Upload 4 files

README.md

@@ -1,12 +1,30 @@
 ---
-title: Srcdaksh
-emoji: 🔥
-colorFrom: purple
-colorTo: purple
+title: SETHU AI - Resume Gap Analyzer
+emoji: 🎓
+colorFrom: indigo
+colorTo: blue
 sdk: gradio
-sdk_version: 6.9.0
+sdk_version: 4.21.0
 app_file: app.py
 pinned: false
+license: mit
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# SETHU AI - Resume Gap Analyzer
+**From Resume to Career Readiness**
+*In collaboration with SASTRA DEEMED UNIVERSITY*
+
+An intelligent tool to analyze the gap between your resume and a specific job description.
+
+## Features
+- **PDF/DOCX Upload**: Extract text from common resume formats.
+- **Skill Extraction**: Automatically identify skills using spaCy NLP.
+- **Similarity Scoring**: semantic comparison using Sentence Transformers (`all-MiniLM-L6-v2`).
+- **Gap Analysis**: Detailed list of missing skills and present skills.
+- **Guidance & Roadmap**: Get learning paths for missing skills.
+
+## Local Installation
+```bash
+pip install -r requirements.txt
+python app.py
+```

app.py

@@ -0,0 +1,217 @@
+import gradio as gr
+import spacy
+import pdfplumber
+from docx import Document
+from sentence_transformers import SentenceTransformer, util
+import pandas as pd
+import re
+
+# Load models
+try:
+    nlp = spacy.load("en_core_web_sm")
+except:
+    # Fallback if model installation via requirements.txt fails in local env
+    import os
+    os.system("python -m spacy download en_core_web_sm")
+    nlp = spacy.load("en_core_web_sm")
+
+model = SentenceTransformer('all-MiniLM-L6-v2')
+
+# Common Skill Dictionary (Simplified for the demo)
+SKILLS_DB = [
+    "python", "javascript", "react", "fastapi", "aws", "docker", "kubernetes", "sql", 
+    "git", "machine learning", "nlp", "tensorflow", "pytorch", "java", "c++", "golang",
+    "postgresql", "mongodb", "redis", "cloud computing", "devops", "rest api", "graphql",
+    "scikit-learn", "pandas", "numpy", "django", "flask", "typescript", "angular", "vue"
+]
+
+ROADMAP_DB = {
+    "python": "Master Python: [Real Python](https://realpython.com/) | [Programming with Mosh](https://www.youtube.com/user/programmingwithmosh)",
+    "react": "Build UI with React: [Official Docs](https://react.dev/) | [FreeCodeCamp React Course](https://www.freecodecamp.org/news/free-react-course-2024/)",
+    "aws": "Cloud Mastery: [AWS Skill Builder](https://explore.skillbuilder.aws/) | [Cloud Guru](https://www.pluralsight.com/cloud-computing/aws)",
+    "docker": "Containerization: [Docker Get Started](https://docs.docker.com/get-started/) | [Docker Tutorial for Beginners](https://www.youtube.com/watch?v=pg19Z8LL06w)",
+    "kubernetes": "Orchestration: [K8s Basics](https://kubernetes.io/docs/tutorials/kubernetes-basics/) | [Nana's K8s Course](https://www.youtube.com/c/TechWorldwithNana)",
+    "fastapi": "Modern APIs: [FastAPI Docs](https://fastapi.tiangolo.com/) | [TestDriven.io FastAPI](https://testdriven.io/blog/fastapi-crud/)",
+    "nlp": "Language Processing: [Hugging Face NLP Course](https://huggingface.co/learn/nlp-course/) | [Stanford CS224N](https://web.stanford.edu/class/cs224n/)",
+    "machine learning": "AI Fundamentals: [ML Specialization by Andrew Ng](https://www.coursera.org/specializations/machine-learning-introduction)",
+    "sql": "Database Management: [SQLZoo](https://sqlzoo.net/) | [Mode SQL Tutorial](https://mode.com/sql-tutorial/)",
+    "git": "Version Control: [Git Immersion](https://gitimmersion.com/) | [GitHub Learning Path](https://skills.github.com/)",
+    "javascript": "JS Deep Dive: [MDN Web Docs](https://developer.mozilla.org/en-US/docs/Web/JavaScript) | [JavaScript.info](https://javascript.info/)",
+    "typescript": "Strict Typing: [TypeScript Handbook](https://www.typescriptlang.org/docs/handbook/intro.html)",
+    "postgresql": "Advanced Data: [Postgres Tutorial](https://www.postgresqltutorial.com/)",
+    "rest api": "API Design: [RESTful API Guide](https://restfulapi.net/)"
+}
+
+def extract_text_from_pdf(pdf_file):
+    with pdfplumber.open(pdf_file) as pdf:
+        text = ""
+        for page in pdf.pages:
+            text += page.extract_text() or ""
+    return text
+
+def extract_text_from_docx(docx_file):
+    doc = Document(docx_file)
+    text = ""
+    for para in doc.paragraphs:
+        text += para.text + "\n"
+    return text
+
+def clean_text(text):
+    text = re.sub(r'[^a-zA-Z0-9\s]', '', text)
+    return text.lower().strip()
+
+def get_skills(text):
+    text = clean_text(text)
+    found_skills = set()
+    for skill in SKILLS_DB:
+        if re.search(r'\b' + re.escape(skill) + r'\b', text):
+            found_skills.add(skill)
+    return found_skills
+
+def analyze_resume(resume_file, jd_text):
+    if resume_file is None or not jd_text.strip():
+        return "Please upload a resume and provide a job description.", "", "", 0, None
+
+    # Step 1: Extract text
+    if resume_file.name.endswith('.pdf'):
+        resume_text = extract_text_from_pdf(resume_file)
+    elif resume_file.name.endswith('.docx'):
+        resume_text = extract_text_from_docx(resume_file)
+    else:
+        return "Unsupported file format. Please upload PDF or DOCX.", "", "", 0, None
+
+    # Step 2: NLP Analysis (Skills)
+    resume_skills = get_skills(resume_text)
+    jd_skills = get_skills(jd_text)
+
+    present_skills = list(resume_skills.intersection(jd_skills))
+    missing_skills = list(jd_skills - resume_skills)
+
+    # Step 3: Similarity Score (Sentence Transformers)
+    embeddings1 = model.encode(resume_text, convert_to_tensor=True)
+    embeddings2 = model.encode(jd_text, convert_to_tensor=True)
+    cosine_score = util.pytorch_cos_sim(embeddings1, embeddings2)
+    match_percentage = round(cosine_score.item() * 100, 2)
+
+    # Format output
+    present_str = ", ".join([s.capitalize() for s in present_skills]) if present_skills else "None found."
+    missing_str = ", ".join([s.capitalize() for s in missing_skills]) if missing_skills else "None! You are a great match."
+    
+    return f"{match_percentage}%", present_str, missing_str, match_percentage, missing_skills
+
+def get_roadmap(missing_skills):
+    if not missing_skills:
+        return "🎉 Great job! You have all the key skills mentioned. Keep up explicitly highlighting them in your experience section."
+    
+    roadmap_items = []
+    for skill in missing_skills:
+        resource = ROADMAP_DB.get(skill.lower(), f"Search for {skill} tutorials on YouTube or Coursera.")
+        roadmap_items.append(f"### {skill.capitalize()}\n{resource}")
+    
+    return "\n\n".join(roadmap_items)
+
+# Custom CSS for Premium Look
+custom_css = """
+#logo-img {
+    margin: auto;
+    display: block;
+}
+.gradio-container {
+    background-color: #f8f9fa;
+}
+.main-header {
+    text-align: center;
+    color: #003366; /* Navy Blue from Logo */
+    margin-bottom: 20px;
+}
+.sub-header {
+    text-align: center;
+    color: #b8860b; /* Gold from Logo */
+    font-weight: bold;
+}
+.sastra-text {
+    text-align: center;
+    font-size: 0.9em;
+    color: #555;
+    letter-spacing: 1px;
+}
+#analyze-btn {
+    background: linear-gradient(90deg, #003366 0%, #004080 100%) !important;
+    color: white !important;
+    border: none;
+    border-radius: 8px;
+    padding: 10px 20px;
+    font-weight: bold;
+}
+#roadmap-btn {
+    background: linear-gradient(90deg, #b8860b 0%, #daa520 100%) !important;
+    color: white !important;
+    border: none;
+}
+"""
+
+# Gradio Interface
+with gr.Blocks(theme=gr.themes.Soft(primary_hue="indigo"), css=custom_css) as demo:
+    with gr.Row(variant="compact"):
+        with gr.Column(scale=1):
+            gr.Image("logo.png", show_label=False, height=120, container=False, elem_id="logo-img")
+        with gr.Column(scale=4):
+            gr.Markdown("# SETHU AI", elem_classes=["main-header"])
+            gr.Markdown("### From Resume to Career Readiness", elem_classes=["sub-header"])
+            gr.Markdown("SASTRA DEEMED UNIVERSITY", elem_classes=["sastra-text"])
+    
+    gr.Markdown("---")
+    
+    with gr.Row():
+        with gr.Column():
+            gr.Markdown("### 📄 Input Details")
+            resume_input = gr.File(label="Upload Resume (PDF or DOCX)", file_types=[".pdf", ".docx"])
+            jd_input = gr.Textbox(label="Job Description", placeholder="Paste the job requirements here...", lines=8)
+            analyze_btn = gr.Button("Analyze Resume", variant="primary", elem_id="analyze-btn")
+        
+        with gr.Column():
+            gr.Markdown("### 📊 Analysis Dashboard")
+            match_score_output = gr.Label(label="Match Percentage")
+            
+            with gr.Tabs():
+                with gr.TabItem("Skills Found"):
+                    present_skills_output = gr.Textbox(label="Available in Resume", interactive=False)
+                with gr.TabItem("Gap Analysis"):
+                    missing_skills_output = gr.Textbox(label="Skills to Acquire", interactive=False)
+            
+            gr.Markdown("---")
+            roadmap_btn = gr.Button("Get Guidance & Roadmap", interactive=True, elem_id="roadmap-btn")
+            roadmap_output = gr.Markdown(visible=False)
+
+    # State for hidden analysis results
+    missing_skills_state = gr.State([])
+
+    def on_analyze(resume, jd):
+        score_str, present, missing, score_val, missing_list = analyze_resume(resume, jd)
+        return {
+            match_score_output: score_str,
+            present_skills_output: present,
+            missing_skills_output: missing,
+            roadmap_btn: gr.update(interactive=True),
+            missing_skills_state: missing_list,
+            roadmap_output: gr.update(visible=False)
+        }
+
+    def on_roadmap(missing_list):
+        roadmap_content = get_roadmap(missing_list)
+        return gr.update(value=roadmap_content, visible=True)
+
+    analyze_btn.click(
+        on_analyze, 
+        inputs=[resume_input, jd_input], 
+        outputs=[match_score_output, present_skills_output, missing_skills_output, roadmap_btn, missing_skills_state, roadmap_output]
+    )
+    
+    roadmap_btn.click(
+        on_roadmap,
+        inputs=[missing_skills_state],
+        outputs=[roadmap_output]
+    )
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,8 @@
+gradio
+spacy
+sentence-transformers
+pdfplumber
+python-docx
+scikit-learn
+reportlab
+https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.7.1/en_core_web_sm-3.7.1-py3-none-any.whl

sample_jd.txt

@@ -0,0 +1,14 @@
+Job Title: Senior Python Developer
+
+Responsibilities:
+- Design and implement scalable backend services using Python and FastAPI.
+- Work with SQL databases like PostgreSQL and NoSQL like Redis.
+- Deploy applications using Docker and Kubernetes.
+- Collaborate with frontend teams to integrate React components with REST APIs.
+- Experience with AWS (EC2, S3, Lambda) is required.
+
+Required Skills:
+- Python, Javascript, React, FastAPI
+- AWS, Docker, Kubernetes, SQL, Git
+- Machine Learning basics, NLP
+- Problem-solving and teamwork