Update app.py

app.py

@@ -9,16 +9,15 @@ sys.path.append(os.path.abspath('common'))
 
 from crewai import Crew, Task, Process
 from RespondentAgent import *
-from langchain_openai import ChatOpenAI
-from langchain_groq import ChatGroq
-
+from LLMConfig import *
+    
 # Configure logging
 logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
 
 # Global tracker for the last active agent
 last_active_agent = None  # Initially, no agent is selected
 
-def parse_question_with_llm(question, respondent_names, openai_llm):
+def parse_question_with_llm(question, respondent_names, processor_llm):
     """
     Uses OpenAI's LLM to extract the specific agents being addressed and their respective questions.
     Supports compound requests.
@@ -50,7 +49,7 @@ def parse_question_with_llm(question, respondent_names, openai_llm):
     """
 
     # Invoke LangChain LLM
-    response = openai_llm.invoke(prompt)
+    response = processor_llm.invoke(prompt)
     chatgpt_output = response.content.strip()
     logging.info(f"LLM Parsed Output: {chatgpt_output}")
 
@@ -70,7 +69,7 @@ def parse_question_with_llm(question, respondent_names, openai_llm):
 
     return parsed_questions
 
-def ask_interview_question(respondent_agents_dict, question, openai_llm):
+def ask_interview_question(respondent_agents_dict, question, processor_llm):
     """
     Handles both individual and group interview questions while tracking conversation flow.
     Uses OpenAI's LLM to extract the intended respondent(s) and their specific question(s).
@@ -85,7 +84,7 @@ def ask_interview_question(respondent_agents_dict, question, openai_llm):
     print(f"Available respondents: {agent_names}")
 
     # Use OpenAI LLM to parse question into individual respondent-specific sub-questions
-    parsed_questions = parse_question_with_llm(question, str(agent_names), openai_llm)
+    parsed_questions = parse_question_with_llm(question, str(agent_names), processor_llm)
 
     if not parsed_questions:
         logging.warning("No parsed questions returned. Exiting function.")
@@ -211,23 +210,8 @@ if __name__ == "__main__":
     Config.load_environment(".", "genz.dev1")
     Config.print_environment()
 
-    # Initialize OpenAI LLM for parsing
-    openai_llm = ChatOpenAI(
-        temperature=0,
-        api_key=Config.openai_api_key,
-        model=Config.model,
-        max_tokens=3000,
-        top_p=0.1,
-        frequency_penalty=0,
-        presence_penalty=-0.5
-    )
-
-    # Set up Groq LLM for response generation
-    fact_based_llm = ChatGroq(
-        groq_api_key=Config.groq_api_key,
-        model_name=Config.agent_model,
-        temperature=0.1,  # Low temperature for deterministic output
-    )
+    processor_llm = get_processor_llm_instance()
+    respondent_agent_llm = get_respondent_agent_llm_instance()
 
     # Load all user profiles from the Excel file
     data_dictionary                = DataDictionary.generate_dictionary(Config.data_dictionary_file)
@@ -237,7 +221,7 @@ if __name__ == "__main__":
     # Create respondent agents for all profiles
     respondent_agents_dict = {
         profile.get_field("Demographics", "Name"): RespondentAgent.create(
-            profile, f"{Config.config_dir}/fastfacts/{profile.ID}_fast_facts.xlsx", fact_based_llm
+            profile, f"{Config.config_dir}/fastfacts/{profile.ID}_fast_facts.xlsx", respondent_agent_llm
         )
         for profile in respondent_agent_user_profiles[:5]
     }
@@ -249,7 +233,7 @@ if __name__ == "__main__":
         if history is None:
             history = []  # Ensure history is initialized
 
-        responses = ask_interview_question(respondent_agents_dict, message, openai_llm)
+        responses = ask_interview_question(respondent_agents_dict, message, processor_llm)
         logging.info(f"Interview response is {responses}")
 
         # Ensure responses is always a list