Create app.py

app.py

@@ -0,0 +1,81 @@
+import streamlit as st
+from PIL import Image
+import os
+from helper import (
+    resize_image, convert_image_to_base64, post_request_and_parse_response, 
+    draw_bounding_boxes_for_textract, extract_text_from_textract_blocks, ChatGPTClient
+)
+
+# Load OpenAI API Key from environment variable
+OPENAI_API_KEY = os.environ["OPENAI_API_KEY"]
+TEXTRACT_API_URL = "https://2tsig211e0.execute-api.us-east-1.amazonaws.com/my_textract"
+
+st.set_page_config(page_title="Chat with OCR", layout="wide")
+
+# Initialize chat history if not in session state
+if "messages" not in st.session_state:
+    st.session_state.messages = []
+
+# Sidebar for image upload
+with st.sidebar:
+    st.title("Upload and Display Images")
+    uploaded_image = st.file_uploader("Upload an Image", type=["png", "jpg", "jpeg"])
+    
+    if uploaded_image:
+        pil_image = Image.open(uploaded_image)
+        resized_image = resize_image(pil_image)
+
+        with st.expander("Original Image", expanded=False):
+            st.image(pil_image, caption="Uploaded Image", use_column_width=True)
+        
+        # Convert image to base64 and send to Textract API
+        image_base64 = convert_image_to_base64(resized_image)
+        payload = {"image": image_base64}
+        result_dict = post_request_and_parse_response(TEXTRACT_API_URL, payload)
+        
+        # Draw bounding boxes
+        image_with_boxes = draw_bounding_boxes_for_textract(resized_image.copy(), result_dict)
+        
+        with st.expander("Image with Bounding Boxes", expanded=True):
+            st.image(image_with_boxes, caption="Image with Bounding Boxes", use_column_width=True)
+        
+        # Extract text from Textract
+        cleaned_up_body = extract_text_from_textract_blocks(result_dict['body'])
+
+# Main chat interface
+st.title("Chat with OCR Output")
+
+# Display previous messages from session state
+for message in st.session_state.messages:
+    with st.chat_message(message["role"]):
+        st.markdown(message["content"])
+
+# Initialize ChatGPTClient with session state history
+if uploaded_image:
+    history_copy = st.session_state.messages.copy()
+
+    if cleaned_up_body:
+        history_copy.append({"role": "system", "content": cleaned_up_body})
+
+    bot = ChatGPTClient(
+        api_key=OPENAI_API_KEY,
+        protocol="You are fed with the text portion of json file that come out of OCR after scanning an image. User will ask you questions about this json file.",
+        body=cleaned_up_body
+    )
+    bot.history = history_copy  # Set ChatGPT history to session state messages
+
+# React to user input
+if prompt := st.chat_input("Ask me about the image"):
+    # Display user message in chat container
+    st.chat_message("user").markdown(prompt)
+    st.session_state.messages.append({"role": "user", "content": prompt})
+
+    # Generate a response using ChatGPTClient
+    if uploaded_image:
+        response = bot.generate_response(prompt)
+    else:
+        response = "Please upload an image before asking questions."
+
+    # Display assistant message in chat container
+    st.chat_message("assistant").markdown(response)
+    st.session_state.messages.append({"role": "assistant", "content": response})