Update app.py

app.py

@@ -3,7 +3,7 @@ from huggingface_hub import InferenceClient
 from transformers import AutoModelForCausalLM, pipeline
 
 # Use a pipeline as a high-level helper
-pipe = pipeline("visual-question-answering", model="openbmb/MiniCPM-Llama3-V-2_5", trust_remote_code=True)
+pipe = pipeline("visual-question-answering", model="dandelin/vilt-b32-finetuned-vqa", trust_remote_code=True)
 
 # Load model directly
 model = AutoModelForCausalLM.from_pretrained("microsoft/Florence-2-large", trust_remote_code=True)
@@ -13,14 +13,21 @@ For more information on `huggingface_hub` Inference API support, please check th
 """
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
+def respond(message, history, system_message, max_tokens, temperature, top_p):
+    """
+    Generates a response based on the user message and chat history.
+    
+    Args:
+        message (str): The user message.
+        history (list): A list of tuples containing user and assistant messages.
+        system_message (str): The system message.
+        max_tokens (int): Maximum number of tokens for the response.
+        temperature (float): Temperature for the response generation.
+        top_p (float): Top-p for nucleus sampling.
+    
+    Yields:
+        str: The generated response.
+    """
     messages = [{"role": "system", "content": system_message}]
 
     for val in history:
@@ -41,29 +48,54 @@ def respond(
         top_p=top_p,
     ):
         token = message.choices[0].delta.content
-
         response += token
         yield response
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-
 def process_video(video):
+    """
+    Processes the uploaded video file.
+    
+    Args:
+        video (gr.Video): The uploaded video file.
+    
+    Returns:
+        str: Confirmation message for the uploaded video.
+    """
     return f"Processing video: {video.name}"
 
 def process_pdf(pdf):
+    """
+    Processes the uploaded PDF file.
+    
+    Args:
+        pdf (gr.File): The uploaded PDF file.
+    
+    Returns:
+        str: Confirmation message for the uploaded PDF.
+    """
     return f"Processing PDF: {pdf.name}"
 
 def process_image(image):
+    """
+    Processes the uploaded image file.
+    
+    Args:
+        image (gr.Image): The uploaded image file.
+    
+    Returns:
+        str: Confirmation message for the uploaded image.
+    """
     return f"Processing image: {image.name}"
 
+# Define upload interfaces
 video_upload = gr.Interface(fn=process_video, inputs=gr.Video(), outputs="text", title="Upload a Video")
 pdf_upload = gr.Interface(fn=process_pdf, inputs=gr.File(file_types=['.pdf']), outputs="text", title="Upload a PDF")
 image_upload = gr.Interface(fn=process_image, inputs=gr.Image(), outputs="text", title="Upload an Image")
 
+# Combine upload interfaces into tabs
 tabbed_interface = gr.TabbedInterface([video_upload, pdf_upload, image_upload], ["Video", "PDF", "Image"])
 
+# Main Gradio interface
 demo = gr.Blocks()
 
 with demo:
@@ -73,7 +105,7 @@ with demo:
             additional_inputs=[
                 gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
                 gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-                gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),  # Corrected syntax error here
+                gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
                 gr.Slider(
                     minimum=0.1,
                     maximum=1.0,