Added Local code for Invitation Generator

LLM_handler.py

@@ -0,0 +1,51 @@
+import os
+from langchain_community.chat_models import ChatOpenAI
+from langchain_groq import ChatGroq
+from dotenv import load_dotenv
+
+load_dotenv()
+
+class LLMHandler:
+    def __init__(self, model_name="gpt-4", provider="openai"):
+        self.provider = provider
+
+        if provider == "openai":
+            self.api_key = os.getenv("OPENAI_API_KEY")
+            if not self.api_key:
+                raise ValueError("OPENAI_API_KEY environment variable not set.")
+            self.model = ChatOpenAI(api_key=self.api_key, model=model_name)
+
+        elif provider == "groq":
+            self.api_key = os.getenv("GROQ_API_KEY")
+            if not self.api_key:
+                raise ValueError("GROQ_API_KEY environment variable not set.")
+            self.model = ChatGroq(api_key=self.api_key, model_name=model_name)
+
+        else:
+            raise ValueError("Unsupported provider. Use 'openai' or 'groq'.")
+
+    def generate_text(self, input_data, user_instruction):
+        """
+        Generates personalized text using the LLM.
+        """
+        try:
+            prompt = self._build_prompt(input_data, user_instruction)
+            response = self.model.generate([prompt])
+            return response[0]["text"]  # Adjust this depending on response format
+        except Exception as e:
+            print(f"Error during text generation: {e}")
+            return "Error generating response"
+
+    @staticmethod
+    def _build_prompt(input_data, user_instruction):
+        """
+        Builds a structured prompt for the LLM.
+        """
+        context = (
+            f"Name: {input_data.get('Name')}\n"
+            f"Job Title: {input_data.get('Job Title')}\n"
+            f"Organization: {input_data.get('Organization', input_data.get('Organisation'))}\n"
+            f"Area of Interest: {input_data.get('Area of Interest')}\n"
+            f"Category: {input_data.get('Category')}\n"
+        )
+        return f"{user_instruction}\n\nContext:\n{context}"

llm_merger.py

@@ -0,0 +1,86 @@
+import os
+from dotenv import load_dotenv
+from langchain_groq import ChatGroq
+from openai import OpenAI
+
+load_dotenv()
+
+
+class PrimaryLLMHandler:
+    def __init__(self, model_name="gpt-4o-mini"):
+        """
+        Initializes the Primary LLM Handler (GPT0-mini).
+        """
+        self.openai_api_key = os.getenv("OPENAI_API_KEY")
+        if not self.openai_api_key:
+            raise ValueError("OPENAI_API_KEY environment variable not set.")
+
+        self.client = OpenAI(api_key=self.openai_api_key)
+        self.model_name = model_name
+
+    def generate_response(self, user_prompt, data):
+        """
+        Generates a response using the primary LLM.
+        """
+        prompt = (
+            f"You are a professional AI model tasked with writing personalized invite texts "
+            f"that are concise (less than 40 words), brochure-suitable, and tailored as per the category in the given sample."
+            f"\n\n"
+            f"User prompt: {user_prompt}\n\n"
+            f"Details of the individual:\n"
+            f"- Name: {data['Name']}\n"
+            f"- Job Title: {data['Job Title']}\n"
+            f"- Organisation: {data['Organisation']}\n"
+            f"- Area of Interest: {data['Area of Interest']}\n"
+            f"- Category: {data['Category']}\n\n"
+            f"The response should start with 'Hello {data['Name']}'."
+            f"Ensure the tone aligns with the instructions. STRICTLY give only one response."
+        )
+
+        completion = self.client.chat.completions.create(
+            model=self.model_name,
+            messages=[
+                {"role": "system", "content": "You are a professional assistant AI."},
+                {"role": "user", "content": prompt},
+            ],
+        )
+
+        return completion.choices[0].message.content.strip()
+
+
+class ValidatorLLMHandler:
+    def __init__(self, model_name="gemma2-9b-it"):
+        """
+        Initializes the Validator LLM Handler (Llama 3.3 8B).
+        """
+        self.groq_api_key = os.getenv("GROQ_API_KEY")
+        if not self.groq_api_key:
+            raise ValueError("GROQ_API_KEY environment variable not set.")
+
+        self.llm = ChatGroq(groq_api_key=self.groq_api_key, model_name=model_name)
+
+    def validate_and_correct_response(self, user_prompt, original_response, data):
+        """
+        Validates and corrects the response using the secondary LLM.
+        """
+        validation_prompt = (
+            f"You are a professional AI model tasked with validating and correcting AI-generated texts. "
+            f"The original response must align strictly with the provided user prompt and input details. "
+            f"If the response fails to meet the requirements, generate a corrected version."
+            f"\n\n"
+            f"User prompt: {user_prompt}\n\n"
+            f"Details of the individual:\n"
+            f"- Name: {data['Name']}\n"
+            f"- Job Title: {data['Job Title']}\n"
+            f"- Organisation: {data['Organisation']}\n"
+            f"- Area of Interest: {data['Area of Interest']}\n"
+            f"- Category: {data['Category']}\n\n"
+            f"Original response: {original_response}\n\n"
+            f"Instructions:\n"
+            f"- If the original response aligns with the user prompt and input details, reply with 'Valid Response'.\n"
+            f"- Otherwise, provide a corrected version starting with 'Hello {data['Name']}'.\n"
+            f"- Keep it concise (less than 40 words) and brochure-suitable.\n"
+        )
+
+        response = self.llm.invoke(validation_prompt)
+        return response.content.strip()

main.py

@@ -0,0 +1,56 @@
+import csv
+import os
+#from query_handler import LLMHandler
+from openai_llms import LLMHandler
+
+def main():
+    """
+    Main function to process input CSV, query LLM, and save responses.
+    """
+    # Ask user for input CSV file path and user prompt
+    #input_csv = input("Enter the path to the input CSV file: ").strip()
+    input_csv = "D:\Projects\Liminal\InviteAI\Test_sample.csv"
+    if not os.path.exists(input_csv):
+        print(f"Error: File '{input_csv}' not found.")
+        return
+    user_prompt = input("Enter your user prompt: ").strip()
+
+    # Output CSV file path
+    output_csv = "D:\Projects\Liminal\InviteAI\Response_sample.csv"
+
+    # Check if the input file exists
+    if not os.path.exists(input_csv):
+        print(f"Error: File '{input_csv}' not found.")
+        return
+
+    # Initialize the LLM handler
+    llm_handler = LLMHandler()
+    #llm_handler = LLMOpenAI()
+
+    # Read the input CSV and process each instance
+    with open(input_csv, mode="r", newline="", encoding="utf-8") as infile:
+        reader = csv.DictReader(infile)
+        fieldnames = reader.fieldnames + ["Generated Text"]
+
+        rows = []
+        for row in reader:
+            # Generate response for the current row
+            try:
+                response = llm_handler.generate_response(user_prompt, row)
+                row["Generated Text"] = response
+                rows.append(row)
+            except Exception as e:
+                print(f"Error generating response for UID {row.get('UID')}: {e}")
+                row["Generated Text"] = "Error generating response"
+                rows.append(row)
+
+    # Save the updated rows to the output CSV
+    with open(output_csv, mode="w", newline="", encoding="utf-8") as outfile:
+        writer = csv.DictWriter(outfile, fieldnames=fieldnames)
+        writer.writeheader()
+        writer.writerows(rows)
+
+    print(f"Responses saved to '{output_csv}'.")
+
+if __name__ == "__main__":
+    main()

openai_llms.py

@@ -1,8 +1,8 @@
 from openai import OpenAI
-#from dotenv import load_dotenv
+from dotenv import load_dotenv
 import os
 
-#load_dotenv()
+load_dotenv()
 
 
 class LLMHandler:

query_handler.py

@@ -0,0 +1,80 @@
+import os
+from langchain_groq import ChatGroq
+from dotenv import load_dotenv
+
+load_dotenv()
+
+class LLMHandler:
+    def __init__(self, model_name="llama-3.3-70b-versatile"):
+        """
+        Initializes the LLMHandler with the specified Groq model.
+        """
+        self.groq_api_key = os.getenv("GROQ_API_KEY")
+        if not self.groq_api_key:
+            raise ValueError("GROQ_API_KEY environment variable not set.")
+
+        # Initialize Groq LLM client
+        self.llm = ChatGroq(groq_api_key=self.groq_api_key, model_name=model_name)
+
+    def generate_response(self, user_prompt, data):
+        """
+        Generate a concise response using the LLM based on user prompt and data.
+        """
+        # Create the full prompt using user input and instance data
+        prompt = (
+            f"You are a professional AI model tasked with writing personalized invite texts "
+            f"that are concise (less than 40 words), brochure-suitable, and tailored as per the category in the given sample."
+            f"\n\n"
+            f"Consider the user prompt: {user_prompt}\n\n"
+            f"Details of the individual:\n"
+            f"- Name: {data['Name']}\n"
+            f"- Job Title: {data['Job Title']}\n"
+            f"- Organisation: {data['Organisation']}\n"
+            f"- Area of Interest: {data['Area of Interest']}\n"
+            f"- Category: {data['Category']}\n\n"
+            f"The response can start with 'Hello {data['Name']}'."
+            f"Write a personalized invitation text for this individual, ensuring the tone and purpose align with the user's instructions."
+            f"STRICTLY give only one response for the category the sample belongs to."
+            f"Do NOT mention the category in the response."
+            f"NO PREAMBLE."
+        )
+
+        # Query the LLM and return the response
+        response = self.llm.invoke(prompt)
+        return response.content.strip()
+
+    def validate_and_correct_response(self, user_prompt, original_response, data):
+        """
+        Use a secondary LLM to validate and correct the response.
+        """
+        # Initialize the second LLM (validator)
+        validator = ChatGroq(
+            groq_api_key=self.groq_api_key,
+            model_name="gemma2-9b-it"
+        )
+
+        # Validation prompt
+        validation_prompt = (
+            f"You are a professional AI model tasked with validating and correcting AI-generated texts. "
+            f"The original response must align strictly with the provided user prompt and input details. "
+            f"If the response fails to meet the requirements, generate a corrected response. "
+            f"\n\n"
+            f"User prompt: {user_prompt}\n\n"
+            f"Details of the individual:\n"
+            f"- Name: {data['Name']}\n"
+            f"- Job Title: {data['Job Title']}\n"
+            f"- Organisation: {data['Organisation']}\n"
+            f"- Area of Interest: {data['Area of Interest']}\n"
+            f"- Category: {data['Category']}\n\n"
+            f"Original response: {original_response}\n\n"
+            f"Instructions:\n"
+            f"- If the original response is correct, reply with 'Valid Response'.\n"
+            f"- Otherwise, provide a corrected version."
+            f"- The corrected version should start with 'Hello {data['Name']}'."
+            f"- The corrected version is concise (less than 40 words), brochure-suitable, and tailored as per the Category"
+            f"- NO PREAMBLE "
+        )
+
+        # Query the validator LLM
+        validation_response = validator.invoke(validation_prompt)
+        return validation_response.content.strip()