Update app.py

app.py

@@ -1,63 +1,36 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+import spacy
+from transformers import GenerationConfig, T5Tokenizer, T5ForConditionalGeneration
+import json
 
 """
 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)",
-        ),
-    ],
-)
-
+def predict(message, history):
+  model = T5ForConditionalGeneration.from_pretrained('kronos25/Temporal_Chatbot')
+  tokenizer = T5Tokenizer.from_pretrained('kronos25/Temporal_Chatbot')
+  input = message + '\n'
+  inputs = tokenizer(input, return_tensors="pt")
+  outputs = model.generate(**inputs,max_length=100)
+  model_result = tokenizer.decode(outputs[0], skip_special_tokens=True)
+  return model_result + '\n'
+
+gr.ChatInterface(
+    predict,
+    chatbot=gr.Chatbot(height=300),
+    textbox=gr.Textbox(placeholder="Ask me anything.", container=False, scale=7),
+    title="Temporal Chatbot",
+    description="Ask Temporal Chatbot any question",
+    theme="soft",
+    examples=["Is the doctor available tomorrow?"],
+    cache_examples=True,
+    retry_btn=None,
+    undo_btn="Delete Previous",
+    clear_btn="Clear"
+).launch(share=True)
 
 if __name__ == "__main__":
     demo.launch()