Update app.py

app.py

@@ -1,22 +1,19 @@
 import streamlit as st
 from pypdf import PdfReader
 from docx import Document
-import tempfile
-import requests
-from gtts import gTTS
-
 from PIL import Image
+import pytesseract
+from gtts import gTTS
+import tempfile
 
 from langchain.vectorstores import FAISS
 from langchain.embeddings import HuggingFaceEmbeddings
 from langchain.text_splitter import CharacterTextSplitter
 from langchain.prompts import PromptTemplate
 from langchain.llms import HuggingFacePipeline
-
 from transformers import pipeline
 
-
-# Setup HuggingFace pipeline with distilgpt2 (CPU)
+# Setup HuggingFace pipeline
 text_gen_pipeline = pipeline(
     "text-generation",
     model="distilgpt2",
@@ -24,70 +21,50 @@ text_gen_pipeline = pipeline(
 )
 llm = HuggingFacePipeline(pipeline=text_gen_pipeline)
 
-# Streamlit app config
+# Streamlit page 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 widgets
+# 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 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].split("&")[0]
-    elif "/d/" in link:
-        file_id = link.split("/d/")[1].split("/")[0]
-    if not file_id:
-        return None
+# File upload widget
+uploaded_file = st.file_uploader("📁 Upload Syllabus File (.pdf, .docx, .jpg, .jpeg, .png)", type=["pdf", "docx", "jpg", "jpeg", "png"])
 
-    url = f"https://drive.google.com/uc?export=download&id={file_id}"
-    response = requests.get(url)
-    if response.status_code == 200:
-        tmp_file = tempfile.NamedTemporaryFile(delete=False)
-        tmp_file.write(response.content)
-        tmp_file.close()
-        return tmp_file.name
-    return None
-
-uploaded_file = None
-file_link = st.text_input("Paste Google Drive Link to Syllabus File (.pdf or .docx)")
-
-if file_link:
-    filepath = fetch_from_gdrive(file_link)
-    if filepath:
-        uploaded_file = filepath
-    else:
-        st.error("Invalid Google Drive link or download error.")
-
-# Extract text content from uploaded file
-def extract_text(file_path: str) -> str:
+# Extract text from file
+def extract_text_from_file(file) -> str:
     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
-    elif file_path.endswith(".docx"):
-        doc = Document(file_path)
-        for para in doc.paragraphs:
-            text += para.text + "\n"
+    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)
+            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)
+            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')
     else:
-        st.error("Unsupported file format. Please upload a PDF or DOCX file.")
+        st.error("Unsupported file format.")
     return text
 
-# Create vector store for similarity search
+# Create vector DB
 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
+    return FAISS.from_documents(docs, embeddings)
 
 # Prompt templates
 story_prompt = PromptTemplate.from_template(
@@ -102,40 +79,35 @@ explain_prompt = PromptTemplate.from_template(
     "براہ کرم بچے کو اردو زبان میں آسان انداز میں سمجھائیں۔"
 )
 
-# Generate speech audio from text
+# Text-to-speech
 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
 
-# Generate answer using vectorstore context and LLM
+# Answer generation
 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])
 
-    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
+    prompt = story_prompt.format(question=query, context=context) if mode == "📖 Storytelling" else explain_prompt.format(question=query, context=context)
+    return llm.invoke(prompt)
 
-# Main app flow
+# Main logic
 if uploaded_file:
-    raw_text = extract_text(uploaded_file)
+    raw_text = extract_text_from_file(uploaded_file)
     if not raw_text.strip():
-        st.error("No text extracted from the file. Please check the file content.")
+        st.error("⚠️ No text found in the uploaded file.")
     else:
-        st.success("📄 Syllabus loaded successfully!")
+        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:
@@ -143,4 +115,4 @@ if uploaded_file:
                     with open(audio_file, "rb") as audio:
                         st.audio(audio.read(), format="audio/mp3")
 else:
-    st.info("Please paste a Google Drive link to your syllabus file (.pdf or .docx) above.")
+    st.info("📂 Please upload your syllabus file to begin.")