Update app.py

app.py

@@ -8,7 +8,9 @@ import google.generativeai as genai
 
 genai.configure(api_key='AIzaSyCeNgXfZx0kJ736XFVtxXxev_RdscB0i5s')
 
-def get_gemini_response(input, image,prompt):
+## Function to load OpenAI model and get respones
+
+def get_gemini_response(input,image,prompt):
     model = genai.GenerativeModel('gemini-pro-vision')
     response = model.generate_content([input,image[0],prompt])
     return response.text
@@ -17,12 +19,12 @@ def get_gemini_response(input, image,prompt):
 def input_image_setup(uploaded_file):
     # Check if a file has been uploaded
     if uploaded_file is not None:
-        
+        # Read the file into bytes
         bytes_data = uploaded_file.getvalue()
 
         image_parts = [
             {
-                "mime_type": uploaded_file.type,  
+                "mime_type": uploaded_file.type,  # Get the mime type of the uploaded file
                 "data": bytes_data
             }
         ]
@@ -31,33 +33,32 @@ def input_image_setup(uploaded_file):
         raise FileNotFoundError("No file uploaded")
 
 
-##streamlit app
+##initialize our streamlit app
 
 st.set_page_config(page_title="Gemini Image Demo")
 
-st.header("Generative AI : Business Card Reader")
+st.header("Generative AI : Business card Reader")
+input=st.text_input("Input Prompt: ",key="input")
 uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
 image=""  
 if uploaded_file is not None:
     image = Image.open(uploaded_file)
     st.image(image, caption="Uploaded Image.", use_column_width=True)
-    input=st.text_input("Input Prompt (optional) : ",key="input")
 
 
 submit=st.button("Submit")
 
 input_prompt = """
                You are an expert in understanding business cards.
-               Input: Image of a business card
-               Task: Extract and label the following information in JSON format if available:
-               Labels : company_name, person_name, occupation, contact_number, email addresse, website, address, other_details (services, features, etc.)
-               Constraints: Do not include missing information.
+               You will receive input images of business card & you will have to answer questions based on the input image.
+               You have to extract information from business card images and give correct tag to the output text 
+               like person name, company name, occupation, address, telephone number, mobile number, email, website, etc. Give output in json format.
                """
 
+## If ask button is clicked
+
 if submit:
     image_data = input_image_setup(uploaded_file)
-    response=get_gemini_response(input_prompt,image_data, input)
+    response=get_gemini_response(input_prompt,image_data,input)
     st.subheader("Output :")
-    st.write(response)
-
-examples = ['examples/Business_card.jpg', 'examples/Business_card10.jpg']
+    st.write(response)