support output data point reported name

core/data_extraction.py

@@ -706,6 +706,8 @@ class DataExtraction:
         share_level_config = output_requirement.get("share_level", {})
 
         example_list = []
+        dp_reported_name_config = output_requirement.get("dp_reported_name", {})
+        dp_reported_name = {}
         for datapoint in datapoints:
             investment_level = self.datapoint_level_config.get(datapoint, "")
             if investment_level == "fund_level":
@@ -720,6 +722,7 @@ class DataExtraction:
                 share_datapoint_value_example[datapoint] = share_level_config.get(
                     f"{datapoint}_value", []
                 )
+            dp_reported_name[datapoint] = dp_reported_name_config.get(datapoint, "")
 
         share_datapoint_list = list(share_datapoint_value_example.keys())
         instructions.append(f"Example:\n")
@@ -739,7 +742,7 @@ class DataExtraction:
                     if index < len(share_datapoint_values):
                         example_dict[share_datapoint] = share_datapoint_values[index]
                 example_list.append(example_dict)
-        example_data = {"data": example_list}
+        example_data = {"data": example_list, "dp_reported_name": dp_reported_name}
         instructions.append(json.dumps(example_data, ensure_ascii=False, indent=4))
         instructions.append("\n")
         instructions.append("\n")

instructions/data_extraction_prompts_config.json

@@ -183,12 +183,13 @@
 			"Don't ignore the data point which with negative value, e.g. -0.12, -1.13",
 			"Don't ignore the data point which with explicit zero value, e.g. 0, 0.00",
 			"Don't extract data which values are -, *, **, N/A, N/A%, N/A %, NONE, it means the value should be NULL, please skip them.",
+			"Please also output the data point reported name in context.",
 			"Example:",
 			"-----Example Start-----",
 			"Sub-Funds\nClass of shares\nCurrency\nTER\nPerformance\nfees\nSwiss Life Funds (LUX) Bond Emerging Markets Corporates\nAM - Shares CHF hedged - Capitalisation\nCHF\n0.23%\n-\nAM - Shares EUR hedged - Capitalisation\nEUR\n0.23%\n0.00%\n",
 			"-----Example End-----",
 			"Output:",
-			"{\"data\": [{\"fund name\": \"Swiss Life Funds (LUX) Bond Emerging Markets Corporates\", \"share name\": \"AM - Shares CHF hedged - Capitalisation\", \"ter\": 0.23}, {\"fund name\": \"Swiss Life Funds (LUX) Bond Emerging Markets Corporates\", \"share name\": \"AM - Shares EUR hedged - Capitalisation\", \"ter\": 0.23, \"performance_fee\": 0}]}",
+			"{\"data\": [{\"fund name\": \"Swiss Life Funds (LUX) Bond Emerging Markets Corporates\", \"share name\": \"AM - Shares CHF hedged - Capitalisation\", \"ter\": 0.23}, {\"fund name\": \"Swiss Life Funds (LUX) Bond Emerging Markets Corporates\", \"share name\": \"AM - Shares EUR hedged - Capitalisation\", \"ter\": 0.23, \"performance_fee\": 0}], \"dp_reported_name\": {\"ter\": \"TER\", \"performance_fee\": \"Performance\nfees\"}}",
 			"Fund level data: (\"fund name\" and \"TOR\") and share level data: (\"fund name\", \"share name\", \"ter\", \"performance fees\", \"ogc\") should be output separately.",
 			"The output should be JSON format, the format is like below example(s):"
 		],
@@ -221,6 +222,12 @@
 				-0.15,
 				0.11
 			]
+		},
+		"dp_reported_name" : {
+			"tor": "TOR",
+			"ogc": "OGC",
+			"ter": "TER",
+			"performance_fee": "Performance fees"
 		}
 	},
 	"end": [

main.py

@@ -99,18 +99,22 @@ class EMEA_AR_Parsing:
                     data_from_gpt = json.load(f)
                 return data_from_gpt
 
-        data_extraction = DataExtraction(
+        try:
-            self.doc_id,
+            data_extraction = DataExtraction(
-            self.pdf_file,
+                self.doc_id,
-            self.output_extract_data_folder,
+                self.pdf_file,
-            self.page_text_dict,
+                self.output_extract_data_folder,
-            self.datapoint_page_info,
+                self.page_text_dict,
-            self.datapoints,
+                self.datapoint_page_info,
-            self.document_mapping_info_df,
+                self.datapoints,
-            extract_way=self.extract_way,
+                self.document_mapping_info_df,
-            output_image_folder=self.output_extract_image_folder,
+                extract_way=self.extract_way,
-        )
+                output_image_folder=self.output_extract_image_folder,
-        data_from_gpt = data_extraction.extract_data()
+            )
+            data_from_gpt = data_extraction.extract_data()
+        except Exception as e:
+            logger.error(f"Error: {e}")
+            data_from_gpt = {"data": []}
         return data_from_gpt
 
     def mapping_data(self, data_from_gpt: list, re_run: bool = False) -> list:
@@ -888,7 +892,7 @@ if __name__ == "__main__":
         "532179676",
         "534300608",
         "539233950",
-        "533727908",
+        # "533727908",
         "532438414",
         "533681744",
         "537654645",
@@ -901,27 +905,12 @@ if __name__ == "__main__":
         "536343790"
         ]
     special_doc_id_list = check_db_mapping_doc_id_list
-    # special_doc_id_list = ["425595958",
+    special_doc_id_list = ["534547266"]
-    #                         "451063582",
-    #                         "451878128",
-    #                         "466580448",
-    #                         "481482392",
-    #                         "492029971",
-    #                         "508704368",
-    #                         "510300817",
-    #                         "512745032",
-    #                         "514213638",
-    #                         "527525440",
-    #                         "532422548",
-    #                         "532998065",
-    #                         "534535767",
-    #                         "536344026",
-    #                         "540307575"]
     output_mapping_child_folder = r"/data/emea_ar/output/mapping_data/docs/"
     output_mapping_total_folder = r"/data/emea_ar/output/mapping_data/total/"
     re_run_extract_data = True
     re_run_mapping_data = True
-    force_save_total_data = True
+    force_save_total_data = False
     calculate_metrics = False
 
     extract_ways = ["text"]