Update app.py

app.py

@@ -6,14 +6,27 @@ import fitz  # PyMuPDF
 import io
 import requests
 import re
+import numpy as np
 from fpdf import FPDF
 from datetime import datetime
+import os
 
 # --- Config ---
 API_URL = "https://openrouter.ai/api/v1/chat/completions"
 API_KEY = "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"
 MODEL = "mistralai/mistral-7b-instruct"
 
+# Set Tesseract path for different environments
+try:
+    # For Windows
+    if os.name == 'nt':
+        pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe'
+    # For Linux (Streamlit Sharing)
+    elif 'tesseract' not in os.environ.get('PATH', ''):
+        pytesseract.pytesseract.tesseract_cmd = '/usr/bin/tesseract'
+except Exception as e:
+    st.warning(f"Tesseract configuration issue: {str(e)}")
+
 # Set page config
 st.set_page_config(
     page_title="🔬 Science Lab Assistant", 
@@ -104,6 +117,13 @@ st.markdown("""
         color: #7f8c8d;
         font-size: 14px;
     }
+    .ocr-warning {
+        background-color: #fef9e7;
+        border-left: 5px solid #f1c40f;
+        padding: 15px;
+        margin: 15px 0;
+        border-radius: 0 8px 8px 0;
+    }
     </style>
     """, unsafe_allow_html=True)
 
@@ -179,6 +199,8 @@ with st.sidebar:
             ai_response = query_ai(f"Explain the term '{term}' in simple words for a student.")
         if ai_response:
             st.markdown(f"<div class='concept-box'>{ai_response}</div>", unsafe_allow_html=True)
+        else:
+            st.warning("Couldn't retrieve definition. Please try again.")
 
 # --- Experiment Assistant Section ---
 if app_mode == "🧪 Experiment Assistant":
@@ -348,17 +370,48 @@ else:
         file_ext = uploaded_file.name.split(".")[-1].lower()
 
         if file_ext == "pdf":
-            doc = fitz.open(stream=file_bytes, filetype="pdf")
-            for page in doc:
-                lab_text += page.get_text()
+            try:
+                doc = fitz.open(stream=file_bytes, filetype="pdf")
+                for page in doc:
+                    lab_text += page.get_text()
+                st.success("✅ PDF text extracted successfully!")
+            except Exception as e:
+                st.error(f"Error reading PDF: {str(e)}")
         else:
-            image = Image.open(io.BytesIO(file_bytes))
-            lab_text = pytesseract.image_to_string(image)
+            try:
+                image = Image.open(io.BytesIO(file_bytes))
+                st.image(image, caption="Uploaded Image", width=300)
+                
+                # OCR processing
+                with st.spinner("Extracting text from image..."):
+                    try:
+                        lab_text = pytesseract.image_to_string(image)
+                        st.success("✅ Text extracted from image!")
+                    except pytesseract.pytesseract.TesseractNotFoundError:
+                        st.error("""
+                        **Tesseract OCR not found!** 
+                        
+                        To enable image text extraction:
+                        1. Install Tesseract OCR on your system
+                        2. Add it to your system PATH
+                        3. Restart the application
+                        
+                        For Windows: Download from [UB-Mannheim/tesseract](https://github.com/UB-Mannheim/tesseract/wiki)
+                        For Linux: `sudo apt install tesseract-ocr`
+                        For Mac: `brew install tesseract`
+                        """)
+                        st.stop()
+                    except Exception as e:
+                        st.error(f"OCR Error: {str(e)}")
+                        st.stop()
+            except Exception as e:
+                st.error(f"Error processing image: {str(e)}")
 
         # Allow text editing
-        st.markdown('<p class="subheader">✍️ Extracted Text</p>', unsafe_allow_html=True)
-        st.caption("Review and edit the extracted text if needed before analysis")
-        lab_text = st.text_area("", lab_text, height=300, label_visibility="collapsed")
+        if lab_text:
+            st.markdown('<p class="subheader">✍️ Extracted Text</p>', unsafe_allow_html=True)
+            st.caption("Review and edit the extracted text if needed before analysis")
+            lab_text = st.text_area("", lab_text, height=300, label_visibility="collapsed")
 
     # --- AI Evaluation ---
     if lab_text.strip():