Create app.py

app.py

@@ -0,0 +1,180 @@
+import os
+import re
+import io
+from datetime import datetime
+import PyPDF2
+import torch
+from transformers import AutoTokenizer, AutoModelForSequenceClassification, AutoModelForSeq2SeqLM
+from groq import Groq
+import gradio as gr
+from docxtpl import DocxTemplate
+
+# Set your API key for Groq
+os.environ["GROQ_API_KEY"] = "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"
+client = Groq(api_key=os.environ.get("GROQ_API_KEY"))
+
+# --- PDF/Text Extraction Functions --- #
+def extract_text_from_file(file_path):
+    """Extracts text from PDF or TXT files based on file extension."""
+    if file_path.endswith('.pdf'):
+        return extract_text_from_pdf(file_path)
+    elif file_path.endswith('.txt'):
+        return extract_text_from_txt(file_path)
+    else:
+        raise ValueError("Unsupported file type. Only PDF and TXT files are accepted.")
+
+def extract_text_from_pdf(pdf_file_path):
+    """Extracts text from a PDF file."""
+    with open(pdf_file_path, 'rb') as pdf_file:
+        pdf_reader = PyPDF2.PdfReader(pdf_file)
+        text = ''.join(page.extract_text() for page in pdf_reader.pages if page.extract_text())
+    return text
+
+def extract_text_from_txt(txt_file_path):
+    """Extracts text from a .txt file."""
+    with open(txt_file_path, 'r', encoding='utf-8') as txt_file:
+        return txt_file.read()
+
+# --- Skill Extraction with Llama Model --- #
+def extract_skills_llama(text):
+    """Extracts skills from the text using the Llama model via Groq API."""
+    try:
+        response = client.chat.completions.create(
+            messages=[{"role": "user", "content": f"Extract skills from the following text: {text}"}],
+            model="llama3-70b-8192",
+        )
+        skills = response.choices[0].message.content.split(', ')  # Expecting a comma-separated list
+        return skills
+    except Exception as e:
+        raise RuntimeError(f"Error during skill extraction: {e}")
+
+# --- Job Description Processing --- #
+def process_job_description(job_description_text):
+    """Processes the job description text and extracts relevant skills."""
+    job_description_text = preprocess_text(job_description_text)
+    return extract_skills_llama(job_description_text)
+
+# --- Text Preprocessing --- #
+def preprocess_text(text):
+    """Preprocesses text for analysis (lowercase, punctuation removal)."""
+    text = text.lower()
+    text = re.sub(r'[^\w\s]', '', text)  # Remove punctuation
+    return re.sub(r'\s+', ' ', text).strip()  # Remove extra whitespace
+
+# --- Resume Similarity Calculation --- #
+def calculate_resume_similarity(resume_text, job_description_text):
+    """Calculates similarity score between resume and job description using a sentence transformer model."""
+    model_name = "cross-encoder/stsb-roberta-base"
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    model = AutoModelForSequenceClassification.from_pretrained(model_name)
+
+    inputs = tokenizer(resume_text, job_description_text, return_tensors="pt", padding=True, truncation=True)
+    with torch.no_grad():
+        outputs = model(**inputs)
+        similarity_score = torch.sigmoid(outputs.logits).item()
+    return similarity_score
+
+# --- Communication Generation --- #
+def communication_generator(resume_skills, job_description_skills, similarity_score, max_length=150):
+    """Generates a communication response based on the extracted skills from the resume and job description."""
+    model_name = "google/flan-t5-base"
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+
+    # Assess candidate fit based on similarity score
+    fit_status = "fit for the job" if similarity_score >= 0.7 else "not a fit for the job"
+
+    # Create a more detailed communication message
+    message = (
+        f"After a thorough review of the candidate's resume, we found a significant alignment "
+        f"between their skills and the job description requirements. The candidate possesses the following "
+        f"key skills: {', '.join(resume_skills)}. These align well with the job requirements, particularly in areas such as "
+        f"{', '.join(job_description_skills)}. The candidate’s diverse expertise suggests they would make a valuable addition to our team. "
+        f"We believe the candidate is {fit_status}. If further evaluation is needed, please let us know how we can assist."
+    )
+
+    inputs = tokenizer(message, return_tensors="pt", padding=True, truncation=True)
+    response = model.generate(**inputs, max_length=max_length, num_beams=4, early_stopping=True)
+
+    return tokenizer.decode(response[0], skip_special_tokens=True)
+
+# --- Sentiment Analysis --- #
+def sentiment_analysis(text):
+    """Analyzes the sentiment of the text."""
+    model_name = "mrm8488/distiluse-base-multilingual-cased-v2-finetuned-stsb_multi_mt-es"
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    model = AutoModelForSequenceClassification.from_pretrained(model_name)
+
+    inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True)
+    with torch.no_grad():
+        outputs = model(**inputs)
+        predicted_sentiment = torch.argmax(outputs.logits).item()
+    return ["Negative", "Neutral", "Positive"][predicted_sentiment]
+
+# --- Resume Analysis Function --- #
+def analyze_resume(resume_file, job_description_file):
+    """Analyzes the resume and job description, returning similarity score, skills, and communication response."""
+    # Extract resume text based on file type
+    try:
+        resume_text = extract_text_from_file(resume_file.name)
+        job_description_text = extract_text_from_file(job_description_file.name)
+    except ValueError as ve:
+        return str(ve)
+
+    # Analyze texts
+    job_description_skills = process_job_description(job_description_text)
+    resume_skills = extract_skills_llama(resume_text)
+    similarity_score = calculate_resume_similarity(resume_text, job_description_text)
+    communication_response = communication_generator(resume_skills, job_description_skills, similarity_score)
+    sentiment = sentiment_analysis(resume_text)
+
+    return (
+        f"Similarity Score: {similarity_score:.2f}",
+        communication_response,
+        f"Sentiment: {sentiment}",
+        ", ".join(resume_skills),
+        ", ".join(job_description_skills),
+    )
+
+# --- Offer Letter Generation --- #
+def generate_offer_letter(template_file, candidate_name, role, start_date, hours):
+    """Generates an offer letter from a template."""
+    try:
+        start_date = datetime.strptime(start_date, "%Y-%m-%d").strftime("%B %d, %Y")
+    except ValueError:
+        return "Invalid date format. Please use YYYY-MM-DD."
+
+    context = {
+        'candidate_name': candidate_name,
+        'role': role,
+        'start_date': start_date,
+        'hours': hours
+    }
+
+    doc = DocxTemplate(template_file)
+    doc.render(context)
+
+    offer_letter_path = f"{candidate_name.replace(' ', '_')}_offer_letter.docx"
+    doc.save(offer_letter_path)
+
+    return offer_letter_path
+
+# --- Gradio Interface --- #
+iface = gr.Interface(
+    fn=analyze_resume,
+    inputs=[
+        gr.File(label="Upload Resume (PDF/TXT)"),
+        gr.File(label="Upload Job Description (PDF/TXT)")
+    ],
+    outputs=[
+        gr.Textbox(label="Similarity Score"),
+        gr.Textbox(label="Communication Response"),
+        gr.Textbox(label="Sentiment Analysis"),
+        gr.Textbox(label="Extracted Resume Skills"),
+        gr.Textbox(label="Extracted Job Description Skills"),
+    ],
+    title="Resume and Job Description Analyzer",
+    description="This tool analyzes a resume against a job description to extract skills, calculate similarity, and generate communication responses."
+)
+
+iface.launch()