Update app.py

app.py

@@ -4,16 +4,16 @@ import os
 import streamlit as st
 import pandas as pd
 import openpyxl
-import torch
 import faiss
+import torch
 from reportlab.lib.pagesizes import letter
 from reportlab.pdfgen import canvas
-from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 from sentence_transformers import SentenceTransformer
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
 # ✅ Streamlit UI Setup
 st.set_page_config(page_title="AI-Powered Timetable", layout="wide")
-st.markdown("<h1 style='text-align: center; color: #4CAF50;'>📅 AI-Powered Timetable with RAG</h1>", unsafe_allow_html=True)
+st.markdown("<h1 style='text-align: center; color: #4CAF50;'>📅 AI-Powered Timetable</h1>", unsafe_allow_html=True)
 
 # ✅ API Key Input
 st.sidebar.markdown("## 🔑 Enter Hugging Face API Key")
@@ -21,10 +21,10 @@ hf_api_key = st.sidebar.text_input("API Key", type="password")
 
 # ✅ File Upload Section
 st.sidebar.markdown("## 📂 Upload Your Timetable Files")
-uploaded_master = st.sidebar.file_uploader("Upload Master Timetable", type=["xlsx", "pdf"])
-uploaded_lab = st.sidebar.file_uploader("Upload Lab Timetable", type=["xlsx", "pdf"])
-uploaded_classroom = st.sidebar.file_uploader("Upload Classroom Timetable", type=["xlsx", "pdf"])
-uploaded_individual = st.sidebar.file_uploader("Upload Individual Timetable", type=["xlsx", "pdf"])
+uploaded_master = st.sidebar.file_uploader("Upload Master Timetable", type=["xlsx"])
+uploaded_lab = st.sidebar.file_uploader("Upload Lab Timetable", type=["xlsx"])
+uploaded_classroom = st.sidebar.file_uploader("Upload Classroom Timetable", type=["xlsx"])
+uploaded_individual = st.sidebar.file_uploader("Upload Individual Timetable", type=["xlsx"])
 
 uploaded_files = {
     "Master Timetable": uploaded_master,
@@ -33,51 +33,58 @@ uploaded_files = {
     "Individual Timetable": uploaded_individual,
 }
 
-# ✅ Load Timetable Data
+# ✅ Load Timetable Data (Directly from Uploaded File)
 def load_timetable(file):
     if not file:
         return None
-    if file.name.endswith('.xlsx'):
-        wb = openpyxl.load_workbook(file)
-        sheet = wb.active
-        return [row for row in sheet.iter_rows(values_only=True)]
-    elif file.name.endswith('.pdf'):
-        import PyPDF2
-        pdf_reader = PyPDF2.PdfReader(file)
-        text = ""
-        for page in pdf_reader.pages:
-            text += page.extract_text() + "\n"
-        return text
-
-# ✅ Extract and Store Data
+    wb = openpyxl.load_workbook(file)
+    sheet = wb.active
+    return [row for row in sheet.iter_rows(values_only=True)]
+
+# ✅ Initialize Sentence Transformer for Embeddings
+embedder = SentenceTransformer("all-MiniLM-L6-v2")
+
+# ✅ Process Uploaded Files and Create RAG Index
 rag_data = {}
 for name, file in uploaded_files.items():
     if file:
-        rag_data[name] = load_timetable(file)
+        timetable_data = load_timetable(file)
+        if timetable_data:
+            rag_data[name] = timetable_data
 
-# ✅ Encode Timetable Data with Sentence Embeddings
-embedder = SentenceTransformer("all-MiniLM-L6-v2")
+# ✅ Convert timetable data to text format
 data_texts = ["\n".join(map(str, data)) for data in rag_data.values() if data]
+
+if not data_texts:
+    st.error("Error: No extracted timetable content available for AI processing.")
+    st.stop()
+
+# ✅ Generate FAISS Embeddings
 data_embeddings = embedder.encode(data_texts, convert_to_tensor=True)
 
-# ✅ Create FAISS Vector Store
-dimension = data_embeddings.shape[1]
+if len(data_embeddings) == 0:
+    st.error("Error: No valid embeddings created. Check your timetable files.")
+    st.stop()
+
+dimension = data_embeddings.shape[1]  # FIXED ERROR: Ensuring valid shape
 index = faiss.IndexFlatL2(dimension)
 index.add(data_embeddings.cpu().numpy())
 
-# ✅ Retrieve Relevant Data using RAG
-def retrieve_data(query):
-    query_embedding = embedder.encode([query], convert_to_tensor=True)
-    D, I = index.search(query_embedding.cpu().numpy(), k=1)
-    return data_texts[I[0][0]] if I[0][0] < len(data_texts) else "No relevant data found."
+# ✅ Function to Retrieve Relevant Data from FAISS
+def retrieve_relevant_text(query, top_k=2):
+    query_embedding = embedder.encode([query], convert_to_tensor=True).cpu().numpy()
+    distances, indices = index.search(query_embedding, top_k)
+    
+    retrieved_texts = [data_texts[idx] for idx in indices[0] if idx < len(data_texts)]
+    return "\n".join(retrieved_texts)
 
-# ✅ Ask LLaMA-3-8B with RAG Context
+# ✅ Ask LLaMA-3 AI via API
 def ask_llama_api(query):
     if not hf_api_key:
         return "Error: Please enter your API key."
-    
-    context = retrieve_data(query)  # Get relevant timetable data
-    final_query = f"Based on the timetable data:\n{context}\nAnswer this query: {query}"
+
+    retrieved_text = retrieve_relevant_text(query)
+    context = f"Relevant timetable data:\n{retrieved_text}\n\nUser Query: {query}"
 
     url = "https://api-inference.huggingface.co/v1/chat/completions"
     headers = {
@@ -86,7 +93,7 @@ def ask_llama_api(query):
     }
     payload = {
         "model": "meta-llama/Meta-Llama-3-8B",
-        "messages": [{"role": "user", "content": final_query}],
+        "messages": [{"role": "user", "content": context}],
         "max_tokens": 500
     }
 
@@ -96,11 +103,37 @@ def ask_llama_api(query):
     else:
         return f"API Error: {response.status_code} - {response.text}"
 
+# ✅ Auto-Schedule Missing Slots
+def auto_schedule(file):
+    if not file:
+        return "No timetable uploaded."
+
+    wb = openpyxl.load_workbook(file)
+    sheet = wb.active
+
+    empty_slots = []
+    for row_idx, row in enumerate(sheet.iter_rows(min_row=2, values_only=True), start=2):
+        if None in row or "" in row:
+            empty_slots.append(row_idx)
+
+    for row_idx in empty_slots:
+        query = f"Suggest a subject and faculty for the empty slot in row {row_idx}."
+        suggestion = ask_llama_api(query)
+
+        try:
+            subject, faculty = suggestion.split(", Faculty: ")
+            sheet.cell(row=row_idx, column=4, value=subject.strip())
+            sheet.cell(row=row_idx, column=5, value=faculty.strip())
+        except:
+            continue  
+
+    return f"Auto-scheduling completed for {len(empty_slots)} slots."
+
 # ✅ AI Query Section
 st.markdown("## 🤖 Ask LLaMA-3 AI About Your Timetable")
 user_query = st.text_input("Type your question here (e.g., 'Who is free at 10 AM on Monday?')")
 
-if st.button("Ask AI via RAG"):
+if st.button("Ask AI via API"):
     ai_response = ask_llama_api(user_query)
     st.write("🧠 **LLaMA-3 AI Suggests:**", ai_response)
 
@@ -109,7 +142,7 @@ st.markdown("## 📅 Auto-Schedule Missing Timetable Slots")
 selected_file = st.selectbox("Choose a timetable file to auto-fill missing slots:", list(uploaded_files.keys()))
 
 if st.button("Auto-Schedule"):
-    result = retrieve_data(selected_file)
+    result = auto_schedule(uploaded_files[selected_file])
     st.write("✅", result)
 
 # ✅ Display Uploaded Timetables
@@ -117,24 +150,6 @@ st.markdown("## 📜 View Uploaded Timetables")
 
 for name, file in uploaded_files.items():
     if file:
-        df = pd.read_excel(file) if file.name.endswith(".xlsx") else None
+        df = pd.read_excel(file)
         st.markdown(f"### {name}")
-        if df is not None:
-            st.dataframe(df)
-        else:
-            st.text(rag_data[name])
-
-# ✅ PDF Export Feature
-st.sidebar.markdown("## 📄 Export AI Responses to PDF")
-if st.sidebar.button("Export as PDF"):
-    c = canvas.Canvas("Timetable_Responses.pdf", pagesize=letter)
-    c.drawString(100, 750, "AI-Powered Timetable Responses")
-    y = 720
-    for query, response in [("Example Query", "Example Response")]:  # Replace with actual
-        c.drawString(50, y, f"Q: {query}")
-        y -= 20
-        c.drawString(70, y, f"A: {response}")
-        y -= 30
-    c.save()
-    st.sidebar.success("PDF Exported: Timetable_Responses.pdf")
-
+        st.dataframe(df)