Update app.py

app.py

@@ -1,33 +1,38 @@
-import json
-import os
-import requests
 import streamlit as st
-import pandas as pd
-import openpyxl
+import requests
 import torch
-from reportlab.lib.pagesizes import letter
-from reportlab.pdfgen import canvas
-from huggingface_hub import InferenceClient
 from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+from huggingface_hub import InferenceClient, login
+import pandas as pd
+import openpyxl
+
+# ✅ 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</h1>", unsafe_allow_html=True)
+
+# ✅ User Input for API Key
+st.sidebar.markdown("## 🔑 Enter Your Hugging Face API Key")
+HF_API_KEY = st.sidebar.text_input("API Key", type="password")
+
+if not HF_API_KEY:
+    st.warning("Please enter your Hugging Face API key to proceed.")
+    st.stop()
 
-# ✅ Secure API Key Input (User provides it manually)
-HF_API_KEY = st.sidebar.text_input("Enter your Hugging Face API Key", type="password")
+# ✅ Authenticate with Hugging Face (No Need for CLI Login)
+login(token=HF_API_KEY, add_to_git_credential=False)
 
 # ✅ Initialize Hugging Face API Client
-client = InferenceClient(token=HF_API_KEY) if HF_API_KEY else None
+client = InferenceClient(token=HF_API_KEY)
 
 # ✅ Load Local Model with Device Optimization
 MODEL_NAME = "mistralai/Mistral-7B-Instruct-v0.2"
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
-tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
-model = AutoModelForCausalLM.from_pretrained(MODEL_NAME).to(device)
+# ✅ Load Model & Tokenizer with API Authentication
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, token=HF_API_KEY)
+model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, token=HF_API_KEY).to(device)
 pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, device=0 if device == "cuda" else -1)
 
-# ✅ 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</h1>", unsafe_allow_html=True)
-
 # ✅ File Upload Section
 st.sidebar.markdown("## 📂 Upload Your Timetable Files")
 uploaded_master = st.sidebar.file_uploader("Upload Master Timetable", type=["xlsx"])
@@ -42,57 +47,82 @@ uploaded_files = {
     "Individual Timetable": uploaded_individual,
 }
 
-# ✅ Load Timetable Data (Directly from Uploaded File)
+# ✅ Load Timetable Data
 def load_timetable(file):
     if not file:
         return None
-    df = pd.read_excel(file)
-    return df
+    wb = openpyxl.load_workbook(file)
+    sheet = wb.active
+    return [row for row in sheet.iter_rows(values_only=True)]
 
-# ✅ Ask Mistral AI via API with Timetable Context
-def ask_mistral_api_with_timetable(query, timetable_df):
-    if timetable_df is None:
-        return "No timetable uploaded."
+# ✅ Query Mistral AI via API
+def ask_mistral_api(query):
+    headers = {"Authorization": f"Bearer {HF_API_KEY}"}
+    url = f"https://api-inference.huggingface.co/models/{MODEL_NAME}"
+    payload = {"inputs": query, "max_new_tokens": 500}
+    
+    response = requests.post(url, headers=headers, json=payload)
+    if response.status_code == 200:
+        return response.json()[0]["generated_text"]
+    else:
+        return f"Error: {response.json()}"
 
-    # Convert timetable to text format
-    timetable_text = timetable_df.to_string(index=False)
+# ✅ Query Mistral AI Locally
+def ask_mistral_local(query):
+    inputs = tokenizer(query, return_tensors="pt").to(device)
+    outputs = model.generate(**inputs, max_new_tokens=200)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
 
-    prompt = f"Here is a timetable:\n\n{timetable_text}\n\nUser Query: {query}\n\nAnswer based on the timetable."
+# ✅ Auto-Schedule Missing Timetable Slots
+def auto_schedule(file):
+    if not file:
+        return "No timetable uploaded."
 
-    headers = {"Authorization": f"Bearer {HF_API_KEY}"}
-    payload = {
-        "model": MODEL_NAME,
-        "messages": [{"role": "user", "content": prompt}],
-        "max_tokens": 500,
-    }
+    wb = openpyxl.load_workbook(file)
+    sheet = wb.active
+    empty_slots = []
 
-    response = requests.post("https://api-inference.huggingface.co/v1/chat/completions", json=payload, headers=headers)
+    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)
 
-    if response.status_code == 200:
-        return response.json()["choices"][0]["message"]["content"]
-    else:
-        return f"Error: {response.json()}"
+    for row_idx in empty_slots:
+        query = f"Suggest a subject and faculty for the empty slot in row {row_idx}."
+        suggestion = ask_mistral_local(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 (with Timetable Scanning)
+# ✅ AI Query Section
 st.markdown("## 🤖 Ask Mistral AI About Your Timetable")
-selected_file = st.selectbox("Choose a timetable file to scan:", list(uploaded_files.keys()))
+user_query = st.text_input("Type your question here (e.g., 'Who is free at 10 AM on Monday?')")
 
-if uploaded_files[selected_file]:
-    timetable_df = load_timetable(uploaded_files[selected_file])
-    user_query = st.text_input("Type your question (e.g., 'Who is free at 10 AM on Monday?')")
+if st.button("Ask AI via API"):
+    ai_response = ask_mistral_api(user_query)
+    st.write("🧠 **Mistral AI Suggests:**", ai_response)
 
-    if st.button("Ask AI via API with Timetable"):
-        ai_response = ask_mistral_api_with_timetable(user_query, timetable_df)
-        st.write("🧠 **Mistral AI Suggests:**", ai_response)
-else:
-    st.write("⚠️ Please upload a timetable file first.")
+if st.button("Ask AI via Local Model"):
+    ai_response = ask_mistral_local(user_query)
+    st.write("🧠 **Mistral AI Suggests:**", ai_response)
+
+# ✅ Auto-Schedule Feature
+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 = auto_schedule(uploaded_files[selected_file])
+    st.write("✅", result)
 
 # ✅ Display Uploaded Timetables
 st.markdown("## 📜 View Uploaded Timetables")
-
 for name, file in uploaded_files.items():
     if file:
         df = pd.read_excel(file)
         st.markdown(f"### {name}")
         st.dataframe(df)
-