Update app.py

app.py

@@ -3,48 +3,61 @@ import os
 from langchain_openai import ChatOpenAI
 
 api_key = os.environ.get("FEATHERLESS_API_KEY")
+llm = ChatOpenAI(
+    base_url="https://api.featherless.ai/v1/",
+    api_key=api_key,
+    streaming=True,
+    model="Qwen/Qwen3-32B",
+    # model="deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
+    # model="meta-llama/Llama-3.3-70B-Instruct",
+    # model="mistralai/Magistral-Small-2506",
+    # model="unsloth/DeepSeek-R1-Distill-Llama-70B",
+    # model="unsloth/Qwen2.5-72B-Instruct",
+    # model="unsloth/Llama-3.3-70B-Instruct",
+)
 
-MODEL_CHOICES = [
-    "Qwen/Qwen3-32B",
-    "deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
-    "meta-llama/Llama-3.3-70B-Instruct",
-    "mistralai/Magistral-Small-2506",
-    "unsloth/DeepSeek-R1-Distill-Llama-70B",
-    "unsloth/Qwen2.5-72B-Instruct",
-    "unsloth/Llama-3.3-70B-Instruct",
-]
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
+    messages = [{"role": "system", "content": system_message}]
 
-def create_llm(model_name: str):
-    return ChatOpenAI(
-        base_url="https://api.featherless.ai/v1/",
-        api_key=api_key,
-        streaming=True,
-        model=model_name,
-    )
+    for val in history:
+        if val[0]:
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:
+            messages.append({"role": "assistant", "content": val[1]})
 
-def respond(message, history, system_message, max_tokens, temperature, top_p, model_name):
-    llm = create_llm(model_name)
-    messages = [{"role":"system","content":system_message}]
-    for u, a in history:
-        if u: messages.append({"role":"user","content":u})
-        if a: messages.append({"role":"assistant","content":a})
-    messages.append({"role":"user","content":message})
+    messages.append({"role": "user", "content": message})
     llm.max_tokens = max_tokens
     llm.temperature = temperature
     llm.top_p = top_p
     response = ""
+
     for chunk in llm.stream(messages):
-        response += chunk.content
+        token = chunk.content
+        response += token
         yield response
 
-with gr.Blocks() as demo:
-    with gr.Row():
-        model_dropdown = gr.Dropdown(choices=MODEL_CHOICES, value=MODEL_CHOICES[0], label="Pilih model")
-    chatbot = gr.Chatbot()
-    system_msg = gr.Textbox("You are a friendly Chatbot.", label="System message")
-    max_t = gr.Slider(1, 16384, value=2048, step=1, label="Max new tokens")
-    temp = gr.Slider(0.1, 2.0, value=0.7, step=0.1, label="Temperature")
-    top_p = gr.Slider(0.1, 1.0, value=0.95, step=0.05, label="Top‑p")
+demo = gr.ChatInterface(
+    respond,
+    additional_inputs=[
+        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Slider(minimum=1, maximum=16384, value=2048, step=1, label="Max new 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,
+            value=0.95,
+            step=0.05,
+            label="Top-p (nucleus sampling)",
+        ),
+    ],
+)
 
-    model_dropdown.change(lambda x: None, inputs=model_dropdown, outputs=[])
+if __name__ == "__main__":
     demo.launch()