mh_classification.py

import os
import time
from langchain_openai import ChatOpenAI
from langchain.prompts import PromptTemplate
from langchain.agents import initialize_agent, AgentType
from langchain.tools import Tool
from dotenv import load_dotenv
from langchain_core.messages import HumanMessage
from prompts.mh_clarification import clarification_prompt

# Load environment variables
load_dotenv()

# Set environment variables for model API key and model type
os.environ.setdefault("DSP_CACHEBOOL", "false")

# Get API key
api_key = os.getenv("OPENAI_API_KEY")
if not api_key:
    raise ValueError("OPENAI_API_KEY environment variable is not set")

# Initialize the chat model
model = ChatOpenAI(
    model=os.getenv("MODEL", "gpt-3.5-turbo"),
    openai_api_key=api_key,
    temperature=0.0,
    max_tokens=4000
)

# Define a tool to process job descriptions
class JobDescriptionProcessor(Tool):
    def __init__(self, name: str, description: str, func):
        super().__init__(name=name, func=func, description=description)

    def _run(self, input: str):
        try:
            # Extract key aspects from the job description
            aspects = self.func(input)
            return aspects
        except Exception as e:
            return f"Error processing job description: {str(e)}"

# Define a function to extract key aspects from job description
def extract_key_aspects(jd: str) -> str:
    try:
        # Create a prompt for extracting key aspects
        prompt = f"""Extract the key aspects from this job description. Focus on:
1. Position title
2. Required qualifications
3. Experience requirements
4. Key skills
5. Must-have requirements

Job Description:
{jd}

Format the output as a clear list of key aspects."""
        
        # Get response from the model
        response = model.invoke([HumanMessage(content=prompt)])
        return response.content
    except Exception as e:
        return f"Error extracting key aspects: {str(e)}"

# Define a tool to process checkpoints and resume
class ClarificationProcessor(Tool):
    def __init__(self, name: str, description: str, func):
        super().__init__(name=name, func=func, description=description)

    def _run(self, input: str):
        # Extract checkpoints and resume from the input string
        try:
            # Split by "Resume:" and ensure we have both parts
            parts = input.split("Resume:")
            if len(parts) != 2:
                return "Error: Input must contain both checkpoints and resume sections"
            
            # Extract checkpoints and resume, removing any extra whitespace
            checkpoints = parts[0].replace("Checkpoints:", "").strip()
            resume = parts[1].strip()
            
            if not checkpoints or not resume:
                return "Error: Both checkpoints and resume sections must not be empty"
                
            return self.func(checkpoints, resume)
        except Exception as e:
            return f"Error processing input: {str(e)}"

# Define a function to generate clarifications based on checkpoints and resume
def generate_clarifications(checkpoints: str, resume: str) -> str:
    try:
        # Create the prompt
        prompt_text = clarification_prompt.format(checkpoints=checkpoints, resume=resume)
        
        # Get response from the model
        response = model.invoke([HumanMessage(content=prompt_text)])
        return response.content
    except Exception as e:
        return f"Error generating clarifications: {str(e)}"

# Define the agent tools
tools = [
    JobDescriptionProcessor(
        name="JobDescriptionProcessor",
        description="Extract key aspects from a job description.",
        func=extract_key_aspects,
    ),
    ClarificationProcessor(
        name="ClarificationProcessor",
        description="Generate clarifications based on the provided checkpoints and resume.",
        func=generate_clarifications,
    ),
]

# Initialize the LangChain agent
agent = initialize_agent(
    tools, model, agent_type=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True
)