Use OpenAI NeonLLM

app.py

@@ -1,60 +1,46 @@
+import os
+from typing import List, Tuple
+
 import gradio as gr
-from huggingface_hub import InferenceClient
+from openai import OpenAI
+
+
+
+client = OpenAI(
+    base_url=f"{os.environ['BASE_URL']}/v1",
+    api_key=os.environ["API_KEY"],
+)
 
-"""
-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,
+    history: List[Tuple[str, str]],
     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 = []
 
     messages.append({"role": "user", "content": message})
 
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
+    completion = client.chat.completions.create(
+        model="neongeckocom/NeonLLM",
+        messages=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
-"""
+        temperature=0,
+        extra_body={
+            "repetition_penalty": 1.05,
+            "use_beam_search": True,
+            "best_of": 5,
+        },
+    )
+    response = completion.choices[0].message.content
+    return response
+
+
 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)",
-        ),
     ],
 )