Update app.py

app.py

@@ -1,63 +1,102 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+import os
+import json
+import requests
 
-"""
-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]})
+API_URL = "https://api.openai.com/v1/chat/completions"
 
-    messages.append({"role": "user", "content": message})
+# Function to handle predictions
+def predict(inputs, top_p, temperature, openai_api_key, system_prompt, chat_counter, chatbot=[], history=[]):  
+    # Build the system prompt if provided
+    messages = []
+    if system_prompt:
+        messages.append({"role": "system", "content": system_prompt})
+    
+    # Add previous conversation history
+    if chat_counter != 0:
+        for data in chatbot:
+            messages.append({"role": "user", "content": data[0]})
+            messages.append({"role": "assistant", "content": data[1]})
+    
+    # Add the current user input to the messages
+    messages.append({"role": "user", "content": inputs})
+    
+    payload = {
+        "model": "gpt-3.5-turbo",
+        "messages": messages,
+        "temperature": temperature,
+        "top_p": top_p,
+        "n": 1,
+        "stream": True,
+        "presence_penalty": 0,
+        "frequency_penalty": 0,
+    }
+    
+    headers = {
+        "Content-Type": "application/json",
+        "Authorization": f"Bearer {openai_api_key}"
+    }
+    
+    chat_counter += 1
+    history.append(inputs)
+    
+    # Make a POST request to the API endpoint using the requests.post method
+    response = requests.post(API_URL, headers=headers, json=payload, stream=True)
+    
+    token_counter = 0
+    partial_words = ""
+    
+    counter = 0
+    for chunk in response.iter_lines():
+        if counter == 0:
+            counter += 1
+            continue
+        
+        if chunk.decode():
+            chunk = chunk.decode()
+            if len(chunk) > 12 and "content" in json.loads(chunk[6:])['choices'][0]['delta']:
+                partial_words = partial_words + json.loads(chunk[6:])['choices'][0]["delta"]["content"]
+                if token_counter == 0:
+                    history.append(" " + partial_words)
+                else:
+                    history[-1] = partial_words
+                chat = [(history[i], history[i + 1]) for i in range(0, len(history) - 1, 2)]
+                token_counter += 1
+                yield chat, history, chat_counter
 
-    response = ""
+# Function to reset the textbox
+def reset_textbox():
+    return gr.update(value='')
 
-    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
+# UI Components
+title = """<h1 align="center">Customizable Chatbot with OpenAI API</h1>"""
+description = """
+Explore the outputs of a GPT-3.5 model, with the ability to customize system prompts, enter your OpenAI API key, and interact with a history of conversation logs.
 """
-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)",
-        ),
-    ],
-)
 
+with gr.Blocks(css="""#col_container {width: 1000px; margin-left: auto; margin-right: auto;}
+                      #chatbot {height: 520px; overflow: auto;}""") as demo:
+    
+    gr.HTML(title)
+    with gr.Column(elem_id="col_container"):
+        openai_api_key = gr.Textbox(type='password', label="Enter your OpenAI API key here")
+        system_prompt = gr.Textbox(placeholder="Enter system prompt (optional)", label="System Prompt", lines=2)
+        chatbot = gr.Chatbot(elem_id='chatbot')
+        inputs = gr.Textbox(placeholder="Type your message here!", label="Input", lines=1)
+        state = gr.State([])
+        chat_counter = gr.Number(value=0, visible=False, precision=0)
+        reset_btn = gr.Button("Reset Chat")
+        
+        # Input parameters for OpenAI API
+        with gr.Accordion("Model 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")
+        
+        # Submit input for model prediction
+        inputs.submit(predict, [inputs, top_p, temperature, openai_api_key, system_prompt, chat_counter, chatbot, state], 
+                      [chatbot, state, chat_counter])
+        reset_btn.click(reset_textbox, [], [inputs])
+        inputs.submit(reset_textbox, [], [inputs])
 
-if __name__ == "__main__":
-    demo.launch()
+    demo.queue().launch(debug=True)