Fixes chatbot_dialogpt demo (#4238)

* demo fix

* changelog

* fix

* demo

---------

Co-authored-by: Abubakar Abid <abubakar@huggingface.co>

CHANGELOG.md

@@ -33,6 +33,7 @@ No changes to highlight.
 - Fix "TypeError: issubclass() arg 1 must be a class" When use Optional[Types] by [@lingfengchencn](https://github.com/lingfengchencn) in [PR 4200](https://github.com/gradio-app/gradio/pull/4200). 
 - Ensure cancelling functions work correctly by [@pngwn](https://github.com/pngwn) in [PR 4225](https://github.com/gradio-app/gradio/pull/4225)
 - Fixes a bug with typing.get_type_hints() on Python 3.9 by [@abidlabs](https://github.com/abidlabs) in [PR 4228](https://github.com/gradio-app/gradio/pull/4228).
+- Fix `chatbot_dialogpt` demo by [@dawoodkhan82](https://github.com/dawoodkhan82) in [PR 4238](https://github.com/gradio-app/gradio/pull/4238).
 
 ## Other Changes:
 

demo/chatbot_dialogpt/run.ipynb

@@ -1 +1 @@
-{"cells": [{"cell_type": "markdown", "id": 302934307671667531413257853548643485645, "metadata": {}, "source": ["# Gradio Demo: chatbot_dialogpt"]}, {"cell_type": "code", "execution_count": null, "id": 272996653310673477252411125948039410165, "metadata": {}, "outputs": [], "source": ["!pip install -q gradio "]}, {"cell_type": "code", "execution_count": null, "id": 288918539441861185822528903084949547379, "metadata": {}, "outputs": [], "source": ["import gradio as gr\n", "from transformers import AutoModelForCausalLM, AutoTokenizer\n", "import torch\n", "\n", "tokenizer = AutoTokenizer.from_pretrained(\"microsoft/DialoGPT-medium\")\n", "model = AutoModelForCausalLM.from_pretrained(\"microsoft/DialoGPT-medium\")\n", "\n", "def user(message, history):\n", "    return \"\", history + [[message, None]]\n", "\n", "\n", "#     bot_message = random.choice([\"Yes\", \"No\"])\n", "#     history[-1][1] = bot_message\n", "#     time.sleep(1)\n", "#     return history\n", "\n", "# def predict(input, history=[]):\n", "#     # tokenize the new input sentence\n", "\n", "def bot(history):\n", "    user_message = history[-1][0]\n", "    new_user_input_ids = tokenizer.encode(user_message + tokenizer.eos_token, return_tensors='pt')\n", "\n", "    # append the new user input tokens to the chat history\n", "    bot_input_ids = torch.cat([torch.LongTensor(history), new_user_input_ids], dim=-1)\n", "\n", "    # generate a response \n", "    history = model.generate(bot_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id).tolist()\n", "\n", "    # convert the tokens to text, and then split the responses into lines\n", "    response = tokenizer.decode(history[0]).split(\"<|endoftext|>\")\n", "    response = [(response[i], response[i+1]) for i in range(0, len(response)-1, 2)]  # convert to tuples of list\n", "    return history\n", "\n", "with gr.Blocks() as demo:\n", "    chatbot = gr.Chatbot()\n", "    msg = gr.Textbox()\n", "    clear = gr.Button(\"Clear\")\n", "\n", "    msg.submit(user, [msg, chatbot], [msg, chatbot], queue=False).then(\n", "        bot, chatbot, chatbot\n", "    )\n", "    clear.click(lambda: None, None, chatbot, queue=False)\n", "\n", "if __name__ == \"__main__\":\n", "    demo.launch()\n"]}], "metadata": {}, "nbformat": 4, "nbformat_minor": 5}
+{"cells": [{"cell_type": "markdown", "id": 302934307671667531413257853548643485645, "metadata": {}, "source": ["# Gradio Demo: chatbot_dialogpt"]}, {"cell_type": "code", "execution_count": null, "id": 272996653310673477252411125948039410165, "metadata": {}, "outputs": [], "source": ["!pip install -q gradio "]}, {"cell_type": "code", "execution_count": null, "id": 288918539441861185822528903084949547379, "metadata": {}, "outputs": [], "source": ["import gradio as gr\n", "from transformers import AutoModelForCausalLM, AutoTokenizer\n", "import torch\n", "\n", "tokenizer = AutoTokenizer.from_pretrained(\"microsoft/DialoGPT-medium\")\n", "model = AutoModelForCausalLM.from_pretrained(\"microsoft/DialoGPT-medium\")\n", "\n", "\n", "def user(message, history):\n", "    return \"\", history + [[message, None]]\n", "\n", "\n", "def bot(history):\n", "    user_message = history[-1][0]\n", "    new_user_input_ids = tokenizer.encode(\n", "        user_message + tokenizer.eos_token, return_tensors=\"pt\"\n", "    )\n", "\n", "    # append the new user input tokens to the chat history\n", "    bot_input_ids = torch.cat([torch.LongTensor([]), new_user_input_ids], dim=-1)\n", "\n", "    # generate a response\n", "    response = model.generate(\n", "        bot_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id\n", "    ).tolist()\n", "\n", "    # convert the tokens to text, and then split the responses into lines\n", "    response = tokenizer.decode(response[0]).split(\"<|endoftext|>\")\n", "    response = [\n", "        (response[i], response[i + 1]) for i in range(0, len(response) - 1, 2)\n", "    ]  # convert to tuples of list\n", "    history[-1] = response[0]\n", "    return history\n", "\n", "\n", "with gr.Blocks() as demo:\n", "    chatbot = gr.Chatbot()\n", "    msg = gr.Textbox()\n", "    clear = gr.Button(\"Clear\")\n", "\n", "    msg.submit(user, [msg, chatbot], [msg, chatbot], queue=False).then(\n", "        bot, chatbot, chatbot\n", "    )\n", "    clear.click(lambda: None, None, chatbot, queue=False)\n", "\n", "if __name__ == \"__main__\":\n", "    demo.launch()\n"]}], "metadata": {}, "nbformat": 4, "nbformat_minor": 5}

demo/chatbot_dialogpt/run.py

@@ -5,33 +5,34 @@ import torch
 tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-medium")
 model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-medium")
 
+
 def user(message, history):
     return "", history + [[message, None]]
 
 
-#     bot_message = random.choice(["Yes", "No"])
-#     history[-1][1] = bot_message
-#     time.sleep(1)
-#     return history
-
-# def predict(input, history=[]):
-#     # tokenize the new input sentence
-
 def bot(history):
     user_message = history[-1][0]
-    new_user_input_ids = tokenizer.encode(user_message + tokenizer.eos_token, return_tensors='pt')
+    new_user_input_ids = tokenizer.encode(
+        user_message + 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)
+    bot_input_ids = torch.cat([torch.LongTensor([]), new_user_input_ids], dim=-1)
 
-    # generate a response 
-    history = model.generate(bot_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id).tolist()
+    # generate a response
+    response = model.generate(
+        bot_input_ids, max_length=1000, 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|>")
-    response = [(response[i], response[i+1]) for i in range(0, len(response)-1, 2)]  # convert to tuples of list
+    response = tokenizer.decode(response[0]).split("<|endoftext|>")
+    response = [
+        (response[i], response[i + 1]) for i in range(0, len(response) - 1, 2)
+    ]  # convert to tuples of list
+    history[-1] = response[0]
     return history
 
+
 with gr.Blocks() as demo:
     chatbot = gr.Chatbot()
     msg = gr.Textbox()