Auto uoload to HF Hub

.gitignore

@@ -0,0 +1,162 @@
+# 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/
+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/
+
+datasets/

app.py

@@ -1,6 +1,31 @@
 import gradio as gr
+from datasets import load_dataset
 from chatgpt_conversation_parser.main import fetch_and_parse_conversation
 
+
+def add_to_dataset(title, data):
+    dataset = load_dataset("beratcmn/parse-gpt-tr", cache_dir="./datasets")
+    model = data[0]["model"]["slug"]
+    id = data[0]["id"]
+
+    for message in data:
+        del message["model"]
+        del message["id"]
+
+    data_dict = {"id": id, "model": model, "messages": data}
+
+    dataset = dataset["train"].add_item(data_dict)
+    dataset.push_to_hub("beratcmn/parse-gpt-tr")
+
+
+def action(url, cb):
+    result = fetch_and_parse_conversation(url)
+    title, data = result
+    yield result
+    if cb:
+        add_to_dataset(title, data)
+
+
 with gr.Blocks() as demo:
     gr.Markdown(
         """
@@ -13,8 +38,14 @@ with gr.Blocks() as demo:
     )
 
     gr.Interface(
-        fn=fetch_and_parse_conversation,
-        inputs=["text"],
+        fn=action,
+        inputs=[
+            "text",
+            gr.Checkbox(
+                True,
+                label="Add this conversation to the public dataset?",
+            ),
+        ],
         outputs=[gr.DownloadButton(label="Download JSONL"), gr.JSON()],
     )
 

chatgpt_conversation_parser

@@ -1 +1 @@
-Subproject commit 14c28efd537a8cfca12b11eef55d1fe62b02ca5a
+Subproject commit 930e49e29033ac450890452bee18a3f4524886d4

requirements.txt

@@ -1,7 +1,10 @@
 aiofiles==23.2.1
+aiohttp==3.9.3
+aiosignal==1.3.1
 altair==5.2.0
 annotated-types==0.6.0
 anyio==4.3.0
+async-timeout==4.0.3
 attrs==23.2.0
 beautifulsoup4==4.12.3
 certifi==2024.2.2
@@ -10,12 +13,15 @@ click==8.1.7
 colorama==0.4.6
 contourpy==1.2.0
 cycler==0.12.1
+datasets==2.18.0
+dill==0.3.8
 exceptiongroup==1.2.0
 fastapi==0.110.0
 ffmpy==0.3.2
 filelock==3.13.1
 fonttools==4.50.0
-fsspec==2024.3.0
+frozenlist==1.4.1
+fsspec==2024.2.0
 gradio==4.21.0
 gradio-client==0.12.0
 h11==0.14.0
@@ -32,11 +38,15 @@ markdown-it-py==3.0.0
 markupsafe==2.1.5
 matplotlib==3.8.3
 mdurl==0.1.2
+multidict==6.0.5
+multiprocess==0.70.16
 numpy==1.26.4
 orjson==3.9.15
 packaging==24.0
 pandas==2.2.1
 pillow==10.2.0
+pyarrow==15.0.1
+pyarrow-hotfix==0.6
 pydantic==2.6.4
 pydantic-core==2.16.3
 pydub==0.25.1
@@ -66,3 +76,5 @@ tzdata==2024.1
 urllib3==2.2.1
 uvicorn==0.28.0
 websockets==11.0.3
+xxhash==3.4.1
+yarl==1.9.4