"""Publish ReviewGuard to Hugging Face: the app as a Space and the trained models as a model repo. The Space runs the app in the cloud, and the model repo lets anyone skip retraining. Uploads use the token saved by `hf auth login`. """ import shutil import tempfile from pathlib import Path from huggingface_hub import HfApi, snapshot_download from reviewguard import config SPACE_ID = "Emirinth/ReviewGuard" MODEL_REPO_ID = "Emirinth/ReviewGuard-models" # Training leftovers that are not needed to run the models. SKIPPED_MODEL_FILES = ["*training_args.bin", "roberta_checkpoints/*"] # Spaces read their settings from the front matter of README.md. SPACE_README = """--- title: ReviewGuard emoji: 🛡️ colorFrom: indigo colorTo: red sdk: gradio sdk_version: {gradio_version} python_version: "3.12" app_file: app.py pinned: false short_description: AI triage for retail reviews and customer photos --- # ReviewGuard AI triage for retail reviews: sentiment, issue type and photo checks combined into one decision. """ # The CPU build of PyTorch is far smaller than the default GPU build. SPACE_REQUIREMENTS = """--extra-index-url https://download.pytorch.org/whl/cpu torch transformers accelerate captum sentence-transformers textblob vaderSentiment joblib pandas pyarrow scikit-learn matplotlib plotly pillow """ ARTIFACT_FOLDERS = ["reports", "examples", "labels"] def stage_space(folder: Path) -> None: """Copy everything the Space needs into one folder.""" import gradio shutil.copy(config.CODE_DIR / "app.py", folder / "app.py") shutil.copytree( config.CODE_DIR / "reviewguard", folder / "reviewguard", ignore=shutil.ignore_patterns("__pycache__"), ) (folder / "README.md").write_text( SPACE_README.format(gradio_version=gradio.__version__), encoding="utf-8" ) (folder / "requirements.txt").write_text(SPACE_REQUIREMENTS, encoding="utf-8") artifacts = folder / "artifacts" for name in ARTIFACT_FOLDERS: shutil.copytree(config.ARTIFACTS_DIR / name, artifacts / name) shutil.copytree( config.MODELS_DIR, artifacts / "models", ignore=shutil.ignore_patterns("training_args.bin", "roberta_checkpoints"), ) def deploy() -> str: """Create the Space if needed, upload the staged folder and return the Space URL.""" api = HfApi() api.create_repo(SPACE_ID, repo_type="space", space_sdk="gradio", exist_ok=True) with tempfile.TemporaryDirectory() as temp: stage_space(Path(temp)) api.upload_folder( folder_path=temp, repo_id=SPACE_ID, repo_type="space", commit_message="Deploy ReviewGuard", delete_patterns=["*"], ) return f"https://huggingface.co/spaces/{SPACE_ID}" # ---------------------------------------------------------------- trained models MODEL_CARD = """--- license: mit tags: [sentiment-analysis, retail, reviews, text-classification] --- # ReviewGuard trained models Models behind the ReviewGuard review-triage app. - `roberta_sentiment/`: RoBERTa fine-tuned on 72,000 Amazon Reviews 2023 reviews. It predicts negative, neutral or positive. - `distilroberta_sentiment/`: a smaller, faster version trained the same way. - `classical/`: TF-IDF with Naive Bayes and Logistic Regression baselines. - `issue_student.joblib`: issue classifier distilled from a zero-shot teacher. - `photo_calibration.json` and `lexicon_bands.json`: calibration and tuning settings. Download them into the project with `python pipeline.py fetch-models`. """ def publish_models() -> str: """Upload the trained models and a short model card, then return the repo URL.""" api = HfApi() api.create_repo(MODEL_REPO_ID, repo_type="model", exist_ok=True) api.upload_file( path_or_fileobj=MODEL_CARD.encode("utf-8"), path_in_repo="README.md", repo_id=MODEL_REPO_ID, repo_type="model", ) api.upload_folder( folder_path=str(config.MODELS_DIR), repo_id=MODEL_REPO_ID, repo_type="model", ignore_patterns=SKIPPED_MODEL_FILES, commit_message="Upload trained ReviewGuard models", ) return f"https://huggingface.co/{MODEL_REPO_ID}" def fetch_models() -> str: """Download the published models into the local models folder. Returns the folder they were saved to. """ config.MODELS_DIR.mkdir(parents=True, exist_ok=True) return snapshot_download(MODEL_REPO_ID, repo_type="model", local_dir=str(config.MODELS_DIR))