Update app.py

app.py

@@ -1,45 +1,46 @@
 import streamlit as st
 from pypdf import PdfReader
 from docx import Document
-from PIL import Image
 import requests
 import os
 import tempfile
-import base64
 from gtts import gTTS
 from langchain.vectorstores import FAISS
 from langchain.embeddings import HuggingFaceEmbeddings
 from langchain.text_splitter import CharacterTextSplitter
-from langchain_core.documents import Document as LCDocument
-from langchain_core.runnables import RunnableLambda, RunnablePassthrough
 from langchain_core.prompts import PromptTemplate
-from langchain_community.llms import Groq
+from transformers import pipeline
 from langchain.chains import RetrievalQA
+from langchain.llms import HuggingFacePipeline
 
-# GROQ API setup
-groq_api_key = st.secrets["GROQ_API_KEY"] if "GROQ_API_KEY" in st.secrets else os.getenv("GROQ_API_KEY")
-llm = Groq(temperature=0.3, model_name="llama3-8b-8192", groq_api_key=groq_api_key)
+# Set up HuggingFace text-generation pipeline (you can change the model)
+text_gen_pipeline = pipeline(
+    "text-generation",
+    model="gpt2",  # Small model for demo; replace with your preferred model
+    max_length=150
+)
+llm = HuggingFacePipeline(pipeline=text_gen_pipeline)
 
 # 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
+# Sidebar controls
 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
+# Fetch file from Google Drive
 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]
-    else:
+    if not file_id:
         return None
-
     url = f"https://drive.google.com/uc?export=download&id={file_id}"
     response = requests.get(url)
     if response.status_code == 200:
@@ -59,7 +60,7 @@ if file_link:
     else:
         st.error("Invalid Google Drive link or download error.")
 
-# Extract text
+# Extract text from PDF or DOCX
 def extract_text(file_path):
     text = ""
     if file_path.endswith(".pdf"):
@@ -74,53 +75,48 @@ def extract_text(file_path):
             text += para.text + "\n"
     return text
 
-# Embeddings + Vectorstore
+# Create vectorstore for retrieval
 def create_vectorstore(text):
-    text_splitter = CharacterTextSplitter(chunk_size=500, chunk_overlap=50)
-    docs = text_splitter.create_documents([text])
+    splitter = CharacterTextSplitter(chunk_size=500, chunk_overlap=50)
+    docs = splitter.create_documents([text])
     embeddings = HuggingFaceEmbeddings()
     vectorstore = FAISS.from_documents(docs, embeddings)
     return vectorstore
 
-# Prompt templates
+# 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۔"
 )
 
-# TTS
+# 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
 
-# QA pipeline
+# 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
 
-    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 logic
+# Main app flow
 if uploaded_file:
     raw_text = extract_text(uploaded_file)
     st.success("📄 Syllabus loaded successfully!")
-
     query = st.text_input("❓ Ask your question (Urdu or English)")
     if query:
         with st.spinner("Thinking..."):
@@ -128,11 +124,9 @@ if uploaded_file:
             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")
+                with open(audio_file, "rb") as f:
+                    st.audio(f.read(), format="audio/mp3")
 else:
     st.info("Please paste a valid Google Drive link to load your syllabus file.")