Update app.py

app.py

@@ -1,11 +1,77 @@
+# import gradio as gr
+# from huggingface_hub import InferenceClient
+
+# """
+# For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
+# """
+# client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+
+
+# def respond(
+#     message,
+#     history: list[tuple[str, str]],
+#     system_message,
+#     max_tokens,
+#     temperature,
+#     top_p,
+# ):
+#     messages = [{"role": "system", "content": system_message}]
+
+#     for val in history:
+#         if val[0]:
+#             messages.append({"role": "user", "content": val[0]})
+#         if val[1]:
+#             messages.append({"role": "assistant", "content": val[1]})
+
+#     messages.append({"role": "user", "content": message})
+
+#     response = ""
+
+#     for message in client.chat_completion(
+#         messages,
+#         max_tokens=max_tokens,
+#         stream=True,
+#         temperature=temperature,
+#         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
+# """
+# demo = gr.ChatInterface(
+#     respond,
+#     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"),
+#         gr.Slider(
+#             minimum=0.1,
+#             maximum=1.0,
+#             value=0.95,
+#             step=0.05,
+#             label="Top-p (nucleus sampling)",
+#         ),
+#     ],
+# )
+
+
+# if __name__ == "__main__":
+#     demo.launch()
+
 import gradio as gr
 from huggingface_hub import InferenceClient
+from PIL import Image
+import io
 
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
+client = InferenceClient("meta-llama/Llama-3.2-11B-Vision-Instruct")
 
 def respond(
     message,
@@ -14,7 +80,9 @@ def respond(
     max_tokens,
     temperature,
     top_p,
+    image: Image
 ):
+    # Prepare messages
     messages = [{"role": "system", "content": system_message}]
 
     for val in history:
@@ -25,24 +93,27 @@ def respond(
 
     messages.append({"role": "user", "content": message})
 
+    # Convert the image to bytes for HuggingFace API processing
+    image_bytes = io.BytesIO()
+    image.save(image_bytes, format='PNG')
+    image_bytes.seek(0)
+
+    # Make the API call with the image and messages
     response = ""
 
-    for message in client.chat_completion(
+    for result in client.chat_completion(
         messages,
+        image=image_bytes,
         max_tokens=max_tokens,
         stream=True,
         temperature=temperature,
         top_p=top_p,
     ):
-        token = message.choices[0].delta.content
-
+        token = result.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
-"""
+# Gradio demo for ChatInterface with image support
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -56,9 +127,10 @@ demo = gr.ChatInterface(
             step=0.05,
             label="Top-p (nucleus sampling)",
         ),
+        gr.Image(type="pil", label="Upload an Image"),  # Image input for vision tasks
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()
+