Update app.py

app.py

@@ -1,19 +1,22 @@
 import streamlit as st
 from pypdf import PdfReader
 from docx import Document
-from PIL import Image
-import requests
-import os
 import tempfile
+import requests
 from gtts import gTTS
+
+from PIL import Image
+
 from langchain.vectorstores import FAISS
 from langchain.embeddings import HuggingFaceEmbeddings
 from langchain.text_splitter import CharacterTextSplitter
-from langchain_core.prompts import PromptTemplate
-from transformers import pipeline
+from langchain.prompts import PromptTemplate
 from langchain.llms import HuggingFacePipeline
 
-# Setup HuggingFace pipeline with distilgpt2 (small, CPU-friendly)
+from transformers import pipeline
+
+
+# Setup HuggingFace pipeline with distilgpt2 (CPU)
 text_gen_pipeline = pipeline(
     "text-generation",
     model="distilgpt2",
@@ -21,24 +24,25 @@ text_gen_pipeline = pipeline(
 )
 llm = HuggingFacePipeline(pipeline=text_gen_pipeline)
 
-# App UI
+# Streamlit app config
 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
+# Sidebar widgets
 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):
+# Fetch syllabus file from Google Drive link
+def fetch_from_gdrive(link: str) -> str | None:
+    file_id = None
     if "id=" in link:
-        file_id = link.split("id=")[1]
+        file_id = link.split("id=")[1].split("&")[0]
     elif "/d/" in link:
         file_id = link.split("/d/")[1].split("/")[0]
-    else:
+    if not file_id:
         return None
 
     url = f"https://drive.google.com/uc?export=download&id={file_id}"
@@ -60,23 +64,27 @@ if file_link:
     else:
         st.error("Invalid Google Drive link or download error.")
 
-# Extract text from PDF or DOCX
-def extract_text(file_path):
+# Extract text content from uploaded file
+def extract_text(file_path: str) -> str:
     text = ""
     if file_path.endswith(".pdf"):
         reader = PdfReader(file_path)
         for page in reader.pages:
-            text += page.extract_text() or ""
+            page_text = page.extract_text()
+            if page_text:
+                text += page_text
     elif file_path.endswith(".docx"):
         doc = Document(file_path)
         for para in doc.paragraphs:
             text += para.text + "\n"
+    else:
+        st.error("Unsupported file format. Please upload a PDF or DOCX file.")
     return text
 
-# Create vectorstore from syllabus text
-def create_vectorstore(text):
-    text_splitter = CharacterTextSplitter(chunk_size=500, chunk_overlap=50)
-    docs = text_splitter.create_documents([text])
+# Create vector store for similarity search
+def create_vectorstore(text: str) -> FAISS:
+    splitter = CharacterTextSplitter(chunk_size=500, chunk_overlap=50)
+    docs = splitter.create_documents([text])
     embeddings = HuggingFaceEmbeddings()
     vectorstore = FAISS.from_documents(docs, embeddings)
     return vectorstore
@@ -94,15 +102,15 @@ 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)
+# Generate speech audio from text
+def generate_voice(text: str, lang='ur') -> str:
+    tts = gTTS(text=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):
+# Generate answer using vectorstore context and LLM
+def get_answer(query: str, vectorstore: FAISS, mode: str) -> str:
     retriever = vectorstore.as_retriever()
     docs = retriever.get_relevant_documents(query)
     context = "\n".join([doc.page_content for doc in docs])
@@ -115,26 +123,24 @@ def get_answer(query, vectorstore, mode):
     answer = llm.invoke(prompt)
     return answer
 
-# Main app logic
+# Main app flow
 if uploaded_file:
     raw_text = extract_text(uploaded_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)
-                answer = get_answer(query, vs, mode)
+                vectorstore = create_vectorstore(raw_text)
+                answer = get_answer(query, vectorstore, 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")
+                        st.audio(audio.read(), format="audio/mp3")
 else:
     st.info("Please paste a Google Drive link to your syllabus file (.pdf or .docx) above.")