Refact: ADDED DOCKER FILE and updated requirement.txt and app.py for hugging face

Dockerfile

@@ -0,0 +1,34 @@
+# Use the latest slim Python 3.11 image
+FROM python:3.11-slim
+
+# Set environment variables
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH \
+    PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential \
+    git \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
+
+# Create a non-root user for safety
+RUN useradd -ms /bin/bash user
+USER user
+WORKDIR $HOME/app
+
+# Copy app source code
+COPY --chown=user . .
+
+# Install Python dependencies
+RUN pip install --no-cache-dir --upgrade pip \
+ && pip install --no-cache-dir -r requirements.txt
+
+# Expose port
+EXPOSE 7860
+
+# Start the FastAPI app using uvicorn
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]
+

HuggingFace/main.py

@@ -1,18 +0,0 @@
-import os
-from huggingface_hub import Repository
-
-
-def download_repo():
-    hf_token = os.getenv("HF_TOKEN")
-    if not hf_token:
-        raise ValueError("HF_TOKEN not found in environment variables.")
-
-    repo_id = "Pujan-Dev/test"
-    local_dir = "../Ai-Text-Detector/"
-
-    repo = Repository(local_dir, clone_from=repo_id, token=hf_token)
-    print(f"Repository downloaded to: {local_dir}")
-
-
-if __name__ == "__main__":
-    download_repo()

HuggingFace/readme.md

@@ -1,61 +0,0 @@
-### Hugging Face CLI Tool
-
-This CLI tool allows you to **upload** and **download** models from Hugging Face repositories. It requires an **Hugging Face Access Token (`HF_TOKEN`)** for authentication, especially for private repositories.
-
-### Prerequisites
-
-1. **Install Hugging Face Hub**:
-
-   ```bash
-   pip install huggingface_hub
-   ```
-
-2. **Get HF_TOKEN**:
-   - Log in to [Hugging Face](https://huggingface.co/).
-   - Go to **Settings** → **Access Tokens** → **Create a new token** with `read` and `write` permissions.
-   - Save the token.
-
-### Usage
-
-1. **Set the Token**:
-
-   - **Linux/macOS**:
-     ```bash
-     export HF_TOKEN=your_token_here
-     ```
-   - **Windows (CMD)**:
-     ```bash
-     set HF_TOKEN=your_token_here
-     ```
-
-2. **Download Model**:
-
-   ```bash
-   python main.py --download --repo-id <repo_name> --save-dir <local_save_path>
-   ```
-
-3. **Upload Model**:
-   ```bash
-   python main.py --upload --repo-id <repo_name> --model-path <local_model_path>
-   ```
-
-### Example
-
-To download a model:
-
-```bash
-python main.py
-```
-
-### Authentication
-
-Ensure you set `HF_TOKEN` to access private repositories. If not set, the script will raise an error.
-Here’s a clearer and more polished version of that note:
-
----
-
-### ⚠️ Note
-
-**Make sure to run this script from the `HuggingFace` directory to ensure correct path resolution and functionality.**
-
----

app.py

@@ -1,44 +1,40 @@
 import torch
-from transformers import GPT2LMHeadModel, GPT2TokenizerFast
-from fastapi import FastAPI, HTTPException, Header
+from transformers import GPT2LMHeadModel, GPT2TokenizerFast, GPT2Config
+from fastapi import FastAPI, HTTPException
 from pydantic import BaseModel
-import asyncio
-from concurrent.futures import ThreadPoolExecutor
 from contextlib import asynccontextmanager
-from dotenv import dotenv_values
+import asyncio
 
-# FastAPI instance
+# FastAPI app instance
 app = FastAPI()
-executor = ThreadPoolExecutor(max_workers=20)
-
-# Load .env file
-env = dotenv_values(".env")
-EXPECTED_TOKEN = env.get("SECRET_TOKEN")
 
-# Global variables for model and tokenizer
+# Global model and tokenizer variables
 model, tokenizer = None, None
 
-# Function to verify token
-
-
-def verify_token(auth: str):
-    if auth != f"Bearer {EXPECTED_TOKEN}":
-        raise HTTPException(status_code=403, detail="Unauthorized")
-
-
 # Function to load model and tokenizer
 
 
 def load_model():
     model_path = "./Ai-Text-Detector/model"
     weights_path = "./Ai-Text-Detector/model_weights.pth"
-    tokenizer = GPT2TokenizerFast.from_pretrained(model_path)
-    model = GPT2LMHeadModel.from_pretrained("gpt2")
-    model.load_state_dict(torch.load(weights_path, map_location=torch.device("cpu")))
-    model.eval()  # Set the model to evaluation mode
+
+    try:
+        tokenizer = GPT2TokenizerFast.from_pretrained(model_path)
+        config = GPT2Config.from_pretrained(model_path)
+        model = GPT2LMHeadModel(config)
+        model.load_state_dict(
+            torch.load(weights_path, map_location=torch.device("cpu"))
+        )
+        model.eval()  # Set model to evaluation mode
+    except Exception as e:
+        raise RuntimeError(f"Error loading model: {str(e)}")
+
     return model, tokenizer
 
 
+# Load model on app startup
+
+
 @asynccontextmanager
 async def lifespan(app: FastAPI):
     global model, tokenizer
@@ -46,20 +42,20 @@ async def lifespan(app: FastAPI):
     yield
 
 
-# Attach the lifespan context manager
+# Attach startup loader
 app = FastAPI(lifespan=lifespan)
 
-# Request body for input data
+# Input schema
 
 
 class TextInput(BaseModel):
     text: str
 
 
-# Sync function to classify text
+# Sync text classification
 
 
-def classify_text_sync(sentence: str):
+def classify_text(sentence: str):
     inputs = tokenizer(sentence, return_tensors="pt", truncation=True, padding=True)
     input_ids = inputs["input_ids"]
     attention_mask = inputs["attention_mask"]
@@ -70,35 +66,26 @@ def classify_text_sync(sentence: str):
         perplexity = torch.exp(loss).item()
 
     if perplexity < 60:
-        result = "AI-generated*"
+        result = "AI-generated"
     elif perplexity < 80:
-        result = "Probably AI-generated*"
+        result = "Probably AI-generated"
     else:
-        result = "Human-written*"
+        result = "Human-written"
 
     return result, perplexity
 
 
-# Async wrapper for text classification
-
-
-async def classify_text(sentence: str):
-    loop = asyncio.get_event_loop()
-    return await loop.run_in_executor(executor, classify_text_sync, sentence)
-
-
 # POST route to analyze text
 
 
 @app.post("/analyze")
-async def analyze_text(data: TextInput, authorization: str = Header(default="")):
-    verify_token(authorization)  # Token verification
+async def analyze_text(data: TextInput):
     user_input = data.text.strip()
-
     if not user_input:
         raise HTTPException(status_code=400, detail="Text cannot be empty")
 
-    result, perplexity = await classify_text(user_input)
+    # Run classification asynchronously to prevent blocking
+    result, perplexity = await asyncio.to_thread(classify_text, user_input)
 
     return {
         "result": result,
@@ -119,11 +106,8 @@ async def health_check():
 
 @app.get("/")
 def index():
-    return {"message": "It's an API"}
-
-
-# Start the app (run with uvicorn)
-if __name__ == "__main__":
-    import uvicorn
-
-    uvicorn.run("main:app", host="0.0.0.0", port=8000, workers=4)
+    return {
+        "message": "FastAPI API is up.",
+        "try": "/docs to test the API.",
+        "status": "OK",
+    }

requirements.txt

@@ -1,210 +1,7 @@
-absl-py==2.2.2
-accelerate==1.6.0
-aiohappyeyeballs==2.6.1
-aiohttp==3.11.16
-aiosignal==1.3.2
-altair==5.5.0
-annotated-types==0.7.0
-anyio==4.9.0
-argon2-cffi==23.1.0
-argon2-cffi-bindings==21.2.0
-arrow==1.3.0
-asgiref==3.8.1
-asttokens==3.0.0
-async-lru==2.0.5
-attrs==25.3.0
-babel==2.17.0
-beautifulsoup4==4.13.4
-bleach==6.2.0
-blinker==1.9.0
-cachetools==5.5.2
-certifi==2025.1.31
-cffi==1.17.1
-charset-normalizer==2.1.1
-click==8.1.8
-comm==0.2.2
-contourpy==1.3.1
-cycler==0.12.1
-datasets==3.5.0
-DateTime==4.7
-debugpy==1.8.13
-decorator==5.2.1
-defusedxml==0.7.1
-dill==0.3.8
-Django==5.2
-dotenv==0.9.9
-executing==2.2.0
-fastapi==0.115.12
-fastjsonschema==2.21.1
-filelock==3.13.1
-Flask==3.1.0
-flask-cors==5.0.1
-fonttools==4.56.0
-fqdn==1.5.1
-frozenlist==1.6.0
-fsspec==2024.6.1
-generativeai==0.0.1
-gitdb==4.0.12
-GitPython==3.1.44
-google-ai-generativelanguage==0.6.15
-google-api-core==2.24.2
-google-api-python-client==2.165.0
-google-auth==2.38.0
-google-auth-httplib2==0.2.0
-google-genai==1.7.0
-google-generativeai==0.8.4
-googleapis-common-protos==1.69.2
-grpcio==1.71.0
-grpcio-status==1.71.0
-h11==0.14.0
-h5py==3.13.0
-html5lib==1.1
-httpcore==1.0.7
-httplib2==0.22.0
-httpx==0.28.1
-huggingface-hub==0.30.2
-idna==3.10
-inquirerpy==0.3.4
-ipykernel==6.29.5
-ipython==9.0.2
-ipython_pygments_lexers==1.1.1
-isoduration==20.11.0
-itsdangerous==2.2.0
-jedi==0.19.2
-Jinja2==3.1.4
-joblib==1.4.2
-json5==0.12.0
-jsonpointer==3.0.0
-jsonschema==4.23.0
-jsonschema-specifications==2024.10.1
-jupyter-events==0.12.0
-jupyter-lsp==2.2.5
-jupyter_client==8.6.3
-jupyter_core==5.7.2
-jupyter_server==2.15.0
-jupyter_server_terminals==0.5.3
-jupyterlab==4.4.0
-jupyterlab_pygments==0.3.0
-jupyterlab_server==2.27.3
-keras==3.9.2
-kiwisolver==1.4.8
-markdown-it-py==3.0.0
-MarkupSafe==3.0.2
-matplotlib==3.10.1
-matplotlib-inline==0.1.7
-mdurl==0.1.2
-mechanize==0.4.10
-mistune==3.1.3
-ml_dtypes==0.5.1
-mpmath==1.3.0
-multidict==6.4.3
-multiprocess==0.70.16
-namex==0.0.8
-narwhals==1.35.0
-nbclient==0.10.2
-nbconvert==7.16.6
-nbformat==5.10.4
-nest-asyncio==1.6.0
-networkx==3.3
-notebook==7.4.0
-notebook_shim==0.2.4
-numpy==2.2.4
-nvidia-cublas-cu11==11.11.3.6
-nvidia-cuda-cupti-cu11==11.8.87
-nvidia-cuda-nvrtc-cu11==11.8.89
-nvidia-cuda-runtime-cu11==11.8.89
-nvidia-cudnn-cu11==9.1.0.70
-nvidia-cufft-cu11==10.9.0.58
-nvidia-curand-cu11==10.3.0.86
-nvidia-cusolver-cu11==11.4.1.48
-nvidia-cusparse-cu11==11.7.5.86
-nvidia-nccl-cu11==2.21.5
-nvidia-nvtx-cu11==11.8.86
-optree==0.15.0
-overrides==7.7.0
-packaging==24.2
-pandas==2.2.3
-pandocfilters==1.5.1
-parso==0.8.4
-pexpect==4.9.0
-pfzy==0.3.4
-pillow==11.1.0
-platformdirs==4.3.7
-prometheus_client==0.21.1
-prompt_toolkit==3.0.50
-propcache==0.3.1
-proto-plus==1.26.1
-protobuf==5.29.4
-psutil==7.0.0
-ptyprocess==0.7.0
-pure_eval==0.2.3
-pyarrow==19.0.1
-pyasn1==0.6.1
-pyasn1_modules==0.4.1
-pycparser==2.22
-pydantic==2.10.6
-pydantic_core==2.27.2
-pydeck==0.9.1
-pygame==2.6.1
-Pygments==2.19.1
-pyparsing==3.2.2
-pystyle==2.0
-python-dateutil==2.9.0.post0
-python-dotenv==1.1.0
-python-json-logger==3.3.0
-pytz==2025.1
-PyYAML==6.0.2
-pyzmq==26.3.0
-referencing==0.36.2
-regex==2024.11.6
-requests==2.32.3
-rfc3339-validator==0.1.4
-rfc3986-validator==0.1.1
-rich==14.0.0
-rpds-py==0.24.0
-rsa==4.9
-safetensors==0.5.3
-scikit-learn==1.6.1
-scipy==1.15.2
-seaborn==0.13.2
-Send2Trash==1.8.3
-setuptools==70.2.0
-six==1.17.0
-smmap==5.0.2
-sniffio==1.3.1
-soupsieve==2.6
-sqlparse==0.5.3
-stack-data==0.6.3
-starlette==0.46.2
-streamlit==1.44.1
-sympy==1.13.1
-tenacity==9.1.2
-terminado==0.18.1
-threadpoolctl==3.6.0
-tinycss2==1.4.0
-tokenizers==0.21.1
-toml==0.10.2
-torch==2.6.0+cu118
-torchaudio==2.6.0+cu118
-torchvision==0.21.0+cu118
-tornado==6.4.2
-tqdm==4.67.1
-traitlets==5.14.3
+torch==2.6.0
 transformers==4.51.3
-triton==3.2.0
-types-python-dateutil==2.9.0.20241206
-typing_extensions==4.12.2
-tzdata==2025.2
-uri-template==1.3.0
-uritemplate==4.1.1
-urllib3==1.26.20
-watchdog==6.0.0
-wcwidth==0.2.13
-webcolors==24.11.1
-webencodings==0.5.1
-websocket-client==1.8.0
-websockets==15.0.1
-Werkzeug==3.1.3
-xxhash==3.5.0
-yarl==1.20.0
-zope.interface==7.2
+fastapi==0.103.0
+pydantic==1.10.12
+asyncio==3.4.3
+uvicorn[standard]==0.21.1
+

test.sh

@@ -1 +0,0 @@
-echo "ok"