Update app.py

app.py

@@ -18,6 +18,7 @@ def find_similar(vector_representation, all_representations, threshold=0.5):
 
     # Find indices where similarity is above the threshold
     similar_indices = np.where(similarities > threshold)[0]
+    sorted_indices = sorted(similar_indices, key=lambda i: similarities[i], reverse=True)
 
     return similar_indices.tolist()
 
@@ -31,9 +32,9 @@ def process_pdf(doc, diff_line):
             for line in block["lines"]:
                 temp = []
                 data_page.append(page_num)
-                data_geom.append(line["bbox"])
+                data_geom.append(line["geometry"])
                 for word in line["words"]:
-                    temp.append(word["text"])
+                    temp.append(word["value"])
                 data_word.append(" ".join(temp))
 
     data = {
@@ -47,8 +48,8 @@ def process_pdf(doc, diff_line):
     y1_coor = []
     y2_coor = []
     for pos in df["posisi"]:
-        y1_coor.append(pos[1])
-        y2_coor.append(pos[3])
+        y1_coor.append(pos[0][1])
+        y2_coor.append(pos[1][1])
 
     df["y1_coor"] = y1_coor
     df["y2_coor"] = y2_coor
@@ -61,7 +62,7 @@ def process_pdf(doc, diff_line):
     merge_y2 = []
     merge_halaman = []
 
-    for i in range(df.shape[0]):
+    for i in range(0, df.shape[0]):
         if i == 0:
             temp_y2 = df["y2_coor"].iloc[i]
             temp_y1 = df["y1_coor"].iloc[i]