added debugging script and changed the data html to pandas

app.py

@@ -13,10 +13,12 @@ def return_html_file(files):
     points = [loc.coords for loc in locations]
     route = coordinates_to_route(points)
     df = pd.DataFrame([loc.to_dict() for loc in locations])
+    llm_parsed = llm_parsed.rename(columns={'business_address': 'Address'})
+    df = df.join(llm_parsed.set_index('Address'), on='Address')
     df_html = df.to_html(index=False, escape=False)
     map_output_path = r"map_output.html"
     generate_route_map(route, map_output_path)
-    html_content = llm_parsed + df_html
+    html_content = df_html
     data_output_path = './data_output.html'
     with open(data_output_path, mode='w', encoding='utf-8') as html:
         html.write(html_content)
@@ -24,15 +26,20 @@ def return_html_file(files):
     return [data_output_path, map_output_path]
 
 
-iface = gr.Interface(
-    fn=return_html_file,
-    inputs=gr.Files(file_types=[".pdf"]),
-    outputs=[
-        gr.File(label="📊 Business Data HTML"),
-        gr.File(label="🗺️ Route Map HTML")
-    ],
-    title="Download HTML File",
-    description="Upload PDF files to trigger the download of a prepared HTML file."
-)
+def main():
+    iface = gr.Interface(
+        fn=return_html_file,
+        inputs=gr.Files(file_types=[".pdf"]),
+        outputs=[
+            gr.File(label="📊 Business Data HTML"),
+            gr.File(label="🗺️ Route Map HTML")
+        ],
+        title="Download HTML File",
+        description="Upload PDF files to trigger the download of a prepared HTML file."
+    )
 
-iface.launch()
+    iface.launch()
+
+
+if __name__ == '__main__':
+    main()

geolocation_apis.py

@@ -1,79 +1,14 @@
 from dotenv import load_dotenv
+from location import Location
 import urllib.parse
 import pandas as pd
 import requests
-import re
 import os
 
 HOME_COORDS = [35.09126, 32.85195]
 load_dotenv()
 
 
-class Location:
-    def __init__(self, address):
-        self.address = address
-        self.city = None
-        self.street = None
-        self.building = None
-        self.coords = None
-        self.coords_level = 'address'
-        self.parse_address()
-
-    def __str__(self):
-        if self.coords:
-            return f"""
-                    ---------------------------------------
-                    city: {self.city}
-                    street: {self.street}
-                    building: {self.building}
-                    coords: {self.coords}
-                    coords level: {self.coords_level}
-                    """
-        else:
-            return f"""
-                    ---------------------------------------
-                    city: {self.city}
-                    street: {self.street}
-                    building: {self.building}
-                    """
-
-    def to_dict(self):
-        return {
-            "Address": self.address,
-            "City": self.city,
-            "Street": self.street,
-            "Building": self.building,
-            "Coordinates": f"{self.coords[0]}, {self.coords[1]}" if self.coords else None,
-            "Precision": self.coords_level,
-        }
-
-    def set_coords_level(self, level):
-        self.coords_level = level
-
-    def set_coords(self, lat, lon):
-        self.coords = (lat, lon)
-
-    def parse_address(self):
-        """
-        Parses address of the form: "StreetName BuildingNumber, CityName"
-        Example: "גושן 1 ,קרית מוצקין"
-        """
-        if not self.address or ',' not in self.address:
-            return
-
-        try:
-            before_comma, after_comma = self.address.split(',', 1)
-            self.city = after_comma.strip()
-
-            # Regex: match "רחוב [שם] מספר [מספר]" or just "[שם] [מספר]"
-            match = re.match(r'(.+?)\s+(\d+)', before_comma.strip())
-            if match:
-                self.street = match.group(1).strip()
-                self.building = match.group(2).strip()
-        except Exception as e:
-            print(f"Failed to parse address: {self.address}. Error: {e}")
-
-
 def call_tomtom_api(location):
     base_url = os.getenv("TOMTOM_URL")
     api_key = os.getenv("TOMTOM_API_KEY")

llm_api.py

@@ -1,3 +1,6 @@
+from copy import copy
+
+import pandas as pd
 from langchain_google_genai import ChatGoogleGenerativeAI
 from langchain.output_parsers import PydanticOutputParser
 from langchain_core.prompts import PromptTemplate
@@ -24,48 +27,9 @@ class InsuredDetails(BaseModel):
         separator = "~" * 20
         return "\n".join([content, separator])
 
-    def to_html(self):
-        return f"""
-            <tr>
-                <td>{self.business_name}</td>
-                <td>{self.business_address}</td>
-                <td>{self.contact_name}</td>
-                <td>{self.contact_phone}</td>
-            </tr>"""
-
-
-def parse_to_html(results):
-    # HTML Header (table structure)
-    html_content = """
-    <html>
-    <head><title>Insured Business Details</title></head>
-    <body>
-    <h1>Insured Business Details</h1>
-    <table border="1">
-        <thead>
-            <tr>
-                <th>Business Name</th>
-                <th>Business Address</th>
-                <th>Contact Name</th>
-                <th>Contact Phone</th>
-            </tr>
-        </thead>
-        <tbody>
-    """
-
-    # Adding each InsuredDetails as a table row
-    for item in results:
-        html_content += item.to_html()
 
-    # Closing table and body tags
-    html_content += """
-        </tbody>
-    </table>
-    </body>
-    </html>
-    """
-
-    return html_content
+def parse_to_df(results):
+    return pd.DataFrame([ins.model_dump() for ins in results])
 
 
 load_dotenv()  # Only needed locally
@@ -132,11 +96,12 @@ def llm_parser(docs, model="gemini-2.0-flash-001"):
     for item in results:
         print(item)
 
-    html_results = parse_to_html(results)
+    df_results = parse_to_df(results)
+
+    return results, df_results
 
-    return results, html_results
 
-# x = llm_parser(["""
+# x = """
 # שומרה חברה לביטוח בע"מ
 #
 # לפנה"צ
@@ -426,8 +391,7 @@ def llm_parser(docs, model="gemini-2.0-flash-001"):
 #
 #
 # """
-#             ])
-# results = x[0]
-# results = addresses_to_coordinates([r.business_address for r in results])
-# results = coordinates_to_route(results)
-# print(results)
+# y = copy(x)
+#
+# results = llm_parser([x, y])
+

location.py

@@ -0,0 +1,66 @@
+import re
+
+
+class Location:
+    def __init__(self, address):
+        self.address = address
+        self.city = None
+        self.street = None
+        self.building = None
+        self.coords = None
+        self.coords_level = 'address'
+        self.parse_address()
+
+    def __str__(self):
+        if self.coords:
+            return f"""
+                    ---------------------------------------
+                    city: {self.city}
+                    street: {self.street}
+                    building: {self.building}
+                    coords: {self.coords}
+                    coords level: {self.coords_level}
+                    """
+        else:
+            return f"""
+                    ---------------------------------------
+                    city: {self.city}
+                    street: {self.street}
+                    building: {self.building}
+                    """
+
+    def to_dict(self):
+        return {
+            "Address": self.address,
+            "City": self.city,
+            "Street": self.street,
+            "Building": self.building,
+            "Coordinates": f"{self.coords[0]}, {self.coords[1]}" if self.coords else None,
+            "Precision": self.coords_level,
+        }
+
+    def set_coords_level(self, level):
+        self.coords_level = level
+
+    def set_coords(self, lat, lon):
+        self.coords = (lat, lon)
+
+    def parse_address(self):
+        """
+        Parses address of the form: "StreetName BuildingNumber, CityName"
+        Example: "גושן 1 ,קרית מוצקין"
+        """
+        if not self.address or ',' not in self.address:
+            return
+
+        try:
+            before_comma, after_comma = self.address.split(',', 1)
+            self.city = after_comma.strip()
+
+            # Regex: match "רחוב [שם] מספר [מספר]" or just "[שם] [מספר]"
+            match = re.match(r'(.+?)\s+(\d+)', before_comma.strip())
+            if match:
+                self.street = match.group(1).strip()
+                self.building = match.group(2).strip()
+        except Exception as e:
+            print(f"Failed to parse address: {self.address}. Error: {e}")