Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,6 +1,8 @@
 import streamlit as st
 from PIL import Image
 import requests
+import easyocr
+from io import BytesIO
 
 st.set_page_config(page_title="WikiExplorer AR", layout="centered")
 st.title("📷 WikiExplorer AR (Streamlit Edition)")
@@ -19,13 +21,38 @@ lang = st.selectbox(
 
 lang_code = lang[1]
 
-# --- Place name input ---
-st.markdown("**📝 Enter a place or person name to learn more:**")
+# --- Load OCR Model ---
+@st.cache_resource
+def load_ocr_model():
+    return easyocr.Reader(['en'])  # You can add 'hi', 'te', 'ta' for multilingual OCR
+
+ocr_reader = load_ocr_model()
+
+# --- Place name input (optional if image is provided) ---
+st.markdown("**📝 Enter a place or person name to learn more (or capture it):**")
 place_name = st.text_input("🏛️ For example: Charminar, Taj Mahal, Shah Jahan")
 
 # --- Camera input ---
 img_file_buffer = st.camera_input("📸 Take a picture (optional)")
 
+# --- OCR from camera image ---
+if img_file_buffer is not None:
+    st.markdown("### 📷 Captured Image")
+    st.image(img_file_buffer, caption="Uploaded via camera", use_column_width=True)
+
+    image_bytes = BytesIO(img_file_buffer.getvalue())
+    result = ocr_reader.readtext(image_bytes)
+
+    if result:
+        detected_texts = [item[1] for item in result if item[1].strip()]
+        if detected_texts:
+            place_name = detected_texts[0]  # Top detected phrase
+            st.success(f"🧠 OCR detected: **{place_name}**")
+        else:
+            st.warning("OCR ran but could not extract any meaningful text.")
+    else:
+        st.warning("Could not detect text in the image.")
+
 # --- Translation helpers ---
 def translate_text(text, target_lang):
     try:
@@ -117,17 +144,13 @@ if place_name.strip():
         else:
             st.warning("No images found on Wikimedia Commons.")
 
-# --- Show captured image ---
-if img_file_buffer is not None:
-    st.markdown("### 📷 Captured Image")
-    st.image(img_file_buffer, caption="Uploaded via camera", use_column_width=True)
-
 # --- Footer ---
 st.markdown("""
 ---
 - 📌 Supports text search and camera input.
-- 🌐 Multilingual summaries using Wikipedia REST API with fallback + sentence-level translation.
-- 🖼️ Relevant Commons image gallery.
+- 🧠 OCR auto-detects place name from image.
+- 🌐 Wikipedia multilingual summary with fallback + sentence-level translation.
+- 🖼️ Commons image gallery integration.
 - ✅ Ready for Hugging Face deployment.
-- 🛠️ Built entirely with Streamlit, no backend needed.
-""")
+- 🛠️ Streamlit only — no backend needed.
+""")