rag_utils_updated_v2.py

import os
import logging
import requests
import json
import PyPDF2
import docx
from bs4 import BeautifulSoup
from chromadb import PersistentClient
from langchain_groq import ChatGroq
from langchain.prompts import ChatPromptTemplate
from langchain.output_parsers import PydanticOutputParser
from pydantic import BaseModel, Field, ValidationError
from typing import List
from sentence_transformers import SentenceTransformer  # Import SentenceTransformer
from dotenv import load_dotenv

# Setup logging
logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
logger = logging.getLogger(__name__)

# --- Text Extraction ---
def extract_text(uploaded_file):
    try:
        if isinstance(uploaded_file, str):
            return extract_text_from_webpage(uploaded_file)
        elif hasattr(uploaded_file, 'type') and uploaded_file.type == "application/pdf":
            if is_image_pdf(uploaded_file):
                logger.warning(f"Image-based PDF detected: {uploaded_file.name}")
                return ""  # Skip processing
            return extract_text_from_pdf(uploaded_file)
        elif hasattr(uploaded_file, 'type') and uploaded_file.type == "application/vnd.openxmlformats-officedocument.wordprocessingml.document":
            return extract_text_from_docx(uploaded_file)
        return ""
    except Exception as e:
        logger.error(f"Error extracting text: {e}")
        return ""

def is_image_pdf(uploaded_file):
    """Check if a PDF is image-based (contains no selectable text)."""
    try:
        reader = PyPDF2.PdfReader(uploaded_file)
        for page in reader.pages:
            if page.extract_text():
                return False  # Text is present, so not an image PDF
        return True  # No text detected, likely an image-based PDF
    except Exception as e:
        logger.error(f"Error checking if PDF is image-based: {e}")
        return True  # Assume image PDF if error occurs

def extract_text_from_pdf(uploaded_file):
    try:
        reader = PyPDF2.PdfReader(uploaded_file)
        return "\n".join([page.extract_text() or "" for page in reader.pages])
    except Exception as e:
        logger.error(f"Error reading PDF {uploaded_file.name}: {e}")
        return ""

def extract_text_from_docx(uploaded_file):
    try:
        doc = docx.Document(uploaded_file)
        return "\n".join([para.text for para in doc.paragraphs])
    except Exception as e:
        logger.error(f"Error reading DOCX: {e}")
        return ""

def extract_text_from_webpage(url):
    try:
        response = requests.get(url)
        response.raise_for_status()
        soup = BeautifulSoup(response.content, 'html.parser')
        return soup.get_text(separator='\n')
    except requests.exceptions.RequestException as e:
        logger.error(f"Error fetching webpage: {e}")
        return ""

def preprocess_text(text):
    return text.lower()

def get_embeddings(text, model):
    return model.encode(text)

def get_similar_cvs(cvs, job_description_embedding, collection):
    results = collection.query(
        query_embeddings=[job_description_embedding],
        n_results=len(cvs),
        include=["distances", "metadatas"]
    )

    similar_cvs = []
    for i in range(len(results['metadatas'][0])): # Corrected loop
        metadata = results['metadatas'][0][i]
        if metadata: #Check if metadata exists
            filename = metadata.get('filename') # Use .get to handle missing keys
            if filename: # Check if filename exists in metadata
                similarity_score = 1 - results['distances'][0][i]
                similar_cvs.append({
                    "filename": filename,
                    "initial_score": similarity_score
                })
            else:
                logger.warning(f"Metadata for CV at index {i} is missing 'filename'.")
        else:
            logger.warning(f"No metadata found for CV at index {i}.")


    similar_cvs.sort(key=lambda x: x['initial_score'], reverse=True)
    return similar_cvs

# ... (CV Assessment & Ranking functions)

class RequirementAssessment(BaseModel):
    requirement: str
    match: str = Field(pattern="^(Yes|No|Partial|Not Applicable)$")
    evidence: str
    justification: str

class CandidateAssessment(BaseModel):
    filename: str
    requirements: List[RequirementAssessment]
    overall_assessment: str = Field(pattern="^(Excellent|Good|Fair|Poor)$")
    recommendation: str = Field(pattern="^(Interview|Reject|Maybe)$")
    justification: str


import time
import requests
import json
from pydantic import ValidationError


def assess_cv(cv_text, requirements, filename, groq_client, max_retries=3, retry_delay=2):
    """Assess CV against specific job requirements with Tree-of-Thoughts."""

    requirements_str = "\n".join([f"- {req}" for req in requirements])
    prompt_template = ChatPromptTemplate.from_template(

        template = os.environ.get("LLM_PROMPT")

    )
    
    prompt = prompt_template.format_messages(requirements=requirements_str, cv_text=cv_text)

    # ... (rest of the assess_cv function remains the same)
    for attempt in range(max_retries):
        try:
            response = groq_client.invoke(prompt, timeout=30)
            response_content = response.content

            return {"filename": filename, "raw_response": response_content}

        except requests.exceptions.RequestException as e:
            logger.error(f"Network error during Groq API call: {e}")
            if attempt == max_retries - 1:
                return {"filename": filename, "error": "Network error during LLM call"}
            else:
                logger.warning(f"Network error, retrying in {retry_delay} seconds (attempt {attempt+1}/{max_retries}).")
                time.sleep(retry_delay)
                retry_delay *= 2

        except Exception as e:
            logger.error(f"Groq API error (attempt {attempt + 1}/{max_retries}): {e}")
            if attempt == max_retries - 1:
                return {"filename": filename, "error": "General LLM failure"}
            else:
                logger.warning(f"General LLM error, retrying in {retry_delay} seconds (attempt {attempt+1}/{max_retries}).")
                time.sleep(retry_delay)
                retry_delay *= 2

    return {"filename": filename, "error": "LLM call failed after multiple retries."}

def extract_job_requirements(job_description, groq_client):
        """Extracts job requirements from the job description using the LLM."""
        prompt_template = ChatPromptTemplate.from_template(
            template="Extract the key job requirements from the following job description:\n\n{job_description}\n\nRequirements:"
        )
        prompt = prompt_template.format_messages(job_description=job_description)

        try:
            response = groq_client.invoke(prompt, timeout=30)
            requirements_text = response.content.strip()
            requirements = [req.strip() for req in requirements_text.split('\n') if req.strip()]
            return requirements
        except Exception as e:
            logger.error(f"Error extracting job requirements: {e}")
            return []