Create app.py

app.py

@@ -0,0 +1,54 @@
+import gradio as gr
+from huggingface_hub import InferenceClient
+import os
+
+hf_key = os.getenv("HF_KEY").strip()
+# Initialize the Hugging Face client
+client = InferenceClient(api_key=hf_key)
+
+# Define the chatbot function
+def chat_with_model(text, image=None):
+    messages = [{"role": "user", "content": {"type": "text", "text": text}}]
+    
+    # If an image is uploaded, encode it and send it as part of the payload
+    if image:
+        import base64
+        from PIL import Image
+        from io import BytesIO
+
+        # Convert image to base64
+        buffered = BytesIO()
+        image.save(buffered, format="PNG")
+        img_str = base64.b64encode(buffered.getvalue()).decode("utf-8")
+
+        # Add the image content to the messages
+        messages.append({
+            "role": "user",
+            "content": {
+                "type": "image_base64",
+                "image_base64": img_str
+            }
+        })
+    
+    # Get response from the model
+    response = client.chat.completions.create(
+        model="meta-llama/Llama-3.2-11B-Vision-Instruct",
+        messages=messages,
+        max_tokens=500
+    )
+    
+    return response.choices[0].message["content"]
+
+# Create the Gradio interface
+ui = gr.Interface(
+    fn=chat_with_model,
+    inputs=[
+        gr.Textbox(label="Enter your message"),
+        gr.Image(type="pil", label="Upload an Image (Optional)")
+    ],
+    outputs=gr.Textbox(label="Response from the chatbot"),
+    title="AI Chatbot with Direct Image Upload"
+)
+
+# Launch the UI
+ui.launch()