Update app.py

app.py

@@ -10,29 +10,27 @@ from langchain.embeddings import HuggingFaceEmbeddings
 from langchain.text_splitter import CharacterTextSplitter
 from langchain_core.prompts import PromptTemplate
 from transformers import pipeline
-from langchain.chains import RetrievalQA
 from langchain.llms import HuggingFacePipeline
 
-# Set up HuggingFace text-generation pipeline (you can change the model)
+# Setup HuggingFace text generation pipeline (replace model with your choice)
 text_gen_pipeline = pipeline(
     "text-generation",
-    model="gpt2",  # Small model for demo; replace with your preferred model
+    model="gpt2",  # lightweight model for demo, swap for bigger model as needed
     max_length=150
 )
 llm = HuggingFacePipeline(pipeline=text_gen_pipeline)
 
-# App UI
+# Streamlit UI setup
 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 controls
+# Sidebar options
 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)
 
-# Fetch file from Google Drive
 def fetch_from_gdrive(link):
     file_id = None
     if "id=" in link:
@@ -60,7 +58,6 @@ 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"):
@@ -75,7 +72,6 @@ def extract_text(file_path):
             text += para.text + "\n"
     return text
 
-# Create vectorstore for retrieval
 def create_vectorstore(text):
     splitter = CharacterTextSplitter(chunk_size=500, chunk_overlap=50)
     docs = splitter.create_documents([text])
@@ -83,37 +79,32 @@ def create_vectorstore(text):
     vectorstore = FAISS.from_documents(docs, embeddings)
     return vectorstore
 
-# Prompts
 story_prompt = PromptTemplate.from_template(
     "ایک طالب علم نے سوال کیا: {question}\n"
     "نصاب کی معلومات: {context}\n"
     "برائے مہربانی ایک دلچسپ کہانی کی صورت میں بچے کو اردو میں جواب دیں۔"
 )
+
 explain_prompt = PromptTemplate.from_template(
     "سوال: {question}\n"
     "نصاب کا سیاق و سباق: {context}\n"
     "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
 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)
-    # Use LLM pipeline to generate answer text
-    response = llm.invoke(prompt)
-    # llm.invoke returns a string answer
-    return response
+    answer = llm.invoke(prompt)
+    return answer
 
-# Main app flow
 if uploaded_file:
     raw_text = extract_text(uploaded_file)
     st.success("📄 Syllabus loaded successfully!")