Update app.py

app.py

@@ -1,63 +1,43 @@
 import gradio as gr
-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("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]})
-
-    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)",
-        ),
-    ],
+from openai import OpenAI
+
+endpoint_id = "vllm-8p6dngdyjt3d2a"
+api_key = "XWV1ST04C0QLWNVAUSJWI6VJMR7YDJCKJSAR6TPA"
+model = "unsloth/Meta-Llama-3.1-8B-Instruct"
+
+AGENT_NAME = "Maddie"
+AGE = "Early 20s"
+INTERESTS = "Typical college student interests (e.g., going out with friends, studying, working out, watching TV shows/movies)"
+PERSONALITY = "Friendly, outgoing, and bubbly, pick-me girl, loves attention"
+
+SYS_PROMPT = f"""You are role-playing as a Tinder user named {AGENT_NAME}, who is {AGE} years old. You have specific interests: {INTERESTS}, and a personality that can be described as {PERSONALITY}. Engage in a friendly, playful, and flirty conversation as if you have just matched with someone you are interested in. Let the dialogue flow naturally, but end the conversation after 10 messages with the phrase "[END OF CHAT]"."""
+
+client = OpenAI(
+    base_url=f"https://api.runpod.ai/v2/{endpoint_id}/openai/v1",
+    api_key=api_key,
 )
 
+def handler(message, history):
+    for _, response in history:
+        if "[END OF CHAT]" in response:
+            return "CHAT ENDS HERE"
+    
+    formatted_history = [{"role": "user" if i % 2 == 0 else "assistant", "content": msg} 
+                         for i, msg in enumerate(sum(history, []))]
+    
+    formatted_history.append({"role": "user", "content": message})
+
+    formatted_history.insert(0, {"role": "system", "content": SYS_PROMPT})
+
+    print(formatted_history)
+    
+    chat_completion = client.chat.completions.create(
+        model=model,
+        messages=formatted_history
+    )
+
+    print(chat_completion)
+
+    return chat_completion.choices[0].message.content
 
-if __name__ == "__main__":
-    demo.launch()
+gr.ChatInterface(handler).launch()