base

.gitignore

@@ -0,0 +1,216 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer,
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml

.ruff.toml

@@ -0,0 +1,52 @@
+line-length = 87
+target-version = "py313"
+src = ["src"]
+
+include = ["src/**.py"]
+
+lint.select = [
+    "ALL"
+]
+lint.ignore = [
+    "ARG",
+    "ANN",
+    "D",
+    "EM101",
+    "EM102",
+    "PT001",
+    "PT023",
+    "SIM108",
+    "RET505",
+    "PLR0913",
+    "SIM103",
+    "ISC003",
+
+    # identitcal by code != identical by meaning
+    "SIM114",
+
+    # awful things, never use.
+    # It makes runtime work differently from typechecker
+    "TC001",
+    "TC002",
+    "TC003",
+    "TC006",
+
+    # only affects perfomance and brings nothing useful
+    "UP038",
+    "PGH003",
+    "TRY003",
+    "F401",
+    "TD003",
+    "FBT002",
+    "FBT001",
+    "E701",
+    "RUF001",
+    "ERA001",
+    "PERF401"
+]
+
+[lint.isort]
+no-lines-before = ["local-folder"]
+
+[lint.flake8-tidy-imports]
+ban-relative-imports = "parents"

README.md

@@ -1,12 +1,17 @@
 ---
+<<<<<<< HEAD
 title: Lsb Antispam
 emoji: 📚
 colorFrom: indigo
 colorTo: green
+=======
+title: Luana Support Bot [Antispam]
+emoji: 🔍
+colorFrom: blue
+colorTo: purple
+>>>>>>> 9da1c83 (improvements)
 sdk: docker
 pinned: false
 license: mit
 short_description: Antispam API for t.me/LuanaSupportBot
 ---
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

pyproject.toml

@@ -0,0 +1,21 @@
+[project]
+name = "lsb-antispam"
+version = "0.1.0"
+requires-python = ">=3.13"
+dependencies = [
+    "accelerate>=1.10.1",
+    "blacksheep>=2.4.0",
+    "granian>=2.5.1",
+    "loguru>=0.7.3",
+    "msgspec>=0.19.0",
+    "numpy>=2.3.2",
+    "protobuf>=6.32.0",
+    "sentencepiece>=0.2.1",
+    "torch>=2.8.0",
+    "transformers>=4.55.4",
+]
+
+[project.optional-dependencies]
+dev = [
+    "ruff>=0.12.10",
+]

src/antispam_api/__init__.py

@@ -0,0 +1 @@
+__version__ = (0, 1, 0)

src/antispam_api/config.py

@@ -0,0 +1,8 @@
+import os
+
+LABELS = {
+    "LABEL_1": True,
+    "LABEL_0": False,
+}
+API_KEY = os.getenv("API_KEY")
+MODEL_NAME = os.getenv("MODEL_NAME", "mshenoda/roberta-spam")

src/antispam_api/loader.py

@@ -0,0 +1,23 @@
+import torch
+from loguru import logger
+from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline
+
+from antispam_api.config import MODEL_NAME
+
+try:
+    logger.info(f"Loading model {MODEL_NAME!r}")
+    tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+    model = AutoModelForSequenceClassification.from_pretrained(
+        MODEL_NAME,
+        torch_dtype=torch.float32,
+        device_map="auto",
+        low_cpu_mem_usage=True,
+    )
+    generator = pipeline(
+        "text-classification",
+        model=model,
+        tokenizer=tokenizer,
+    )
+except Exception as e:  # noqa: BLE001
+    logger.error(f"Model loading error: {e}")
+    generator = None

src/antispam_api/main.py

@@ -0,0 +1,55 @@
+from http import HTTPStatus
+
+import msgspec
+from blacksheep import Application, Request
+from blacksheep.server.bindings import FromJSON
+from blacksheep.server.responses import json
+from loguru import logger
+
+from antispam_api.config import API_KEY, LABELS
+from antispam_api.loader import generator
+
+app = Application()
+
+
+class RequestData(msgspec.Struct):
+    message: str
+
+
+@app.router.post("/check")
+async def check_message(request: Request, data: FromJSON[RequestData]):
+    logger.info("New request: {}", {"message": data.value.message})
+
+    key = request.headers.get_first(b"x-api-key")
+    if not key:
+        logger.warning("Tried to request without key!")
+        return json({"detail": "No API key provided"}, status=HTTPStatus.UNAUTHORIZED)
+
+    if key.decode() != API_KEY:
+        return json({"detail": "Incorrect API key"}, status=HTTPStatus.UNAUTHORIZED)
+
+    if not generator:
+        logger.error("Model not loaded")
+        return json(
+            {"detail": "Model not loaded"},
+            status=HTTPStatus.SERVICE_UNAVAILABLE,
+        )
+
+    try:
+        output = generator(data.value.message)
+        result = {
+            "is_spam": LABELS[output[0]["label"]],
+            "score": output[0]["score"],
+        }
+        logger.info("Returning: {}", result)
+        return json(result)
+    except Exception as e:  # noqa: BLE001
+        logger.error("Error while checking message: {!r}", str(e))
+        return json({"detail": str(e)}, status=HTTPStatus.INTERNAL_SERVER_ERROR)
+
+
+@app.router.get("/")
+async def health_check():
+    status = "ok" if generator else "unavailable"
+    logger.info("Server status: {}", status)
+    return json({"status": status})