"]
-    return data
+    model = lp.EfficientDetLayoutModel(
+        "lp://efficientdet/PubLayNet",
+        extra_config=["MODEL.ROI_HEADS.SCORE_THRESH_TEST", 0.6],
+        label_map={0: "Text", 1: "Title", 2: "List", 3: "Table", 4: "Figure"}
+    )
+    return model.detect(image)