Deploy final

.dockerignore

@@ -0,0 +1,3 @@
+venv
+__pycache__
+.git

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,23 @@
+# Sử dụng Python 3.10 làm nền tảng
+FROM python:3.10
+
+# Tạo thư mục làm việc trong Container
+WORKDIR /code
+
+# Copy file requirements.txt vào Container trước để cài thư viện
+COPY ./requirements.txt /code/requirements.txt
+
+# Cài đặt các thư viện cần thiết
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+# Copy toàn bộ code (bao gồm thư mục model và main.py) vào Container
+COPY . /code
+
+# Thiết lập quyền user (Yêu cầu bắt buộc của Hugging Face Spaces)
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -0,0 +1,11 @@
+---
+title: Nexore Toxic Api
+emoji: 📉
+colorFrom: purple
+colorTo: gray
+sdk: docker
+pinned: false
+license: mit
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

main.py

@@ -0,0 +1,94 @@
+import uvicorn
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline
+import torch
+
+app = FastAPI()
+
+
+MODEL_PATH = "fallinluv8/nexore-toxic-model"
+
+HARD_BLACKLIST = [
+    "đéo", "đ**", "dm", "dcm", "đm", "vcl", "vl", 
+    "cc", "cmn", "cmm", "lồn", "l**", "đĩ", "đ**", 
+    "cặc", "c**", "buồi", "bu**", "đụ", "đụ mẹ",
+    "đụ bố", "đụ con mẹ mày", "đụ con", "đụ mày",
+]
+
+print(" Đang tải model NER (Token Classification)...")
+
+try:
+    tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)
+    model = AutoModelForTokenClassification.from_pretrained(MODEL_PATH)
+    
+    classifier = pipeline(
+        "token-classification", 
+        model=model, 
+        tokenizer=tokenizer, 
+        aggregation_strategy="simple",
+        device=0 if torch.cuda.is_available() else -1 
+    )
+    print(" Model NER đã tải thành công!")
+except Exception as e:
+    print(f" Lỗi tải model: {e}")
+
+class ToxicRequest(BaseModel):
+    text: str
+
+@app.get("/")
+def home():
+    return {"status": "AI NER Service is running"}
+
+@app.post("/predict")
+async def predict_toxicity(request: ToxicRequest):
+    if not request.text:
+        raise HTTPException(status_code=400, detail="Thiếu nội dung text")
+    text_lower = request.text.lower()
+
+    is_toxic = False
+    max_score = 0.0
+    toxic_words = []
+
+    for bad_word in HARD_BLACKLIST:
+        if f" {bad_word} " in f" {text_lower} " or text_lower.startswith(bad_word) or text_lower.endswith(bad_word) or bad_word in text_lower:
+            if bad_word in text_lower:
+                is_toxic = True
+                max_score = 1.0 
+                if not any(t['word'] == bad_word for t in toxic_words):
+                    toxic_words.append({
+                        "word": bad_word,
+                        "score": 1.0
+                    })
+
+    results = classifier(request.text)
+    
+    for entity in results:
+        print(f" AI thấy: '{entity['word']}' ({entity['score']:.4f})")
+
+        if entity['entity_group'] == 'BAD':
+            score = float(entity['score'])
+            word = entity['word']
+            
+            # Chỉ thêm nếu từ này chưa bị Blacklist bắt (tránh hiện trùng 2 lần)
+            if not any(t['word'].lower() == word.lower() for t in toxic_words):
+                toxic_words.append({
+                    "word": word,
+                    "score": score
+                })
+            
+            if score > max_score:
+                max_score = score
+
+    if max_score > 0.9:
+        is_toxic = True
+
+    return {
+        "is_toxic": is_toxic,
+        "score": float(max_score), 
+        "toxic_words": toxic_words,
+        "details": str(results)
+    }
+
+if __name__ == "__main__":
+    uvicorn.run(app, host="0.0.0.0", port=8000)

requirements.txt

@@ -0,0 +1,6 @@
+fastapi
+uvicorn
+transformers
+torch
+pydantic
+safetensors