Update app.py

app.py

@@ -1,35 +1,98 @@
+# import gradio as gr
+# from transformers import GPT2LMHeadModel, GPT2Tokenizer
+# import torch
+# import os
+
+# # Load token from environment variable
+# token = os.getenv('ACCESS_SECRET')
+
+# # Specify the repository ID
+# model_repo_id = "Ajay12345678980/QA_Chatbot"
+
+# # Load model and tokenizer
+# model = GPT2LMHeadModel.from_pretrained(model_repo_id, use_auth_token=token)
+# tokenizer = GPT2Tokenizer.from_pretrained(model_repo_id, use_auth_token=token)
+
+# # Define prediction function
+# def predict(text):
+#     inputs = tokenizer.encode(text, return_tensors="pt")
+#     with torch.no_grad():
+#         outputs = model.generate(inputs, max_length=50, do_sample=True)
+#     prediction = tokenizer.decode(outputs[0], skip_special_tokens=True)
+#     return prediction
+
+# # Set up Gradio interface
+# interface = gr.Interface(
+#     fn=predict, 
+#     inputs="text", 
+#     outputs="text", 
+#     title="GPT-2 Text Generation",
+#     description="Enter some text and see what the model generates!"
+# )
+
+# # Launch the Gradio app
+# if __name__ == "__main__":
+#     interface.launch()
 import gradio as gr
-from transformers import GPT2LMHeadModel, GPT2Tokenizer
-import torch
-import os
-
-# Load token from environment variable
-token = os.getenv('ACCESS_SECRET')
-
-# Specify the repository ID
-model_repo_id = "Ajay12345678980/QA_Chatbot"
-
-# Load model and tokenizer
-model = GPT2LMHeadModel.from_pretrained(model_repo_id, use_auth_token=token)
-tokenizer = GPT2Tokenizer.from_pretrained(model_repo_id, use_auth_token=token)
-
-# Define prediction function
-def predict(text):
-    inputs = tokenizer.encode(text, return_tensors="pt")
-    with torch.no_grad():
-        outputs = model.generate(inputs, max_length=50, do_sample=True)
-    prediction = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    return prediction
-
-# Set up Gradio interface
-interface = gr.Interface(
-    fn=predict, 
-    inputs="text", 
-    outputs="text", 
-    title="GPT-2 Text Generation",
-    description="Enter some text and see what the model generates!"
+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("Ajay12345678980/QA_Chatbot")
+
+
+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)",
+        ),
+    ],
 )
 
-# Launch the Gradio app
+
 if __name__ == "__main__":
-    interface.launch()
+    demo.launch()