Merged in refactor/prompt_refactor (pull request #353)

READY: Refactor/prompt refactor

* Prompt refactor

* refactor imports

* Prompt refactor

* Import refactor

* Remove excess prompts from investment_prompts.py


Approved-by: Alex Galarce

fieldExtraction/src/utils/string_utils.py

@@ -5,8 +5,9 @@ import warnings
 import numpy as np
 import pandas as pd
 
+from src.prompts import preprocessing_prompts
 import src.utils.llm_utils as llm_utils
-from src import config, prompts
+from src import config
 from src.enums.delimiters import Delimiter
 from src.regex.regex_patterns import (BACKTICK_PATTERN, PIPE_PATTERN,
                                       TRIPLE_BACKTICK_PATTERN)
@@ -177,7 +178,7 @@ def secondary_string_to_dict(dict_string: str, filename: str) -> dict:
             result_dict = json.loads(dict_substring)
         except:
             try:
-                prompt = prompts.FIX_JSON(dict_substring)
+                prompt = preprocessing_prompts.FIX_JSON(dict_substring)
                 dict_substring = llm_utils.invoke_claude(
                     prompt, config.MODEL_ID_CLAUDE3_HAIKU, filename
                 )

fieldExtraction/src/utils/table_utils.py

@@ -1,12 +1,13 @@
+from src.prompts import preprocessing_prompts
 import src.utils.llm_utils as llm_utils
 import src.utils.string_utils as string_utils
-from src import config, prompts
+from src import config
 
 
 def align_and_format_tables(text_dict, filename):
     for page_num, page_text in text_dict.items():
         if "Table Start" in page_text and string_utils.contains_reimbursement(page_text):
-            prompt = prompts.ALIGN_AND_FORMAT_TABLES(page_text)
+            prompt = preprocessing_prompts.ALIGN_AND_FORMAT_TABLES(page_text)
             aligned_page = llm_utils.invoke_claude(
                 prompt, config.MODEL_ID_CLAUDE35_SONNET, filename, 8192
             )