Update app.py

app.py

@@ -1,37 +1,24 @@
-import streamlit as st
+import json
 import requests
-import torch
-from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
-from huggingface_hub import InferenceClient, login
+import os
+import streamlit as st
 import pandas as pd
 import openpyxl
+import torch
+from reportlab.lib.pagesizes import letter
+from reportlab.pdfgen import canvas
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 
 # ✅ 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()
+st.markdown(
+    "<h1 style='text-align: center; color: #4CAF50;'>📅 AI-Powered Timetable</h1>",
+    unsafe_allow_html=True,
+)
 
-# ✅ 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)
-
-# ✅ Load Local Model with Device Optimization
-MODEL_NAME = "mistralai/Mistral-7B-Instruct-v0.2"
-device = "cuda" if torch.cuda.is_available() else "cpu"
-
-# ✅ 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)
+# ✅ API Key Input
+st.sidebar.markdown("## 🔑 Enter Hugging Face API Key")
+hf_api_key = st.sidebar.text_input("API Key", type="password")
 
 # ✅ File Upload Section
 st.sidebar.markdown("## 📂 Upload Your Timetable Files")
@@ -47,7 +34,7 @@ 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
@@ -55,41 +42,45 @@ def load_timetable(file):
     sheet = wb.active
     return [row for row in sheet.iter_rows(values_only=True)]
 
-# ✅ 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}
-    
+# ✅ Ask LLaMA-3 API via Hugging Face
+def ask_llama_api(query):
+    if not hf_api_key:
+        return "Error: Please enter your API key."
+
+    url = "https://api-inference.huggingface.co/v1/chat/completions"
+    headers = {
+        "Authorization": f"Bearer {hf_api_key}",
+        "Content-Type": "application/json",
+    }
+    payload = {
+        "model": "meta-llama/Meta-Llama-3-8B",
+        "messages": [{"role": "user", "content": query}],
+        "max_tokens": 500,
+    }
+
     response = requests.post(url, headers=headers, json=payload)
     if response.status_code == 200:
-        return response.json()[0]["generated_text"]
+        return response.json()["choices"][0]["message"]["content"]
     else:
-        return f"Error: {response.json()}"
+        return f"API Error: {response.status_code} - {response.text}"
 
-# ✅ 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
-
-# ✅ Auto-Schedule Missing Timetable Slots
+# ✅ 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 = []
 
+    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_mistral_local(query)
+        suggestion = ask_llama_api(query)
+
         try:
             subject, faculty = suggestion.split(", Faculty: ")
             sheet.cell(row=row_idx, column=4, value=subject.strip())
@@ -99,30 +90,132 @@ def auto_schedule(file):
 
     return f"Auto-scheduling completed for {len(empty_slots)} slots."
 
+# ✅ PDF Generation for Timetable
+def generate_pdf(file, filename="generated_timetable.pdf"):
+    if not file:
+        return "No timetable uploaded."
+
+    wb = openpyxl.load_workbook(file)
+    sheet = wb.active
+
+    pdf_filename = os.path.join(os.getcwd(), filename)
+    c = canvas.Canvas(pdf_filename, pagesize=letter)
+    width, height = letter
+    y = height - 50
+
+    c.setFont("Helvetica-Bold", 14)
+    c.drawString(200, y, "Generated Timetable")
+    y -= 30
+
+    c.setFont("Helvetica", 10)
+    for row in sheet.iter_rows(values_only=True):
+        row_text = " | ".join(str(cell) if cell else "" for cell in row)
+        c.drawString(50, y, row_text)
+        y -= 20
+        if y < 50:
+            c.showPage()
+            c.setFont("Helvetica", 10)
+            y = height - 50
+
+    c.save()
+    return pdf_filename
+
 # ✅ AI Query Section
-st.markdown("## 🤖 Ask Mistral AI About Your Timetable")
+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 API"):
-    ai_response = ask_mistral_api(user_query)
-    st.write("🧠 **Mistral AI Suggests:**", ai_response)
-
-if st.button("Ask AI via Local Model"):
-    ai_response = ask_mistral_local(user_query)
-    st.write("🧠 **Mistral AI Suggests:**", ai_response)
+    ai_response = ask_llama_api(user_query)
+    st.write("🧠 **LLaMA-3 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()))
+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)
 
+# ✅ Generate PDF
+st.markdown("## 📄 Generate PDF of Timetable")
+if st.button("Download PDF"):
+    pdf_path = generate_pdf(uploaded_files[selected_file])
+    with open(pdf_path, "rb") as pdf_file:
+        st.download_button("Download Timetable PDF", pdf_file, file_name="timetable.pdf")
+
 # ✅ 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)
+
+# ✅ Inject JavaScript for Real-Time Chat
+st.markdown(
+    """
+    <script>
+        async function fetchChatResponse() {
+            const apiKey = document.getElementById("hf-api-key").value;
+            const userInput = document.getElementById("user-input").value;
+            if (!apiKey) {
+                alert("Please enter your Hugging Face API key.");
+                return;
+            }
+
+            try {
+                const response = await fetch("https://api-inference.huggingface.co/v1/chat/completions", {
+                    method: "POST",
+                    headers: {
+                        "Authorization": `Bearer ${apiKey}`,
+                        "Content-Type": "application/json"
+                    },
+                    body: JSON.stringify({
+                        model: "meta-llama/Meta-Llama-3-8B",
+                        messages: [{ role: "user", content: userInput }],
+                        max_tokens: 500
+                    })
+                });
+
+                if (!response.ok) {
+                    throw new Error(`API Error: ${response.statusText}`);
+                }
+
+                const data = await response.json();
+                const botMessage = data.choices[0].message.content;
+
+                document.getElementById("chat-box").innerHTML += 
+                    `<div class='bot-message'><strong>VarunGPT-3:</strong> ${botMessage}</div>`;
+
+            } catch (error) {
+                console.error("Error fetching chat response:", error);
+                document.getElementById("chat-box").innerHTML += 
+                    `<div class='bot-message'><strong>Error:</strong> Unable to fetch response.</div>`;
+            }
+        }
+    </script>
+    """,
+    unsafe_allow_html=True,
+)
+
+# ✅ Chat UI with User Input for API Key
+st.markdown(
+    """
+    <div style="text-align: center;">
+        <input id="hf-api-key" type="password" placeholder="Enter Hugging Face API Key" 
+               style="width: 50%; padding: 8px; margin-bottom: 10px;"/>
+        <br/>
+        <input id="user-input" type="text" placeholder="Type your message..." 
+               style="width: 50%; padding: 8px;"/>
+        <button onclick="fetchChatResponse()" 
+                style="padding: 10px 20px; background-color: #4CAF50; color: white; border: none; cursor:pointer;">
+            Ask AI
+        </button>
+        <div id="chat-box" style="margin-top: 20px; text-align: left;"></div>
+    </div>
+    """,
+    unsafe_allow_html=True,
+)