Update app.py

app.py

@@ -1,6 +1,7 @@
 import streamlit as st
 from pypdf import PdfReader
 from docx import Document
+from PIL import Image
 import requests
 import os
 import tempfile
@@ -12,33 +13,34 @@ from langchain_core.prompts import PromptTemplate
 from transformers import pipeline
 from langchain.llms import HuggingFacePipeline
 
-# Setup HuggingFace text generation pipeline (replace model with your choice)
+# Setup HuggingFace pipeline with distilgpt2 (small, CPU-friendly)
 text_gen_pipeline = pipeline(
     "text-generation",
-    model="gpt2",  # lightweight model for demo, swap for bigger model as needed
-    max_length=150
+    model="distilgpt2",
+    device=-1  # CPU only
 )
 llm = HuggingFacePipeline(pipeline=text_gen_pipeline)
 
-# Streamlit UI setup
+# App UI
 st.set_page_config(page_title="Learning with Fun", layout="wide")
 st.title("📘 Learning with Fun - Kids QA App")
 st.markdown("Ask questions from your syllabus! 📚")
 
-# Sidebar options
+# Sidebar
 grade = st.sidebar.selectbox("Select Grade", ["Grade 5", "Grade 6"])
 subject = st.sidebar.selectbox("Select Subject", ["Science", "Math", "Computer", "Islamiyat"])
 mode = st.sidebar.radio("Answer Format", ["🧠 Beginner Explanation", "📖 Storytelling"])
 voice_enabled = st.sidebar.checkbox("🔈 Enable Voice", value=True)
 
+# Google Drive PDF/DOC support
 def fetch_from_gdrive(link):
-    file_id = None
     if "id=" in link:
         file_id = link.split("id=")[1]
     elif "/d/" in link:
         file_id = link.split("/d/")[1].split("/")[0]
-    if not file_id:
+    else:
         return None
+
     url = f"https://drive.google.com/uc?export=download&id={file_id}"
     response = requests.get(url)
     if response.status_code == 200:
@@ -58,33 +60,28 @@ if file_link:
     else:
         st.error("Invalid Google Drive link or download error.")
 
+# Extract text from PDF or DOCX
 def extract_text(file_path):
     text = ""
     if file_path.endswith(".pdf"):
         reader = PdfReader(file_path)
         for page in reader.pages:
-            page_text = page.extract_text()
-            if page_text:
-                text += page_text
+            text += page.extract_text() or ""
     elif file_path.endswith(".docx"):
         doc = Document(file_path)
         for para in doc.paragraphs:
             text += para.text + "\n"
-    return text.strip()
+    return text
 
+# Create vectorstore from syllabus text
 def create_vectorstore(text):
-    if not text:
-        return None
-    splitter = CharacterTextSplitter(chunk_size=500, chunk_overlap=50)
-    docs = splitter.create_documents([text])
-    # Filter out empty docs if any
-    docs = [doc for doc in docs if doc.page_content.strip()]
-    if not docs:
-        return None
+    text_splitter = CharacterTextSplitter(chunk_size=500, chunk_overlap=50)
+    docs = text_splitter.create_documents([text])
     embeddings = HuggingFaceEmbeddings()
     vectorstore = FAISS.from_documents(docs, embeddings)
     return vectorstore
 
+# Prompt templates
 story_prompt = PromptTemplate.from_template(
     "ایک طالب علم نے سوال کیا: {question}\n"
     "نصاب کی معلومات: {context}\n"
@@ -97,39 +94,47 @@ explain_prompt = PromptTemplate.from_template(
     "براہ کرم بچے کو اردو زبان میں آسان انداز میں سمجھائیں۔"
 )
 
+# Generate voice from text
 def generate_voice(text, lang='ur'):
     tts = gTTS(text, lang=lang)
     tts_file = tempfile.NamedTemporaryFile(delete=False, suffix=".mp3")
     tts.save(tts_file.name)
     return tts_file.name
 
+# Get answer using LLM and vectorstore
 def get_answer(query, vectorstore, mode):
     retriever = vectorstore.as_retriever()
     docs = retriever.get_relevant_documents(query)
     context = "\n".join([doc.page_content for doc in docs])
-    prompt = story_prompt.format(question=query, context=context) if mode == "📖 Storytelling" else explain_prompt.format(question=query, context=context)
+
+    if mode == "📖 Storytelling":
+        prompt = story_prompt.format(question=query, context=context)
+    else:
+        prompt = explain_prompt.format(question=query, context=context)
+
     answer = llm.invoke(prompt)
     return answer
 
+# Main app logic
 if uploaded_file:
     raw_text = extract_text(uploaded_file)
-    if not raw_text:
-        st.error("❌ No text could be extracted from the syllabus file. Please check the file.")
+    if not raw_text.strip():
+        st.error("No text extracted from the file. Please check the file content.")
     else:
         st.success("📄 Syllabus loaded successfully!")
+
         query = st.text_input("❓ Ask your question (Urdu or English)")
         if query:
             with st.spinner("Thinking..."):
                 vs = create_vectorstore(raw_text)
-                if vs is None:
-                    st.error("❌ Failed to create vector store. The syllabus content may be too short or invalid.")
-                else:
-                    answer = get_answer(query, vs, mode)
-                    st.markdown("### ✅ Answer:")
-                    st.write(answer)
-                    if voice_enabled:
-                        audio_file = generate_voice(answer)
-                        with open(audio_file, "rb") as f:
-                            st.audio(f.read(), format="audio/mp3")
+                answer = get_answer(query, vs, mode)
+                st.markdown("### ✅ Answer:")
+                st.write(answer)
+
+                if voice_enabled:
+                    audio_file = generate_voice(answer)
+                    with open(audio_file, "rb") as audio:
+                        audio_bytes = audio.read()
+                        st.audio(audio_bytes, format="audio/mp3")
 else:
-    st.info("Please paste a valid Google Drive link to load your syllabus file.")
+    st.info("Please paste a Google Drive link to your syllabus file (.pdf or .docx) above.")