Upload 2 files

app.py

@@ -1,64 +1,74 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from openai import OpenAI
+import os
+import time
 
-"""
-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 predict(message, history, system_prompt, model, max_tokens, temperature, top_p):
 
+    # Initialize the OpenAI client
+    client = OpenAI(
+        api_key=os.environ.get("API_TOKEN"),
+    )
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+    # Start with the system prompt
+    messages = [{"role": "system", "content": system_prompt}]
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+    # Add the conversation history
+    messages.extend(history if history else [])
 
+    # Add the current user message
     messages.append({"role": "user", "content": message})
 
-    response = ""
+    # Record the start time
+    start_time = time.time()
 
-    for message in client.chat_completion(
-        messages,
+    # Streaming response
+    response = client.chat.completions.create(
+        model=model,
+        messages=messages,
         max_tokens=max_tokens,
-        stream=True,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+        stop=None,
+        stream=True
+    )
 
-        response += token
-        yield response
+    full_message = ""
+    first_chunk_time = None
+    last_yield_time = None
 
+    for chunk in response:
+        if chunk.choices and chunk.choices[0].delta.content:
+            if first_chunk_time is None:
+                first_chunk_time = time.time() - start_time  # Record time for the first chunk
 
-"""
-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)",
-        ),
-    ],
-)
+            full_message += chunk.choices[0].delta.content
+            current_time = time.time()
+            chunk_time = current_time - start_time  # calculate the time delay of the chunk
+            print(f"Message received {chunk_time:.2f} seconds after request: {chunk.choices[0].delta.content}")  
+
+            if last_yield_time is None or (current_time - last_yield_time >= 0.25):
+                yield full_message
+                last_yield_time = current_time
 
+    # Ensure to yield any remaining message that didn't meet the time threshold
+    if full_message:
+        total_time = time.time() - start_time
+        # Append timing information to the response message
+        full_message += f" (First Chunk: {first_chunk_time:.2f}s, Total: {total_time:.2f}s)"
+        yield full_message
 
-if __name__ == "__main__":
-    demo.launch()
+gr.ChatInterface(
+    fn=predict,
+    type="messages",
+    #save_history=True,
+    #editable=True,
+    additional_inputs=[
+        gr.Textbox("You are a helpful AI assistant.", label="System Prompt"),
+        gr.Dropdown(["gpt-4o", "gpt-4o-mini"], label="Model"),
+        gr.Slider(800, 4000, value=2000, label="Max Token"),
+        gr.Slider(0, 1, value=0.7, label="Temperature"),
+        gr.Slider(0, 1, value=0.95, label="Top P"),
+    ],
+    css="footer{display:none !important}"
+).launch()

requirements.txt

@@ -1 +1,3 @@
-huggingface_hub==0.25.2
+gradio
+huggingface
+openai