v 0.0.1

.gitignore

@@ -0,0 +1,165 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$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
+
+# 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
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+env_dev/
+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/
+.DS_Store
+actilex/private_dossiers/
+actilex/core/credentials.json
+actilex/core/token.json

app.py

@@ -3,9 +3,8 @@ import requests
 import streamlit as st
 from huggingface_hub import InferenceClient
 from prompt import default_prompt, prompt_enhanced
-from transformers import GPT2Tokenizer
-# Initialize LLaMA tokenizer
-tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
+
+
 # Function to load the README.md directly from the Hugging Face API
 def load_readme(dataset_name: str):
     api_url = f"https://huggingface.co/datasets/{dataset_name}/raw/main/README.md"
@@ -21,9 +20,8 @@ def load_readme(dataset_name: str):
 
 # Function to check if the README content exceeds the token limit
 def check_token_limit(content: str, max_tokens: int = 7500):
-    tokens = tokenizer.encode(content)
-    if len(tokens) > max_tokens:
-        truncated_content = tokenizer.decode(tokens[:max_tokens])
+    if len(content)//4 > max_tokens:
+        truncated_content = content[:max_tokens]
         st.warning("Warning: The README.md exceeds 8192 tokens. It has been truncated for evaluation. This may affect the quality of the evaluation results.")
         return truncated_content
     return content

requirements.txt

@@ -1 +1,46 @@
-transformers
+altair==5.4.1
+attrs==24.2.0
+blinker==1.8.2
+cachetools==5.5.0
+certifi==2024.8.30
+charset-normalizer==3.4.0
+click==8.1.7
+filelock==3.16.1
+fsspec==2024.9.0
+gitdb==4.0.11
+GitPython==3.1.43
+huggingface-hub==0.25.2
+idna==3.10
+Jinja2==3.1.4
+jsonschema==4.23.0
+jsonschema-specifications==2024.10.1
+markdown-it-py==3.0.0
+MarkupSafe==3.0.1
+mdurl==0.1.2
+narwhals==1.9.3
+numpy==2.1.2
+packaging==24.1
+pandas==2.2.3
+pillow==10.4.0
+protobuf==5.28.2
+pyarrow==17.0.0
+pydeck==0.9.1
+Pygments==2.18.0
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+pytz==2024.2
+PyYAML==6.0.2
+referencing==0.35.1
+requests==2.32.3
+rich==13.9.2
+rpds-py==0.20.0
+six==1.16.0
+smmap==5.0.1
+streamlit==1.39.0
+tenacity==9.0.0
+toml==0.10.2
+tornado==6.4.1
+tqdm==4.66.5
+typing_extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3