Spaces:
Sleeping
Sleeping
| 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="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. | |
| :param user_prompt: Prompt provided by the user. | |
| :param data: Dictionary containing the instance information (e.g., UID, Name, etc.). | |
| :return: Generated response text. | |
| """ | |
| # 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 (40 to 50 words), brochure-suitable, and tailored as per the user prompt.\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"- Instance info: {data}\n" | |
| f"- Go through the Instance info If the {user_prompt} mentions you to use variables that are not mentioned above. " | |
| f"- The response **MUST**:\n" | |
| f"- Start with 'Hello {data['Name']}'.\n" | |
| f"- Be concise, professional, and STRICTLY DO NOT generate invalid characters or encoding errors (e.g. 'SoraVR’s').\n" | |
| f"- Use standard English punctuation, such as single quotes (e.g., 'can't', 'it's').\n" | |
| f"- STRICTLY Give only one response for the Category the sample belongs to.\n" | |
| f"- Do NOT include preambles or unnecessary text.\n\n" | |
| f"Return the final response cleanly, without any extraneous symbols or characters." | |
| ) | |
| # Query the LLM and return the response | |
| response = self.llm.invoke(prompt) | |
| return response.content.strip() | |