Update app.py

app.py

@@ -1,89 +1,20 @@
-import gradio as gr
-import os
-import sys
-import json
-import requests
-import random
-
-MODEL = "gpt-4.1-mini"
-API_URL = os.getenv("API_URL")
-DISABLED = os.getenv("DISABLED") == 'True'
-OPENAI_API_KEYS = os.getenv("OPENAI_API_KEYS").split(',')
-NUM_THREADS = int(os.getenv("NUM_THREADS", "1"))
-
-def exception_handler(exception_type, exception, traceback):
-    print(f"{exception_type.__name__}: {exception}")
-sys.excepthook = exception_handler
-sys.tracebacklimit = 0
-
-def predict(inputs, top_p, temperature, chat_counter, chatbot, history, request: gr.Request):
-    payload = {
-        "model": MODEL,
-        "messages": [{"role": "user", "content": inputs}],
-        "temperature": temperature,
-        "top_p": top_p,
-        "n": 1,
-        "stream": True,
-        "presence_penalty": 0,
-        "frequency_penalty": 0,
-    }
-    OPENAI_API_KEY = random.choice(OPENAI_API_KEYS)
-    
-    headers = {
-        "Content-Type": "application/json",
-        "Authorization": f"Bearer {OPENAI_API_KEY}",
-    }
-
-    if chat_counter != 0:
-        messages = []
-        for i, data in enumerate(history):
-            role = "user" if i % 2 == 0 else "assistant"
-            messages.append({"role": role, "content": data})
-        messages.append({"role": "user", "content": inputs})
-        payload["messages"] = messages
-
-    chat_counter += 1
-    history.append(inputs)
-    partial_words = ""
-    token_counter = 0
-    counter = 0
-
-    try:
-        response = requests.post(API_URL, headers=headers, json=payload, stream=True)
-        for chunk in response.iter_lines():
-            if counter == 0:
-                counter += 1
-                continue
-            if chunk:
-                chunk_str = chunk.decode()
-                chunk_json = json.loads(chunk_str[6:])
-                delta = chunk_json['choices'][0]['delta']
-                if "content" in delta:
-                    partial_words += delta["content"]
-                    if token_counter == 0:
-                        history.append(" " + partial_words)
-                    else:
-                        history[-1] = partial_words
-                    token_counter += 1
-                    yield [(history[i], history[i + 1]) for i in range(0, len(history) - 1, 2)], history, chat_counter, gr.update(interactive=False), gr.update(interactive=False)
-    except Exception as e:
-        print(f"Error: {e}")
-    
-    yield [(history[i], history[i + 1]) for i in range(0, len(history) - 1, 2)], history, chat_counter, gr.update(interactive=True), gr.update(interactive=True)
-
-def reset_textbox():
-    return gr.update(value='', interactive=False), gr.update(interactive=False)
-
-title = """<h1 align="center">GPT-4.1 mini: Research Preview (Short-Term Availability)</h1>"""
-if DISABLED:
-    title = """<h1 align="center" style="color:red">This app has reached OpenAI's usage limit. Please check back tomorrow.</h1>"""
-description = """Language models can be conditioned to act like dialogue agents through a conversational prompt."""
+In this app, you can explore the outputs of a gpt-4 turbo LLM.
+"""
 
 theme = gr.themes.Default(primary_hue="green")
 
-with gr.Blocks(css="#col_container { margin-left: auto; margin-right: auto;} #chatbot {height: 520px; overflow: auto;}", theme=theme) as demo:
+with gr.Blocks(css="""#col_container { margin-left: auto; margin-right: auto;}
+                #chatbot {height: 520px; overflow: auto;}""",
+              theme=theme) as demo:
     gr.HTML(title)
     gr.HTML("""<h3 align="center">This app provides you full access to GPT-4.1 mini (1M token limit). You don't need any OPENAI API key.</h3>""")
+    gr.HTML("""
+<div style="padding: 12px; margin-bottom: 16px; border-radius: 6px; background-color: #e6f4ea; text-align: center;">
+    🚀 <b>Try our new ChatAnnotator</b> powered by Cohere's <b>Command-A</b> model! 
+    It offers a much-improved interface allowing you to <b>highlight and annotate specific errors</b> directly within chatbot responses, and even prompt immediate corrections. 
+    <a href="https://chatannotator.com" target="_blank">Click here to check it out!</a>
+</div>
+""")
 
     with gr.Column(elem_id="col_container", visible=not DISABLED) as main_block:
         chatbot = gr.Chatbot(elem_id='chatbot')
@@ -94,14 +25,17 @@ with gr.Blocks(css="#col_container { margin-left: auto; margin-right: auto;} #ch
                 b1 = gr.Button(visible=not DISABLED)
             with gr.Column(scale=3):
                 server_status_code = gr.Textbox(label="Status code from OpenAI server")
+
         with gr.Accordion("Parameters", open=False):
             top_p = gr.Slider(minimum=0, maximum=1.0, value=1.0, step=0.05, interactive=True, label="Top-p (nucleus sampling)")
             temperature = gr.Slider(minimum=0, maximum=5.0, value=1.0, step=0.1, interactive=True, label="Temperature")
             chat_counter = gr.Number(value=0, visible=False, precision=0)
 
     inputs.submit(reset_textbox, [], [inputs, b1], queue=False)
-    inputs.submit(predict, [inputs, top_p, temperature, chat_counter, chatbot, state], [chatbot, state, chat_counter, inputs, b1])
+    inputs.submit(predict, [inputs, top_p, temperature, chat_counter, chatbot, state], 
+                  [chatbot, state, chat_counter, server_status_code, inputs, b1])
     b1.click(reset_textbox, [], [inputs, b1], queue=False)
-    b1.click(predict, [inputs, top_p, temperature, chat_counter, chatbot, state], [chatbot, state, chat_counter, inputs, b1])
+    b1.click(predict, [inputs, top_p, temperature, chat_counter, chatbot, state], 
+             [chatbot, state, chat_counter, server_status_code, inputs, b1])
 
     demo.queue(max_size=10, default_concurrency_limit=NUM_THREADS, api_open=False).launch(share=False)