Update codes

src/codes/code_funcs.py

@@ -351,9 +351,11 @@ def code_implicit_rag(service, implicit_run_dict, filename, constants):
             )
         )
 
+        prompt, _parser = prompt_templates.CODE_IMPLICIT(service, level_dict["match_list"])
+        
         # Run Prompt
-        claude_answer_raw = llm_utils.invoke_claude(
-            prompt_templates.CODE_IMPLICIT(service, level_dict["match_list"]),
+        llm_answer_raw = llm_utils.invoke_claude(
+            prompt,
             "sonnet_latest",
             filename,
             cache=True,
@@ -361,18 +363,18 @@ def code_implicit_rag(service, implicit_run_dict, filename, constants):
         )
 
         try:
-            claude_answer_final = string_utils.universal_json_load(claude_answer_raw)
+            llm_answer_final = _parser(llm_answer_raw)
         except Exception as e:
             return {"CODE_METHODOLOGY": e}
 
-        if not claude_answer_final:
+        if not llm_answer_final:
             continue
 
         # Populate answers, if any
         code_answer_dict = {}
         proc_codes, rev_codes = [], []
         proc_descs, rev_descs = [], []
-        for description in claude_answer_final:
+        for description in llm_answer_final:
             if description == "INVALID_SERVICE":
                 code_answer_dict["CODE_METHODOLOGY"] = "Generic - Prompt"
                 continue

src/constants/delimiters.py

@@ -2,6 +2,5 @@ from enum import Enum
 
 
 class Delimiter(Enum):
-    PIPE = "|"
     BACKTICK = "`"
     TRIPLE_BACKTICK = "```"

src/crosswalk/crosswalk_builder.py

@@ -147,7 +147,7 @@ class CrosswalkBuilder:
         df = pd.DataFrame(self.mapping.items(), columns=[from_col, to_col])
         df.to_csv(output_path, index=False, quoting=csv.QUOTE_ALL, encoding="utf-8-sig")
 
-    def create_reverse_mapping(self) -> dict[str, str]:
+    def create_reverse_mapping(self) -> dict[str, list[str]]:
         """Create a reverse mapping where values that map to the same key are concatenated
 
         Example:
@@ -166,7 +166,7 @@ class CrosswalkBuilder:
                 reverse_dict[target] = [str(source)]
 
         # Then join the lists with commas
-        return {target: "|".join(sources) for target, sources in reverse_dict.items()}
+        return {target: sources for target, sources in reverse_dict.items()}
 
     def map_value(self, key_value):
         return self.mapping.get(key_value)

src/pipelines/shared/extraction/one_to_one_funcs.py

@@ -6,15 +6,12 @@ import json
 import pandas as pd
 import src.pipelines.shared.postprocessing.postprocessing_funcs as postprocessing_funcs
 import src.pipelines.saas.prompts.prompt_calls as prompt_calls
-import src.prompts.prompt_templates as prompt_templates
-import src.utils.llm_utils as llm_utils
 import src.utils.string_utils as string_utils
 from src.constants.constants import Constants
-from src.constants.delimiters import Delimiter
 from src import config
 from src.pipelines.shared.postprocessing import postprocessing_funcs
 from src.pipelines.shared.extraction.vision_funcs import get_image_array_based_answer
-from src.prompts.fieldset import Field, FieldSet
+from src.prompts.fieldset import FieldSet
 
 
 def pass_smart_chunked_to_full_context(answers_dict, one_to_one_fields):

src/pipelines/shared/extraction/tin_npi_funcs.py

@@ -2,16 +2,12 @@ import json
 
 import logging
 import re
-from typing import Optional
-
 import src.constants.regex_patterns as regex_patterns
 import src.config as config
 import src.prompts.prompt_templates as prompt_templates
 from src.utils import llm_utils, string_utils
 from src.pipelines.saas.prompts import prompt_calls
-from src.constants.delimiters import Delimiter
 from src.prompts.fieldset import Field, FieldSet
-from difflib import SequenceMatcher
 
 
 def get_all_matches(text: str, pattern: str) -> list[str]:

src/pipelines/shared/postprocessing/aarete_derived.py

@@ -1,12 +1,7 @@
-import logging
-import os
-from collections import defaultdict
 
-import pandas as pd
 import src.config as config
 import src.utils.string_utils as string_utils
 from src.constants.constants import Constants
-from src.constants.delimiters import Delimiter
 from src.crosswalk.crosswalk_builder import CrosswalkBuilder
 from src.prompts.fieldset import FieldSet
 from src.utils.crosswalk_utils import apply_crosswalk

src/pipelines/shared/postprocessing/postprocessing_funcs.py

@@ -4,11 +4,7 @@ import logging
 import os
 import re
 from datetime import datetime
-import json
 import pandas as pd
-import src.prompts.prompt_templates as prompt_templates
-import src.utils.llm_utils as llm_utils
-from src.constants.delimiters import Delimiter
 from src.utils import string_utils
 
 # Determine the base directory for the project