.

app.py

@@ -1,53 +1,49 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+import requests
+import os
 
-"""
-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")
+# Set up the API endpoint and key
+API_URL = "https://api.runpod.ai/v2/vllm-2lzb7pk51fq0wd/openai/v1/chat/completions"
+API_KEY = os.getenv("RUNPOD_API_KEY")  # Make sure to set this in your Hugging Face Space secrets
 
+headers = {
+    "Authorization": f"Bearer {API_KEY}",
+    "Content-Type": "application/json"
+}
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
+def respond(message, history, 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]})
-
+    
+    for human, assistant in history:
+        messages.append({"role": "user", "content": human})
+        messages.append({"role": "assistant", "content": assistant})
+    
     messages.append({"role": "user", "content": message})
+    
+    data = {
+        "model": "forcemultiplier/fmx-reflective-2b",  # Adjust if needed
+        "messages": messages,
+        "max_tokens": max_tokens,
+        "temperature": temperature,
+        "top_p": top_p
+    }
+    
+    response = requests.post(API_URL, headers=headers, json=data)
+    
+    if response.status_code == 200:
+        return response.json()['choices'][0]['message']['content']
+    else:
+        return f"Error: {response.status_code} - {response.text}"
 
-    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.Textbox(
+            value="You are an advanced artificial intelligence system, capable of <thinking> <reflection> and you output a brief and to-the-point <output>.",
+            label="System message"
+        ),
+        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max tokens"),
+        gr.Slider(minimum=0.1, maximum=2.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(
             minimum=0.1,
             maximum=1.0,
@@ -58,6 +54,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()