Update app.py

app.py

@@ -3,27 +3,36 @@ import faiss
 import numpy as np
 from sentence_transformers import SentenceTransformer
 
-# Load resume data
+# Load resume data in structured format
 resume_data = {
-    "name": "Pradeep Singh Sengar",
-    "linkedin": "www.linkedin.com/in/ipradeepsengarr",
-    "email": "pradeep19sengar@gmail.com",
-    "github": "github.com/pradeepsengar",
-    "mobile": "+91-7898367211",
-    "education": "Bachelor of Engineering (Hons.) - Information Technology; CGPA: 8.31 (Oriental College Of Technology, Bhopal, 2019-2023)",
-    "skills": "Python, HTML/CSS, Django, Reactjs, Node.js, Git, Web Scraping, Generative AI, Machine Learning (LLM)",
-    "experience": "Graduate Engineer Trainee at Jio Platform Limited (Dec. 2023 - Present). Implemented chatbots with Docker, used Git/GitHub, worked with LLM concepts and Hugging Face.",
-    "projects": "Room Rental System, Text to Image Generator, Fitness Tracker, Movie Recommendation System",
-    "honors_awards": "Qualified for Round 1B of SnackDown (CodeChef), Startup Challenge (Top 10 teams)",
-    "certifications": "Web Development (Internshala), The Complete Python Pro Bootcamp (Udemy), Data Science (LinkedIn Learning), Web Scraping (LinkedIn Learning)"
+    "Name": "Pradeep Singh Sengar",
+    "LinkedIn": "[LinkedIn Profile](https://www.linkedin.com/in/pradeepsengarr)",
+    "Email": "pradeep19sengar@gmail.com",
+    "GitHub": "[GitHub Profile](https://github.com/pradeepsengar)",
+    "Mobile": "+91-7898367211",
+    "Education": "Bachelor of Engineering (Hons.) - Information Technology (CGPA: 8.31, Oriental College Of Technology, Bhopal, 2019-2023)",
+    "Skills": "Python, HTML/CSS, Django, React.js, Node.js, Git, Web Scraping, Generative AI, Machine Learning (LLM)",
+    "Experience": "Graduate Engineer Trainee at Jio Platform Limited (Dec. 2023 - Present). Implemented chatbots with Docker, used Git/GitHub, worked with LLM concepts and Hugging Face.",
+    "Projects": "Room Rental System, Text to Image Generator, Fitness Tracker, Movie Recommendation System",
+    "Certifications": "Salesforce AI Associate, Web Development (Internshala), Data Science (LinkedIn Learning)",
 }
 
-# Convert data to list of sentences for retrieval
+# Suggested common questions
+suggested_questions = [
+    "What are your key skills?",
+    "Tell me about your work experience?",
+    "What projects have you worked on?",
+    "What certifications do you have?",
+    "How can I contact you?",
+]
+
+# Convert resume data to list for embedding
+resume_keys = list(resume_data.keys())
 resume_values = list(resume_data.values())
 
 # Load embedding model
 model = SentenceTransformer('all-MiniLM-L6-v2')
-embeddings = model.encode(resume_values)
+embeddings = model.encode(resume_keys)
 
 # Store embeddings in FAISS index
 index = faiss.IndexFlatL2(embeddings.shape[1])
@@ -32,13 +41,28 @@ index.add(np.array(embeddings))
 def get_response(query):
     query_embedding = model.encode([query])
     D, I = index.search(query_embedding, 1)
-    return resume_values[I[0][0]]
+    score = 1 - (D[0][0] / np.max(D))  # Convert distance to similarity
+    key = resume_keys[I[0][0]]
+    response = resume_data[key]
+    return key, response, round(score * 100, 2)
 
 # Streamlit UI
-st.title("📝 Resume Chatbot")
-st.write("Ask anything about Pradeep's resume!")
+st.set_page_config(page_title="Resume Chatbot", page_icon="🤖", layout="centered")
+st.title("🤖 Chat with My Resume")
+st.write("Ask me anything about my resume or pick a question below:")
+
+# Suggested questions UI
+cols = st.columns(len(suggested_questions))
+for i, question in enumerate(suggested_questions):
+    if cols[i].button(question):
+        user_input = question
+    
+# User input box
+user_input = st.text_input("Your question:", key="user_query")
 
-user_input = st.text_input("Your question:")
 if user_input:
-    response = get_response(user_input)
-    st.success(f"**Answer:** {response}")
+    key, response, confidence = get_response(user_input)
+    if confidence > 50:
+        st.success(f"**{key}:** {response} (Confidence: {confidence}%)")
+    else:
+        st.warning("I'm not sure about this. Can you ask in a different way?")