#259- Refactor: Externalize LLM system prompt to configuration file

src/llm.py

@@ -7,9 +7,13 @@ class LLM:
     def __init__(self, transcript_text=None, target_fields=None, json=None):
         if json is None:
             json = {}
-        self._transcript_text = transcript_text  # str
-        self._target_fields = target_fields  # List, contains the template field.
-        self._json = json  # dictionary
+        self._transcript_text = transcript_text
+        self._target_fields = target_fields
+        self._json = json
+
+        pp = os.path.join(os.path.dirname(__file__), "prompt.txt")
+        with open(pp, "r", encoding="utf-8") as f:
+            self.sp = f.read()
 
     def type_check_all(self):
         if type(self._transcript_text) is not str:
@@ -24,29 +28,17 @@ def type_check_all(self):
             )
 
     def build_prompt(self, current_field):
-        """
-        This method is in charge of the prompt engineering. It creates a specific prompt for each target field.
-        @params: current_field -> represents the current element of the json that is being prompted.
-        """
-        prompt = f""" 
-            SYSTEM PROMPT:
-            You are an AI assistant designed to help fillout json files with information extracted from transcribed voice recordings. 
-            You will receive the transcription, and the name of the JSON field whose value you have to identify in the context. Return 
-            only a single string containing the identified value for the JSON field. 
-            If the field name is plural, and you identify more than one possible value in the text, return both separated by a ";".
-            If you don't identify the value in the provided text, return "-1".
-            ---
+        prompt = f"""{self.sp}
             DATA:
             Target JSON field to find in text: {current_field}
 
             TEXT: {self._transcript_text}
             """
-
         return prompt
 
     def main_loop(self):
         # self.type_check_all()
-        for field in self._target_fields.keys():
+        for field in self._target_fields:
             prompt = self.build_prompt(field)
             # print(prompt)
             # ollama_url = "http://localhost:11434/api/generate"

src/main.py

@@ -3,6 +3,7 @@
 from commonforms import prepare_form 
 from pypdf import PdfReader
 from controller import Controller
+from typing import Union
 
 def input_fields(num_fields: int):
     fields = []
@@ -68,7 +69,7 @@ def run_pdf_fill_process(user_input: str, definitions: list, pdf_form_path: Unio
 if __name__ == "__main__":
     file = "./src/inputs/file.pdf"
     user_input = "Hi. The employee's name is John Doe. His job title is managing director. His department supervisor is Jane Doe. His phone number is 123456. His email is jdoe@ucsc.edu. The signature is <Mamañema>, and the date is 01/02/2005"
-    fields = ["Employee's name", "Employee's job title", "Employee's department supervisor", "Employee's phone number", "Employee's email", "Signature", "Date"]
+    descriptive_fields = ["Employee's name", "Employee's job title", "Employee's department supervisor", "Employee's phone number", "Employee's email", "Signature", "Date"]
     prepared_pdf = "temp_outfile.pdf"
     prepare_form(file, prepared_pdf)
 
@@ -80,4 +81,4 @@ def run_pdf_fill_process(user_input: str, definitions: list, pdf_form_path: Unio
         num_fields = 0
 
     controller = Controller()
-    controller.fill_form(user_input, fields, file)
+    controller.fill_form(user_input, descriptive_fields, file)

src/prompt.txt

@@ -0,0 +1,7 @@
+SYSTEM PROMPT:
+You are an AI assistant designed to help fillout json files with information extracted from transcribed voice recordings. 
+You will receive the transcription, and the name of the JSON field whose value you have to identify in the context. Return 
+only a single string containing the identified value for the JSON field. 
+If the field name is plural, and you identify more than one possible value in the text, return both separated by a ";".
+If you don't identify the value in the provided text, return "-1".
+---