new_test.py

import PyPDF2  # For PDF text extraction
import streamlit as st  # For building the Streamlit app
from docx import Document  # For Word document text extraction
from langchain.chains import RunnableLambda, RunnablePassthrough
from langchain.chat_models import ChatGoogleGenerativeAI
from langchain.memory import ConversationBufferMemory
from langchain.prompts import (ChatPromptTemplate, HumanMessagePromptTemplate, MessagesPlaceholder, SystemMessage)
from langchain.schema import StrOutputParser  # For parsing the output


# Function to extract text from PDF
def extract_text_from_pdf(uploaded_file):
    text = ""
    reader = PyPDF2.PdfReader(uploaded_file)
    for page in reader.pages:
        text += page.extract_text()
    return text

# Function to extract text from Word document
def extract_text_from_word(uploaded_file):
    text = ""
    doc = Document(uploaded_file)
    for paragraph in doc.paragraphs:
        text += paragraph.text + "\n"
    return text



# Initialize Google Generative AI chat model
def initialize_chat_model():
    with open("key.txt", "r") as f:
        GOOGLE_API_KEY = f.read().strip()

    chat_model = ChatGoogleGenerativeAI(
        google_api_key=GOOGLE_API_KEY,
        model="gemini-1.5-pro-latest",
        temperature=0.4,
        max_tokens=2000,
        timeout=120,
        max_retries=5,
        top_p=0.9,
        top_k=40,
        presence_penalty=0.6,
        frequency_penalty=0.3
    )
    return chat_model

chat_model = initialize_chat_model()

# Create Chat Template
chat_prompt_template = ChatPromptTemplate.from_messages(
    [
        SystemMessage(
            content="""  You are a language model designed to follow user instructions exactly as given.
            Do not take any actions or provide any information unless specifically directed by the user.
            Your role is to fulfill the user's requests precisely without deviating from the instructions provided."""
        ),
        MessagesPlaceholder(variable_name="chat_history"),
        HumanMessagePromptTemplate.from_template("{human_input}")
    ]
)

# Initialize the Memory
memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)

# Create an Output Parser
output_parser = StrOutputParser()

# Define a chain
chain = RunnablePassthrough.assign(
            chat_history=RunnableLambda(lambda human_input: memory.load_memory_variables(human_input)['chat_history'])
        ) | chat_prompt_template | chat_model | output_parser

# Streamlit App
st.title("Interview Preparation with AI")
st.markdown("## Part-1: Upload Files, Summarize, and Extract Keywords")

# File upload section
file1 = st.file_uploader("Upload your resume (PDF or DOCX):", type=["pdf", "docx"])
file2 = st.file_uploader("Upload the job description (PDF or DOCX):", type=["pdf", "docx"])

if file1 and file2:
    try:
        # Detect file type and extract text for file 1
        if file1.name.endswith('.pdf'):
            text1 = extract_text_from_pdf(file1)
        elif file1.name.endswith('.docx'):
            text1 = extract_text_from_word(file1)
        else:
            st.error("Unsupported file type for file 1")

        # Detect file type and extract text for file 2
        if file2.name.endswith('.pdf'):
            text2 = extract_text_from_pdf(file2)
        elif file2.name.endswith('.docx'):
            text2 = extract_text_from_word(file2)
        else:
            st.error("Unsupported file type for file 2")


        # Ensure session state variables are initialized

        if "ats_score_calculated" not in st.session_state:
            st.session_state.ats_score_calculated = False


        # Button to Calculate ATS Score
        if st.button("ATS Score") or st.session_state.ats_score_calculated:
            
            st.session_state.ats_score_calculated = True
            resume_keywords = set(keywords1)
            job_description_keywords = set(keywords2)
            st.markdown("### ATS Score Calculation")
            query = {"human_input": f"""
You are an advanced Applicant Tracking System (ATS) designed to evaluate resumes against job descriptions with exceptional accuracy. Analyze the following keywords extracted from a job description and a resume, compare them, and calculate the match percentage.
Job Description Keywords:
{list(job_description_keywords)}
Resume Keywords:
{list(resume_keywords)}
Provide the ATS score as a percentage match between the resume and the job description in the following format:
The ATS Score of your Resume According to the Job Description is \"XX%\".
"""}

            response = chain.invoke(query)
            memory.save_context(query, {"output": response})

            st.write(response)

            
    except Exception as e:
        st.error(f"An error occurred: {e}")

else:
    st.info("Please upload both files to proceed.")