Create app.py

app.py

@@ -0,0 +1,88 @@
+import gradio as gr
+import fitz  # PyMuPDF for PDF reading
+from sentence_transformers import SentenceTransformer, util
+
+# Load sentence transformer model
+model = SentenceTransformer("all-MiniLM-L6-v2")
+
+# Sample top skills to match in resume
+top_skills = [
+    "Python", "Java", "C++", "SQL", "JavaScript", "React", "Node.js",
+    "Machine Learning", "Data Analysis", "Excel", "Communication",
+    "Project Management", "AWS", "Docker", "Leadership", "Time Management",
+    "Problem Solving", "Teamwork", "Critical Thinking"
+]
+
+def extract_text_from_pdf(pdf_file):
+    doc = fitz.open(pdf_file)
+    text = ""
+    for page in doc:
+        text += page.get_text()
+    return text
+
+def analyze_resume(text):
+    # Split into sentences
+    sentences = [s.strip() for s in text.split(".") if len(s.strip()) > 5]
+    if not sentences:
+        return "Could not extract sentences.", "", "", ""
+
+    # Encode sentences and skills
+    sentence_embeddings = model.encode(sentences, convert_to_tensor=True)
+    skill_embeddings = model.encode(top_skills, convert_to_tensor=True)
+
+    # Compare each skill to each sentence
+    cosine_scores = util.cos_sim(skill_embeddings, sentence_embeddings)
+
+    found_skills = []
+    for idx, skill in enumerate(top_skills):
+        score = max(cosine_scores[idx])  # Best score across all sentences
+        if score > 0.4:
+            found_skills.append(skill)
+
+    # Match to job titles (basic logic)
+    job_titles = []
+    if "Python" in found_skills and "Data Analysis" in found_skills:
+        job_titles.append("Data Analyst")
+    if "JavaScript" in found_skills and "React" in found_skills:
+        job_titles.append("Frontend Developer")
+    if "Project Management" in found_skills:
+        job_titles.append("Project Manager")
+    if "Machine Learning" in found_skills:
+        job_titles.append("ML Engineer")
+    if not job_titles:
+        job_titles.append("General Tech Roles")
+
+    missing_skills = [s for s in top_skills if s not in found_skills]
+
+    return ", ".join(found_skills), ", ".join(job_titles), ", ".join(missing_skills[:5])
+
+def process_resume(file_obj):
+    filename = file_obj.name
+    ext = filename.split(".")[-1].lower()
+
+    if ext == "pdf":
+        resume_text = extract_text_from_pdf(filename)
+    elif ext == "txt":
+        resume_text = file_obj.read().decode("utf-8")
+    else:
+        return "Unsupported file format", "", "", ""
+
+    extracted, jobs, suggestions = analyze_resume(resume_text)
+    return resume_text, extracted, jobs, suggestions
+
+# Gradio UI
+demo = gr.Interface(
+    fn=process_resume,
+    inputs=gr.File(label="Upload your resume (.pdf or .txt)"),
+    outputs=[
+        gr.Textbox(label="Resume Text", lines=10),
+        gr.Textbox(label="Detected Skills"),
+        gr.Textbox(label="Suggested Job Titles"),
+        gr.Textbox(label="Recommended Skills to Learn")
+    ],
+    title="Resume Analyzer & Job Matcher",
+    description="Upload a PDF or text resume to get job suggestions and skill feedback using AI."
+)
+
+if __name__ == "__main__":
+    demo.launch()