Update app.py

app.py

@@ -7,7 +7,21 @@ import numpy as np
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
 from io import StringIO
-import pytesseract
+import easyocr
+
+# Function to extract text from image using EasyOCR
+def extract_text_from_image(image):
+    # Initialize EasyOCR reader
+    reader = easyocr.Reader(['en'])  # Specify language(s); you can add more like ['en', 'fr'] for multiple languages
+    
+    # Read text from the image
+    result = reader.readtext(image)
+    
+    # Extract and concatenate the text from the OCR result
+    text = ' '.join([item[1] for item in result])  # item[1] contains the recognized text
+    
+    return text
+
 # Function to extract text from a PDF file
 def extract_text_from_pdf(pdf_file):
     reader = PyPDF2.PdfReader(pdf_file)
@@ -67,12 +81,6 @@ def generate_math_solution(query):
     )
     return response['choices'][0]['message']['content']
 
-# Function to extract text from image using OCR
-def extract_text_from_image(image):
-    # Use pytesseract to do OCR on the image and extract text
-    text = pytesseract.image_to_string(image)
-    return text
-
 # Function to answer questions based on the image or its content
 def answer_question_based_on_image(query, image_text):
     prompt = f"The following is text extracted from an image: {image_text}\n\nQuestion: {query}\n\nAnswer the question based on the image text."
@@ -81,7 +89,7 @@ def answer_question_based_on_image(query, image_text):
         messages=[{"role": "user", "content": prompt}]
     )
     return response['choices'][0]['message']['content']
-
+    
 from PIL import Image  # Required for local image files
 
 # Streamlit app starts here
@@ -402,28 +410,28 @@ if openai_api_key:
 
         # Image upload feature
         uploaded_image = st.file_uploader("Upload an image:", type=["jpg", "jpeg", "png"])
-    
+
         if uploaded_image:
             # Open the image with PIL
             image = Image.open(uploaded_image)
-    
+
             # Display the uploaded image
             st.image(image, caption="Uploaded Image", use_column_width=True)
-    
-            # Extract text from the image using OCR
+
+            # Extract text from the image using EasyOCR
             with st.spinner("Extracting text from the image..."):
                 image_text = extract_text_from_image(image)
-    
+
             # Show the extracted text
             if image_text:
                 st.write("### Extracted Text from Image:")
                 st.write(image_text)
             else:
                 st.write("No text was extracted from the image.")
-    
+
             # Allow the user to ask questions about the image
             question = st.text_input("Ask a question about the image:")
-    
+
             if question:
                 with st.spinner("Getting answer..."):
                     answer = answer_question_based_on_image(question, image_text)