llama_groq.py

from langchain_groq import ChatGroq
from dotenv import load_dotenv
from typing import Optional
import os



class LlamaModel:
    """
    This class is used to interact with the Llama LLM models for text generation.

    Args:
        model: The name of the model to be used. Defaults to 'gemini-pro'.
        max_output_tokens: The maximum number of tokens to generate. Defaults to 1024.
        top_p: The probability of generating the next token. Defaults to 1.0.
        temperature: The temperature of the model. Defaults to 0.0.
        top_k: The number of top tokens to consider. Defaults to 5.
    """

    def __init__(self,
                 model: Optional[str] = 'llama3-70b-8192',
                 ):
        
        
        load_dotenv()
        
        self.model = llm = ChatGroq(groq_api_key = os.getenv('groq_llama70_key'),model = model)
        

    def execute(self, prompt: str) -> str:
        
        try:
            response = self.model.invoke(prompt)
            res=response.content
            meta=response.response_metadata
            return {'text':res,'meta':meta}
        except Exception as e:
            return f"An error occurred: {e}"