Create app.py

app.py

@@ -0,0 +1,86 @@
+import os
+import time
+import gradio as gr
+import google.generativeai as genai
+
+# Configure Gemini API
+genai.configure(api_key=os.environ["GEMINI_API_KEY"])
+
+# Upload files to Gemini
+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
+
+# Wait for files to process
+def wait_for_files_active(files):
+    """Wait until uploaded files are processed and 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(5)
+            file = genai.get_file(name)
+        if file.state.name != "ACTIVE":
+            raise Exception(f"File {file.name} failed to process")
+    print("...all files ready")
+
+# Handle inputs and send a message to Gemini
+def process_inputs(image_path, audio_path, pdf_path, video_path, user_prompt):
+    """Handles user inputs, uploads files to Gemini, and queries the model."""
+    files = []
+
+    # Upload files based on user input
+    if image_path:
+        files.append(upload_to_gemini(image_path, mime_type="image/png"))
+    if audio_path:
+        files.append(upload_to_gemini(audio_path, mime_type="audio/ogg"))
+    if pdf_path:
+        files.append(upload_to_gemini(pdf_path, mime_type="application/pdf"))
+    if video_path:
+        files.append(upload_to_gemini(video_path, mime_type="video/quicktime"))
+
+    # Wait for files to be processed
+    if files:
+        wait_for_files_active(files)
+
+    # Construct conversation history
+    history = []
+    if files:
+        for file in files:
+            history.append({"role": "user", "parts": [file]})
+    if user_prompt:
+        history.append({"role": "user", "parts": [user_prompt]})
+
+    # Start chat and send a message
+    model = genai.GenerativeModel(model_name="gemini-2.0-flash-exp")
+    chat_session = model.start_chat(history=history)
+    response = chat_session.send_message(user_prompt)
+    return response.text
+
+# Gradio Interface
+with gr.Blocks() as demo:
+    gr.Markdown("## Multimodal Gemini AI Chat Interface")
+
+    with gr.Row():
+        image_input = gr.File(label="Upload Image File (PNG)")
+        audio_input = gr.File(label="Upload Audio File (OGG)")
+    with gr.Row():
+        pdf_input = gr.File(label="Upload PDF File")
+        video_input = gr.File(label="Upload Video File (MOV)")
+
+    user_prompt = gr.Textbox(label="Enter Your Prompt", placeholder="Type your question here...")
+
+    submit_button = gr.Button("Submit")
+    output = gr.Textbox(label="Gemini Response")
+
+    submit_button.click(
+        fn=process_inputs,
+        inputs=[image_input, audio_input, pdf_input, video_input, user_prompt],
+        outputs=output
+    )
+
+# Launch Gradio app
+demo.launch()