Update app.py

app.py

@@ -1,42 +1,47 @@
+from transformers import AutoModelForCausalLM, AutoTokenizer
 import gradio as gr
-from transformers import pipeline
-
-# Load the hotdog-not-hotdog model
-hotdog_pipeline = pipeline(task="image-classification", model="julien-c/hotdog-not-hotdog")
-
-# Load the chatbot model (DialoGPT)
-chatbot_pipeline = pipeline(task="text-generation", model="microsoft/DialoGPT-medium")
-
-def predict(input_data, option, chat_input=""):
-    if option == "Image Classification":
-        # Predict hotdog or not
-        hotdog_predictions = hotdog_pipeline(input_data)
-        return input_data, {
-            "Hotdog Classification": {p["label"]: p["score"] for p in hotdog_predictions},
-            "Chatbot Response": "",  # Placeholder for chatbot response when not selected
-        }
-    elif option == "Chatbot":
-        # Generate chatbot response
-        chatbot_response = chatbot_pipeline(chat_input, max_length=50)[0]['generated_text']
-        return input_data, {
-            "Hotdog Classification": {},
-            "Chatbot Response": chatbot_response,
-        }
-
-iface = gr.Interface(
+import torch
+
+
+title = "????AI ChatBot"
+description = "A State-of-the-Art Large-scale Pretrained Response generation model (DialoGPT)"
+examples = [["How are you?"]]
+
+
+tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-large")
+model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-large")
+
+
+def predict(input, history=[]):
+    # tokenize the new input sentence
+    new_user_input_ids = tokenizer.encode(
+        input + tokenizer.eos_token, return_tensors="pt"
+    )
+
+    # append the new user input tokens to the chat history
+    bot_input_ids = torch.cat([torch.LongTensor(history), new_user_input_ids], dim=-1)
+
+    # generate a response
+    history = model.generate(
+        bot_input_ids, max_length=4000, pad_token_id=tokenizer.eos_token_id
+    ).tolist()
+
+    # convert the tokens to text, and then split the responses into lines
+    response = tokenizer.decode(history[0]).split("<|endoftext|>")
+    # print('decoded_response-->>'+str(response))
+    response = [
+        (response[i], response[i + 1]) for i in range(0, len(response) - 1, 2)
+    ]  # convert to tuples of list
+    # print('response-->>'+str(response))
+    return response, history
+
+
+gr.Interface(
     fn=predict,
-    inputs=[
-        gr.Image(label="Select hot dog candidate", sources=['upload', 'webcam'], type="pil"),
-        gr.Dropdown(label="Choose Option", choices=["Image Classification", "Chatbot"]),
-        gr.Textbox(label="Chatbot Input", placeholder="Type something to chat with the bot", type="text"),
-    ],
-    outputs=[
-        gr.Image(label="Processed Image"),
-        gr.Label(label="Hotdog Classification", num_top_classes=2),
-        gr.Textbox(label="Chatbot Response", type="text"),
-    ],
-    title="Hot Dog? Or Chat with the Bot?",
-)
-
-if __name__ == "__main__":
-    iface.launch()
+    title=title,
+    description=description,
+    examples=examples,
+    inputs=["text", "state"],
+    outputs=["chatbot", "state"],
+    theme="finlaymacklon/boxy_violet",
+).launch()