import streamlit as st import PyPDF2 from docx import Document from transformers import pipeline, AutoTokenizer, AutoModelForSeq2SeqLM import spacy import pytextrank from langchain_google_genai import ChatGoogleGenerativeAI from langchain_core.messages import SystemMessage from langchain_core.prompts import ChatPromptTemplate, HumanMessagePromptTemplate, MessagesPlaceholder from langchain.memory import ConversationBufferMemory from langchain_core.output_parsers import StrOutputParser from langchain_core.runnables import RunnablePassthrough, RunnableLambda import spacy import subprocess import re # Function to check and download spaCy model def ensure_spacy_model(model_name="en_core_web_sm"): try: spacy.load(model_name) except OSError: subprocess.run(["python", "-m", "spacy", "download", model_name]) spacy.load(model_name) # 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 # Function to summarize text def summarize_text(text, max_length=1000, min_length=30): max_length = min(max_length, 1000) # Ensure max_length doesn't exceed 1000 try: # Initialize the summarizer pipeline summarizer = pipeline("summarization", model="facebook/bart-large-cnn") summary = summarizer(text, max_length=max_length, min_length=min_length, do_sample=False) if isinstance(summary, list) and len(summary) > 0: return summary[0]['summary_text'] else: raise ValueError("Unexpected summarizer output format") except Exception as e: return f"Error in summarization: {e}" # Function to extract keywords using spaCy and PyTextRank def extract_keywords(text, top_n=15): ensure_spacy_model("en_core_web_sm") nlp = spacy.load("en_core_web_sm") nlp.add_pipe("textrank", last=True) doc = nlp(text) keywords = [phrase.text for phrase in doc._.phrases[:top_n]] return keywords def parse_mcq_questions(mcq_list): # Split the string into individual questions questions = re.split(r'\d+\.\s+', mcq_list)[1:] # Skip the empty first element parsed_questions = [] for q in questions: # Split into question and options parts = q.strip().split(' - ') question = parts[0].strip() options = { opt[0]: opt[2:].strip() for opt in parts[1:] } parsed_questions.append({ 'question': question, 'options': options }) return parsed_questions # Function to generate MCQs using LLM def generate_mcqs(keywords): query = {"human_input": f""" You are an advanced AI model trained to generate high-quality multiple-choice questions (MCQs). Based on the provided list of skills: {keywords}, create **exactly 10 MCQs**. Each MCQ should focus on most important concepts related to the internal topics of each skill. For example, if the keyword is \"Python,\" the questions should be derived from core Python concepts, like data structures, syntax, or libraries. The MCQs should follow this structure: 1. A clear and concise important question based on a topic within the skill. 2. Four options (labeled as A, B, C, and D). 3. Only one correct answer per question, with the other options serving as plausible distractors. Do not provide any other information, explanations, or extra text. Output **only** the 10 MCQs in proper structure, like this: 1. Question text... - A) Option 1 - B) Option 2 - C) Option 3 - D) Option 4 2. Question text... - A) Option 1 - B) Option 2 - C) Option 3 - D) Option 4 Continue this format for all 10 questions. """} response = chain.invoke(query) memory.save_context(query, {"output": response}) return response # Function to evaluate MCQ answers def evaluate_mcqs(mcq_list, answers): query = {"human_input": f""" You are an advanced AI model trained to evaluate answers for high-quality multiple-choice questions (MCQs). Act as an expert professional in all relevant skills and concepts, analyzing the user's answers in detail. Follow these instructions: 1. Evaluate the provided answers {answers} against the correct answers for the MCQs. 2. Award 1 mark for each correct answer. Determine if each answer is correct or incorrect. 3. For incorrect answers: - Analyze deeply to identify the specific concepts or subtopics within the skill where the user is struggling. - Provide a focused list of concepts the user needs to improve on, derived from the incorrect answers. 4. At the end of the evaluation, output: - Total marks scored (out of 10). - A detailed and analyzed one by one list of concepts to focus on, ensuring they address the root areas of misunderstanding or lack of knowledge. Output **only** the following information: - Total marks scored: X/10 - Concepts to focus on: [Provide an analyzed and specific list of concepts derived from incorrect answers] """} response = chain.invoke(query) memory.save_context(query, {"output": response}) return response # 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") # Summarize texts #st.markdown("### Summarizing the uploaded documents...") #summary1 = summarize_text(text1) #summary2 = summarize_text(text2) #st.markdown("### Results for File 1 (Resume)") #st.subheader("Summary:") #st.write(summary1) #st.markdown("### Results for File 2 (Job Description)") #st.subheader("Summary:") #st.write(summary2) # Ensure session state variables are initialized if "keywords_extracted" not in st.session_state: st.session_state.keywords_extracted = False if "ats_score_calculated" not in st.session_state: st.session_state.ats_score_calculated = False # Button to Extract Keywords if st.button("Extract Keywords") or st.session_state.keywords_extracted: st.session_state.keywords_extracted = True # Extract keywords st.markdown("### Extracting keywords...") keywords1 = extract_keywords(text1) keywords2 = extract_keywords(text2) # Display Keywords st.markdown("### Results for File 1 (Resume)") st.subheader("Keywords:") st.write(", ".join(keywords1)) st.markdown("### Results for File 2 (Job Description)") st.subheader("Keywords:") st.write(", ".join(keywords2)) resume_keywords = set(keywords1) job_description_keywords = set(keywords2) # Button to Calculate ATS Score if st.button("ATS Score") or st.session_state.ats_score_calculated: st.session_state.ats_score_calculated = True 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) st.title("Multiple Choice Quiz") # Initialize session state variables if they don't exist if 'current_question' not in st.session_state: st.session_state.current_question = 0 if st.button("MCQ Test"): if 'answers' not in st.session_state: st.session_state.answers = [] if 'questions' not in st.session_state: # Your MCQ string goes here mcq_list = generate_mcqs(job_description_keywords) st.session_state.questions = parse_mcq_questions(mcq_list) # Display current question number and total questions st.write(f"Question {st.session_state.current_question + 1} of {len(st.session_state.questions)}") # Display current question current_q = st.session_state.questions[st.session_state.current_question] st.write(current_q['question']) # Create radio buttons for options with the corrected format_func answer = st.radio( "Select your answer:", options=['A', 'B', 'C', 'D'], # List of option keys format_func=lambda x: f"{x}) {current_q['options'].get(x, ' ')}", key=f"question_{st.session_state.current_question}" # Unique key per question ) # Navigation buttons in columns col1, col2 = st.columns(2) if st.session_state.current_question > 0: with col1: if st.button("Previous"): st.session_state.current_question -= 1 st.rerun() if st.session_state.current_question < len(st.session_state.questions) - 1: with col2: if st.button("Next"): st.session_state.answers.append(f"{st.session_state.current_question + 1}-{answer}") st.session_state.current_question += 1 st.rerun() else: with col2: if st.button("Submit"): st.session_state.answers.append(f"{st.session_state.current_question + 1}-{answer}") st.write("Quiz completed! Your answers:") st.write(st.session_state.answers) # Add a restart button if st.button("Restart Quiz"): st.session_state.current_question = 0 st.session_state.answers = [] st.rerun() except Exception as e: st.error(f"An error occurred: {e}") else: st.info("Please upload both files to proceed.")