Update vision.py

vision.py

@@ -1,61 +1,89 @@
-import os
-import time
-from PIL import Image
-import streamlit as st
-import google.generativeai as genai
-
-# Load environment variables
-from dotenv import load_dotenv
-load_dotenv()
-
-# Configure the Google AI Python SDK
-genai.configure(api_key=os.getenv("GEMINI_API_KEY"))
-
-def upload_to_gemini(path, mime_type=None):
-    """Uploads the given file to Gemini."""
-    file = genai.upload_file(path, mime_type=mime_type)
-    # print(f"Uploaded file '{file.display_name}' as: {file.uri}")
-    return file
-
-def wait_for_files_active(files):
-    """Waits for the given files to be active."""
-    # print("Waiting for file processing...")
-    for name in (file.name for file in files):
-        file = genai.get_file(name)
-        while file.state.name == "PROCESSING":
-            print(".", end="", flush=True)
-            time.sleep(10)
-            file = genai.get_file(name)
-        if file.state.name != "ACTIVE":
-            raise Exception(f"File {file.name} failed to process")
-    # print("...all files ready")
-    # print()
-
-def get_gemini_response(input, image):
-    context = """Generates a response based on the image and input prompt."""
-    model = genai.GenerativeModel('gemini-pro-vision')
-    if input != "":
-        input += context
-        response = model.generate_content([input, image])
-    else:
-        response = model.generate_content(image)
-    return response.text
-
-def visoto():
-    """Main function to run the Streamlit app."""
-    st.title = "Gemini Image Demo"
-    st.header ="Image Chat Assistant" 
-    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)
-    submit = st.button("Tell me about the image")
-    if submit:
-        response = get_gemini_response(input, image)
-        st.subheader("The Response is")
-        st.write(response)
-
-# if __name__ == "__main__":
-#     main()
+import os
+import time
+from PIL import Image
+import streamlit as st
+import google.generativeai as genai
+
+# Load environment variables
+from dotenv import load_dotenv
+load_dotenv()
+
+# Configure the Google AI Python SDK
+genai.configure(api_key=os.getenv("GEMINI_API_KEY"))
+
+def upload_to_gemini(path, mime_type=None):
+    """Uploads the given file to Gemini."""
+    file = genai.upload_file(path, mime_type=mime_type)
+    return file
+
+def wait_for_files_active(files):
+    """Waits for the given files to be active."""
+    for name in (file.name for file in files):
+        file = genai.get_file(name)
+        while file.state.name == "PROCESSING":
+            print(".", end="", flush=True)
+            time.sleep(10)
+            file = genai.get_file(name)
+        if file.state.name != "ACTIVE":
+            raise Exception(f"File {file.name} failed to process")
+
+def get_gemini_response(input, images):
+    context = """Generates a response based on the images and input prompt."""
+    model = genai.GenerativeModel('gemini-pro-vision')
+    responses = []
+    for image in images:
+        if input != "":
+            input += context
+            response = model.generate_content([input, image])
+        else:
+            response = model.generate_content(image)
+        
+        # Use result.parts to access the response parts
+        for part in response.parts:
+            if part.text:
+                responses.append(part.text)
+    return responses
+
+def visoto():
+    """Main function to run the Streamlit app."""
+    st.title= "Gemini Image Demo"
+    st.header= "Image Chat Assistant"
+    
+    input = st.text_input("Input Prompt: ", key="input")
+    
+    # State variable to control camera input visibility
+    if 'camera_open' not in st.session_state:
+        st.session_state.camera_open = False
+    
+    if st.button("Open Camera"):
+        st.session_state.camera_open = True
+    
+    if st.button("Close Camera"):
+        st.session_state.camera_open = False
+    
+    camera_image = None
+    if st.session_state.camera_open:
+        camera_image = st.camera_input("Capture an image")
+    
+    uploaded_files = st.file_uploader("Choose images...", type=["jpg", "jpeg", "png"], accept_multiple_files=True)
+    images = []
+    
+    if camera_image is not None:
+        images.append(Image.open(camera_image))
+        st.image(images[-1], caption="Captured Image.", use_column_width=True)
+    
+    if uploaded_files is not None:
+        for uploaded_file in uploaded_files:
+            image = Image.open(uploaded_file)
+            images.append(image)
+            st.image(image, caption="Uploaded Image.", use_column_width=True)
+    
+    submit = st.button("Tell me about the images")
+    if submit and images:
+        responses = get_gemini_response(input, images)
+        st.subheader("The Responses are")
+        for response in responses:
+            st.write(response)
+
+if __name__ == "__main__":
+    visoto()