Update app.py

app.py

@@ -1,72 +1,161 @@
-import os
-os.system('pip install dashscope')
-import gradio as gr
+# import os
+# !os.system('pip install dashscope')
+# import gradio as gr
 from http import HTTPStatus
-import dashscope
-from dashscope import Generation
-from dashscope.api_entities.dashscope_response import Role
-from typing import List, Optional, Tuple, Dict
+
+# from dashscope import Generation
+# !from dashscope.api_entities.dashscope_response import Role
+# from typing import List, Optional, Tuple, Dict
 from urllib.error import HTTPError
-default_system = 'You are a helpful assistant.'
+# default_system = 'You are a helpful assistant.'e
+
+
+
+# History = List[Tuple[str, str]]
+# Messages = List[Dict[str, str]]
+
+# def clear_session() -> History:
+#     return '', []
+
+# def modify_system_session(system: str) -> str:
+#     if system is None or len(system) == 0:
+#         system = default_system
+#     return system, system, []
+
+# def history_to_messages(history: History, system: str) -> Messages:
+#     messages = [{'role': Role.SYSTEM, 'content': system}]
+#     for h in history:
+#         messages.append({'role': Role.USER, 'content': h[0]})
+#         messages.append({'role': Role.ASSISTANT, 'content': h[1]})
+#     return messages
+
+
+# def messages_to_history(messages: Messages) -> Tuple[str, History]:
+#     assert messages[0]['role'] == Role.SYSTEM
+#     system = messages[0]['content']
+#     history = []
+#     for q, r in zip(messages[1::2], messages[2::2]):
+#         history.append([q['content'], r['content']])
+#     return system, history
+
 
-YOUR_API_TOKEN = os.getenv('YOUR_API_TOKEN')
-dashscope.api_key = YOUR_API_TOKEN
+# def model_chat(query: Optional[str], history: Optional[History], system: str
+# ) -> Tuple[str, str, History]:
+#     if query is None:
+#         query = ''
+#     if history is None:
+#         history = []
+#     messages = history_to_messages(history, system)
+#     messages.append({'role': Role.USER, 'content': query})
+#     gen = Generation.call(
+#         model = "codeqwen1.5-7b-chat",
+#         messages=messages,
+#         result_format='message',
+#         stream=True
+#     )
+#     for response in gen:
+#         if response.status_code == HTTPStatus.OK:
+#             role = response.output.choices[0].message.role
+#             response = response.output.choices[0].message.content
+#             system, history = messages_to_history(messages + [{'role': role, 'content': response}])
+#             yield '', history, system
+#         else:
+#             raise HTTPError('Request id: %s, Status code: %s, error code: %s, error message: %s' % (
+#                 response.request_id, response.status_code,
+#                 response.code, response.message
+#             ))
 
+
+# with gr.Blocks() as demo:
+#     gr.Markdown("""<center><font size=8>CodeQwen1.5-7B-Chat Bot👾</center>""")
+
+#     with gr.Row():
+#         with gr.Column(scale=3):
+#             system_input = gr.Textbox(value=default_system, lines=1, label='System')
+#         with gr.Column(scale=1):
+#             modify_system = gr.Button("🛠️ Set system prompt and clear history", scale=2)
+#         system_state = gr.Textbox(value=default_system, visible=False)
+#     chatbot = gr.Chatbot(label='codeqwen1.5-7b-chat')
+#     textbox = gr.Textbox(lines=2, label='Input')
+
+#     with gr.Row():
+#         clear_history = gr.Button("🧹 Clear History")
+#         sumbit = gr.Button("🚀 Send")
+
+#     sumbit.click(model_chat,
+#                  inputs=[textbox, chatbot, system_state],
+#                  outputs=[textbox, chatbot, system_input])
+#     clear_history.click(fn=clear_session,
+#                         inputs=[],
+#                         outputs=[textbox, chatbot])
+#     modify_system.click(fn=modify_system_session,
+#                         inputs=[system_input],
+#                         outputs=[system_state, system_input, chatbot])
+
+# demo.queue(api_open=False)
+# demo.launch(max_threads=30, share=True)
+import os
+import torch
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from typing import List, Optional, Tuple, Dict
+
+# Set up default system prompt and history/message structures
+default_system = 'You are Andrej Karpathy, the most helpful coding assistant and solves everything with working code.'
 History = List[Tuple[str, str]]
 Messages = List[Dict[str, str]]
 
+# Clear the chat session
 def clear_session() -> History:
     return '', []
 
-def modify_system_session(system: str) -> str:
-    if system is None or len(system) == 0:
+# Modify the chat system's prompt
+def modify_system_session(system: str) -> Tuple[str, str, History]:
+    if system is None or system == "":
         system = default_system
     return system, system, []
 
+# Convert the history of messages into a format suitable for model input
 def history_to_messages(history: History, system: str) -> Messages:
-    messages = [{'role': Role.SYSTEM, 'content': system}]
+    messages = [{'role': 'system', 'content': system}]
     for h in history:
-        messages.append({'role': Role.USER, 'content': h[0]})
-        messages.append({'role': Role.ASSISTANT, 'content': h[1]})
+        messages.append({'role': 'user', 'content': h[0]})
+        messages.append({'role': 'assistant', 'content': h[1]})
     return messages
 
-
+# Convert messages back into a history format after model processing
 def messages_to_history(messages: Messages) -> Tuple[str, History]:
-    assert messages[0]['role'] == Role.SYSTEM
+    assert messages[0]['role'] == 'system'
     system = messages[0]['content']
     history = []
     for q, r in zip(messages[1::2], messages[2::2]):
         history.append([q['content'], r['content']])
     return system, history
 
+# Handle the chat interaction, including processing the input and generating a response
+def model_chat(query: Optional[str], history: Optional[History], system: str) -> Tuple[str, History, str]:
+    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+    model_name = "codeqwen1.5-7b-chat"
+
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    model = AutoModelForCausalLM.from_pretrained(model_name).to(device)
 
-def model_chat(query: Optional[str], history: Optional[History], system: str
-) -> Tuple[str, str, History]:
     if query is None:
         query = ''
     if history is None:
         history = []
     messages = history_to_messages(history, system)
-    messages.append({'role': Role.USER, 'content': query})
-    gen = Generation.call(
-        model = "codeqwen1.5-7b-chat",
-        messages=messages,
-        result_format='message',
-        stream=True
-    )
-    for response in gen:
-        if response.status_code == HTTPStatus.OK:
-            role = response.output.choices[0].message.role
-            response = response.output.choices[0].message.content
-            system, history = messages_to_history(messages + [{'role': role, 'content': response}])
-            yield '', history, system
-        else:
-            raise HTTPError('Request id: %s, Status code: %s, error code: %s, error message: %s' % (
-                response.request_id, response.status_code,
-                response.code, response.message
-            ))
+    messages.append({'role': 'user', 'content': query})
+
+    inputs = tokenizer(messages[-1]['content'], return_tensors="pt").to(device)
+    outputs = model.generate(inputs, max_length=100, pad_token_id=tokenizer.eos_token_id)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+    system, history = messages_to_history(messages + [{'role': 'assistant', 'content': response}])
 
+    return '', history, system
 
+# Setting up the Gradio interface
 with gr.Blocks() as demo:
     gr.Markdown("""<center><font size=8>CodeQwen1.5-7B-Chat Bot👾</center>""")
 
@@ -81,9 +170,9 @@ with gr.Blocks() as demo:
 
     with gr.Row():
         clear_history = gr.Button("🧹 Clear History")
-        sumbit = gr.Button("🚀 Send")
+        submit = gr.Button("🚀 Send")
 
-    sumbit.click(model_chat,
+    submit.click(model_chat,
                  inputs=[textbox, chatbot, system_state],
                  outputs=[textbox, chatbot, system_input])
     clear_history.click(fn=clear_session,
@@ -93,5 +182,4 @@ with gr.Blocks() as demo:
                         inputs=[system_input],
                         outputs=[system_state, system_input, chatbot])
 
-demo.queue(api_open=False)
-demo.launch(max_threads=30)
+demo.launch(share=True, enable_queue=True)