Update app.py

app.py

@@ -2,9 +2,8 @@ import streamlit as st
 from pypdf import PdfReader
 from docx import Document
 from PIL import Image
-import pytesseract
-from gtts import gTTS
 import tempfile
+from gtts import gTTS
 
 from langchain.vectorstores import FAISS
 from langchain.embeddings import HuggingFaceEmbeddings
@@ -13,106 +12,106 @@ from langchain.prompts import PromptTemplate
 from langchain.llms import HuggingFacePipeline
 from transformers import pipeline
 
-# Setup HuggingFace pipeline
+# Setup LLM pipeline
 text_gen_pipeline = pipeline(
     "text-generation",
     model="distilgpt2",
-    device=-1  # CPU only
+    device=-1  # Use CPU
 )
 llm = HuggingFacePipeline(pipeline=text_gen_pipeline)
 
-# Streamlit page config
+# Streamlit App Config
 st.set_page_config(page_title="Learning with Fun", layout="wide")
-st.title("📘 Learning with Fun - Kids QA App")
+st.title("🌈📘 Learning with Fun 🎓 Kids QA App")
 st.markdown("Ask questions from your syllabus! 📚")
 
-# Sidebar options
+# 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)
 
-# File upload widget
-uploaded_file = st.file_uploader("📁 Upload Syllabus File (.pdf, .docx, .jpg, .jpeg, .png)", type=["pdf", "docx", "jpg", "jpeg", "png"])
+# File Upload
+uploaded_file = st.file_uploader("📂 Upload Syllabus File (PDF, DOCX, JPG, PNG)", type=["pdf", "docx", "jpg", "jpeg", "png"])
 
-# Extract text from file
-def extract_text_from_file(file) -> str:
+# Extract text from PDF/DOCX
+def extract_text(file) -> str:
     text = ""
     if file.name.endswith(".pdf"):
-        with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp_file:
-            tmp_file.write(file.read())
-            reader = PdfReader(tmp_file.name)
+        with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp:
+            tmp.write(file.read())
+            reader = PdfReader(tmp.name)
             for page in reader.pages:
                 page_text = page.extract_text()
                 if page_text:
                     text += page_text
     elif file.name.endswith(".docx"):
-        with tempfile.NamedTemporaryFile(delete=False, suffix=".docx") as tmp_file:
-            tmp_file.write(file.read())
-            doc = Document(tmp_file.name)
+        with tempfile.NamedTemporaryFile(delete=False, suffix=".docx") as tmp:
+            tmp.write(file.read())
+            doc = Document(tmp.name)
             for para in doc.paragraphs:
                 text += para.text + "\n"
-    elif file.name.lower().endswith((".jpg", ".jpeg", ".png")):
-        img = Image.open(file)
-        text = pytesseract.image_to_string(img, lang='eng+urd')
+    elif file.name.endswith((".jpg", ".jpeg", ".png")):
+        st.warning("🖼️ Image uploaded. Text extraction from images is disabled. Showing image only.")
+        image = Image.open(file)
+        st.image(image, caption="Uploaded Image", use_column_width=True)
     else:
         st.error("Unsupported file format.")
     return text
 
-# Create vector DB
+# Vectorstore creation
 def create_vectorstore(text: str) -> FAISS:
     splitter = CharacterTextSplitter(chunk_size=500, chunk_overlap=50)
     docs = splitter.create_documents([text])
     embeddings = HuggingFaceEmbeddings()
     return FAISS.from_documents(docs, embeddings)
 
-# Prompt templates
+# Urdu 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۔"
 )
 
-# Text-to-speech
+# Voice generator
 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
 
-# Answer generation
+# Answer generator
 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])
-
     prompt = story_prompt.format(question=query, context=context) if mode == "📖 Storytelling" else explain_prompt.format(question=query, context=context)
     return llm.invoke(prompt)
 
-# Main logic
+# Main App Logic
 if uploaded_file:
-    raw_text = extract_text_from_file(uploaded_file)
-    if not raw_text.strip():
-        st.error("⚠️ No text found in the uploaded file.")
-    else:
+    raw_text = extract_text(uploaded_file)
+    if raw_text.strip():
         st.success("✅ Syllabus loaded successfully!")
         query = st.text_input("❓ Ask your question (Urdu or English)")
         if query:
             with st.spinner("Thinking..."):
                 vectorstore = create_vectorstore(raw_text)
                 answer = get_answer(query, vectorstore, mode)
-                st.markdown("### 📘 Answer:")
+                st.markdown("### ✅ Answer:")
                 st.write(answer)
 
                 if voice_enabled:
                     audio_file = generate_voice(answer)
                     with open(audio_file, "rb") as audio:
                         st.audio(audio.read(), format="audio/mp3")
+    else:
+        if not uploaded_file.name.endswith((".jpg", ".jpeg", ".png")):
+            st.error("⚠️ Could not extract any text from the file.")
 else:
-    st.info("📂 Please upload your syllabus file to begin.")
+    st.info("📁 Upload your syllabus file (PDF, DOCX, or image) to get started.")