Create app.py

app.py

@@ -0,0 +1,215 @@
+import os
+import PyPDF2
+import re
+import torch
+from transformers import AutoTokenizer, AutoModelForSequenceClassification, AutoModelForSeq2SeqLM
+from groq import Groq
+import gradio as gr
+from docxtpl import DocxTemplate
+from datetime import datetime
+
+# Set your API key
+os.environ["GROQ_API_KEY"] = "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"
+# Initialize Groq client
+client = Groq(api_key=os.environ.get("GROQ_API_KEY"))
+
+# --- Resume Extraction Functions ---
+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 = ''
+        for page in range(len(pdf_reader.pages)):
+            text += pdf_reader.pages[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') as txt_file:
+        text = txt_file.read()
+    return text
+
+# --- Skill Extraction with Llama Model ---
+def extract_skills_llama(text):
+    """Extracts skills from the text using the Llama model via Groq API."""
+    chat_completion = client.chat.completions.create(
+        messages=[
+            {
+                "role": "user",
+                "content": f"Extract skills from the following text: {text}",
+            }
+        ],
+        model="llama3-70b-8192",  # Using Llama model
+    )
+    skills = chat_completion.choices[0].message.content.split(', ')  # Assuming skills are returned as a comma-separated list
+    return skills
+
+# --- Job Description Processing ---
+def process_job_description(job_description_text):
+    """Processes the job description text."""
+    # 1. Preprocess the job description text
+    job_description_text = preprocess_text(job_description_text)
+    # 2. Extract skills from the job description using Llama
+    job_description_skills = extract_skills_llama(job_description_text)
+    return job_description_skills
+
+# --- Text Preprocessing ---
+def preprocess_text(text):
+    """Preprocesses text for better analysis."""
+    text = text.lower()  # Convert to lowercase
+    text = re.sub(r'[^\w\s]', '', text)  # Remove punctuation
+    text = re.sub(r'\s+', ' ', text)  # Remove extra whitespace
+    return text
+
+# --- Resume Similarity ---
+def calculate_resume_similarity(resume_text, job_description_text):
+    """Calculates the similarity between the resume and job description using a Hugging Face 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, max_length=512)
+    with torch.no_grad():
+        outputs = model(**inputs)
+        similarity_score = torch.sigmoid(outputs.logits).item()
+    return similarity_score
+
+# --- Communication Generation ---
+def communication_generator(message, max_length=100):
+    """Generates a communication response based on the input message using a Hugging Face model."""
+    model_name = "google/flan-t5-base"
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+    inputs = tokenizer(message, return_tensors="pt", padding=True, truncation=True, max_length=512)
+    response = model.generate(**inputs, max_length=max_length, num_beams=4, early_stopping=True)
+    generated_response = tokenizer.batch_decode(response, skip_special_tokens=True)[0]
+    return generated_response + " We look forward to getting in touch with you soon!"
+
+# --- Sentiment Analysis ---
+def sentiment_model(text):
+    """Analyzes the sentiment of the text using a Hugging Face model."""
+    model_name = "distilbert-base-uncased-finetuned-sst-3-literal"
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    model = AutoModelForSequenceClassification.from_pretrained(model_name)
+    inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True, max_length=512)
+    with torch.no_grad():
+        outputs = model(**inputs)
+        predicted_class = torch.argmax(outputs.logits).item()
+    sentiment_labels = {0: "Negative", 1: "Neutral", 2: "Positive"}
+    return sentiment_labels[predicted_class]
+
+# --- Placeholder Functions for Enhancement ---
+def enhance_resume(resume_text):
+    """Placeholder function for enhancing the resume (you can implement your own logic here)."""
+    return resume_text
+
+def enhance_job_description(job_description_text):
+    """Placeholder function for enhancing the job description (you can implement your own logic here)."""
+    return job_description_text
+
+# --- Resume Analysis Function ---
+def analyze_resume(resume_file, job_description_file):
+    """Analyzes the resume and job description."""
+    if resume_file.name.endswith(('.pdf', '.txt')):
+        if resume_file.name.endswith('.pdf'):
+            resume_text = extract_text_from_pdf(resume_file.name)
+        else:
+            resume_text = extract_text_from_txt(resume_file.name)
+    else:
+        return "Invalid file type. Please upload a PDF or TXT file for the resume."
+
+    if job_description_file.name.endswith('.txt'):
+        job_description_text = extract_text_from_txt(job_description_file.name)
+    else:
+        return "Invalid file type. Please upload a TXT file for the job description."
+
+    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(f"I am reviewing a resume for a {job_description_text} position. The candidate has the following skills: {', '.join(resume_skills)}")
+    sentiment = sentiment_model(resume_text)
+    enhanced_resume = enhance_resume(resume_text)
+    enhanced_job_description = enhance_job_description(job_description_text)
+
+    return (
+        f"## Resume and Job Description Analysis",
+        f"**Similarity Score:** {similarity_score:.2f}",
+        f"**Communication Response:** {communication_response}",
+        f"**Sentiment:** {sentiment}",
+        f"**Resume Skills:** {', '.join(resume_skills)}",
+        f"**Job Description Skills:** {', '.join(job_description_skills)}",
+        f"**Enhanced Resume:**\n{enhanced_resume}",
+        f"**Enhanced Job Description:**\n{enhanced_job_description}",
+    )
+
+# --- Offer Letter Generation ---
+def generate_offer_letter(template_file, candidate_name, role, start_date, hours):
+    """Generates an offer letter."""
+    # Parse the start date string
+    try:
+        start_date = datetime.strptime(start_date, "%Y-%m-%d").strftime("%B %d, %Y")  # Format for DocxTemplate
+    except ValueError:
+        return "Invalid date format. Please use YYYY-MM-DD."
+
+    # Define the context variables
+    context = {
+        'candidate_name': candidate_name,
+        'role': role,
+        'start_date': start_date,
+        'hours': hours,
+    }
+
+    # Load the template document and render it with the context variables
+    tpl = DocxTemplate(template_file.name)
+    tpl.render(context)
+
+    # Save the generated document
+    script_dir = os.path.dirname(os.path.abspath(__file__))
+    docx_file_path = os.path.join(script_dir, f"{candidate_name}_offer_letter.docx")
+    tpl.save(docx_file_path)
+
+    # Return the file object
+    return open(docx_file_path, 'rb')
+
+# --- Gradio Interface ---
+demo = gr.Interface(
+    fn=analyze_resume,
+    inputs=[
+        gr.File(label="Upload Resume (PDF or TXT)"),
+        gr.File(label="Upload Job Description (TXT)"),
+    ],
+    outputs=[
+        gr.Textbox(label="Similarity Score"),
+        gr.Textbox(label="Communication Response"),
+        gr.Textbox(label="Sentiment Analysis"),
+        gr.Textbox(label="Resume Skills"),
+        gr.Textbox(label="Job Description Skills"),
+        gr.Textbox(label="Enhanced Resume", lines=20),
+        gr.Textbox(label="Enhanced Job Description", lines=10),
+    ],
+    title="Resume and Job Description Analyzer",
+    description="Upload your resume (PDF or TXT) and job description (TXT) to analyze their similarity, extract skills, and generate a communication response.",
+)
+
+offer_demo = gr.Interface(
+    fn=generate_offer_letter,
+    inputs=[
+        gr.File(label="Upload Offer Letter Template (DOCX)"),
+        gr.Textbox(label="Candidate Name"),
+        gr.Textbox(label="Role"),
+        gr.Textbox(label="Start Date (YYYY-MM-DD)"),  # Use Textbox for date
+        gr.Number(label="Hours per Week"),
+    ],
+    outputs=gr.File(label="Offer Letter"),  # Change to gr.File
+    title="Offer Letter Generator",
+    description="Upload an offer letter template and enter candidate information to generate an offer letter.",
+)
+
+# Combine the interfaces using a Tabbed interface
+demo = gr.TabbedInterface(
+    [demo, offer_demo],
+    ["Resume Analyzer", "Offer Letter Generator"],
+    title="HR Assistant",
+)
+
+if __name__ == '__main__':
+    demo.launch(share=True)