Update app.py

app.py

@@ -1,70 +1,60 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-
-
-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)",
-        ),
-    ],
+from fastapi import FastAPI
+from fastapi.middleware.cors import CORSMiddleware
+from pydantic import BaseModel
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+import torch
+import warnings
+import uvicorn
+
+# Tắt warning lặt vặt
+warnings.filterwarnings("ignore")
+
+# Load model
+MODEL_NAME = "tarudesu/ViHateT5-base-HSD"
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+model = AutoModelForSeq2SeqLM.from_pretrained(MODEL_NAME)
+
+# Khởi tạo FastAPI
+app = FastAPI(title="Vietnamese Toxic Comment Detection API")
+
+# Bật CORS cho tất cả domain
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],   # Cho phép tất cả domain
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
-
+# Schema cho input
+class CommentInput(BaseModel):
+    text: str
+    prefix: str = "hate-speech-detection"
+
+# Hàm dự đoán
+def predict_vihatet5(comment: str, prefix: str = "hate-speech-detection"):
+    input_text = prefix + ": " + comment
+    inputs = tokenizer(
+        input_text,
+        return_tensors="pt",
+        truncation=True,
+        padding=True,
+        max_length=128
+    )
+    output_ids = model.generate(**inputs, max_length=50)
+    output = tokenizer.decode(output_ids[0], skip_special_tokens=True)
+    return output
+
+# API route
+@app.post("/predict")
+def predict(input_data: CommentInput):
+    result = predict_vihatet5(input_data.text, prefix=input_data.prefix)
+    return {
+        "input": input_data.text,
+        "prefix": input_data.prefix,
+        "prediction": result
+    }
+
+# Chạy app
 if __name__ == "__main__":
-    demo.launch()
+    uvicorn.run(app, host="0.0.0.0", port=7860)