1

app.py

@@ -1,89 +1,35 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
+from fastapi import FastAPI
+from pydantic import BaseModel
+import uvicorn
 from translator import translate
 
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    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(token=hf_token.token, model="openai/gpt-oss-20b")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
-    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,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = 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
-"""
-chatbot = gr.ChatInterface(
-    respond,
-    type="messages",
-    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)",
-        ),
-    ],
-)
-
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
-# ===== Translator =====
-def translate_ui(text, direction):
-    return translate(text, direction)
-
-# ===== Layout Gradio =====
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    
-    with gr.Tabs():
-        with gr.Tab("Chatbot"):
-            chatbot.render()
-        
-        with gr.Tab("Translator"):
-            input_text = gr.Textbox(lines=4, label="Input")
-            direction = gr.Dropdown(["ID → EN", "EN → ID"], label="Direction")
-            output_text = gr.Textbox(label="Output")
-            translate_btn = gr.Button("Translate")
-            translate_btn.click(fn=translate_ui, inputs=[input_text, direction], outputs=output_text)
-
+app = FastAPI()
+
+# ===== Model untuk request/response =====
+class ChatRequest(BaseModel):
+    message: str
+    history: list[dict] = []
+    system_message: str = "You are a friendly chatbot."
+    max_tokens: int = 512
+    temperature: float = 0.7
+    top_p: float = 0.95
+
+class TranslateRequest(BaseModel):
+    text: str
+    direction: str  # "ID → EN" atau "EN → ID"
+
+# ===== Endpoint Chatbot =====
+@app.post("/chat")
+def chat_endpoint(req: ChatRequest):
+    # ⚡ Di sini kamu bisa sambungkan dengan InferenceClient seperti di kode awal
+    return {"response": f"Simulasi jawaban untuk: {req.message}"}
+
+# ===== Endpoint Translator =====
+@app.post("/translate")
+def translate_endpoint(req: TranslateRequest):
+    result = translate(req.text, req.direction)
+    return {"translation": result}
+
+# ====== Run local (Space akan otomatis pakai uvicorn) ======
 if __name__ == "__main__":
-    demo.launch()
+    uvicorn.run(app, host="0.0.0.0", port=7860)