ai-data-summarizer 0.7.1__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (34) hide show
  1. ai_data_summarizer-0.7.1/.dockerignore +30 -0
  2. ai_data_summarizer-0.7.1/.env.sample +7 -0
  3. ai_data_summarizer-0.7.1/.github/workflows/update-licenses.yml +54 -0
  4. ai_data_summarizer-0.7.1/.gitignore +232 -0
  5. ai_data_summarizer-0.7.1/.idea/.gitignore +10 -0
  6. ai_data_summarizer-0.7.1/.idea/ai-data-summarizer.iml +14 -0
  7. ai_data_summarizer-0.7.1/.idea/inspectionProfiles/profiles_settings.xml +6 -0
  8. ai_data_summarizer-0.7.1/.idea/modules.xml +8 -0
  9. ai_data_summarizer-0.7.1/.idea/vcs.xml +6 -0
  10. ai_data_summarizer-0.7.1/.idea/workspace.xml +574 -0
  11. ai_data_summarizer-0.7.1/.vscode/settings.json +4 -0
  12. ai_data_summarizer-0.7.1/CONFIGURATION.md +36 -0
  13. ai_data_summarizer-0.7.1/Dockerfile +30 -0
  14. ai_data_summarizer-0.7.1/INSTALL.md +54 -0
  15. ai_data_summarizer-0.7.1/LICENSE +21 -0
  16. ai_data_summarizer-0.7.1/PKG-INFO +200 -0
  17. ai_data_summarizer-0.7.1/README.md +179 -0
  18. ai_data_summarizer-0.7.1/SECURITY.md +21 -0
  19. ai_data_summarizer-0.7.1/THIRD-PARTY-NOTICES.txt +4600 -0
  20. ai_data_summarizer-0.7.1/apicheck.py +86 -0
  21. ai_data_summarizer-0.7.1/envvar.py +99 -0
  22. ai_data_summarizer-0.7.1/examples/CTA_Ridership_RedLine_WrigleyField_DailyTotals.csv +9225 -0
  23. ai_data_summarizer-0.7.1/examples/OverviewPrompt_CTA_Ridership_RedLine_WrigleyField_DailyTotals.txt +32 -0
  24. ai_data_summarizer-0.7.1/examples/README.md +19 -0
  25. ai_data_summarizer-0.7.1/fileloader.py +142 -0
  26. ai_data_summarizer-0.7.1/main.py +155 -0
  27. ai_data_summarizer-0.7.1/profiler.py +108 -0
  28. ai_data_summarizer-0.7.1/prompt.py +144 -0
  29. ai_data_summarizer-0.7.1/pyproject.toml +49 -0
  30. ai_data_summarizer-0.7.1/requirements.txt +8 -0
  31. ai_data_summarizer-0.7.1/summarizer.py +109 -0
  32. ai_data_summarizer-0.7.1/test_profile.py +20 -0
  33. ai_data_summarizer-0.7.1/tokenizer.py +48 -0
  34. ai_data_summarizer-0.7.1/uv.lock +1052 -0
@@ -0,0 +1,30 @@
1
+ # Git
2
+ .git
3
+ .gitignore
4
+
5
+ # Python cache/venvs
6
+ __pycache__/
7
+ *.py[cod]
8
+ *.pyo
9
+ *.pyd
10
+ .pytest_cache/
11
+ .mypy_cache/
12
+ .ruff_cache/
13
+ .venv/
14
+
15
+ # Environment/secrets
16
+ .env
17
+ .env.*
18
+ !.env.sample
19
+
20
+ # Build/output artifacts
21
+ build/
22
+ dist/
23
+ *.egg-info/
24
+ summaries/
25
+
26
+ # Editor/OS
27
+ .vscode/
28
+ .idea/
29
+ .DS_Store
30
+ Thumbs.db
@@ -0,0 +1,7 @@
1
+ # SPDX-License-Identifier: MIT
2
+ # RENAME THIS FILE TO .env BEFORE USE!
3
+ GEMINI_API_KEY=""
4
+ OPENAI_API_KEY=""
5
+ ANTHROPIC_API_KEY=""
6
+ GEMINI_FREE_TIER=True
7
+ # Defaults to True, set to False if you pay for the Gemini API.
@@ -0,0 +1,54 @@
1
+ name: Update Third-Party Notices
2
+
3
+ on:
4
+ push:
5
+ branches:
6
+ - main
7
+ paths:
8
+ - "pyproject.toml"
9
+
10
+ permissions:
11
+ contents: write
12
+
13
+ jobs:
14
+ update-notices:
15
+ runs-on: ubuntu-latest
16
+
17
+ steps:
18
+ - name: Check out repository
19
+ uses: actions/checkout@v4
20
+
21
+ - name: Set up Python
22
+ uses: actions/setup-python@v5
23
+ with:
24
+ python-version: "3.14"
25
+
26
+ - name: Install project dependencies
27
+ run: |
28
+ python -m pip install --upgrade pip
29
+ pip install -r requirements.txt
30
+
31
+ - name: Install pip-licenses
32
+ run: |
33
+ pip install pip-licenses
34
+
35
+ - name: Generate THIRD-PARTY-NOTICES.txt
36
+ run: |
37
+ pip-licenses \
38
+ --format=plain-vertical \
39
+ --with-license-file \
40
+ --no-license-path \
41
+ --output-file=THIRD-PARTY-NOTICES.txt
42
+
43
+ - name: Commit changes
44
+ run: |
45
+ if git status --porcelain -- THIRD-PARTY-NOTICES.txt | grep -q '^'; then
46
+ git config user.name "github-actions[bot]"
47
+ git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
48
+
49
+ git add THIRD-PARTY-NOTICES.txt
50
+ git commit -m "chore: update third-party notices"
51
+ git push
52
+ else
53
+ echo "THIRD-PARTY-NOTICES.txt is already up to date."
54
+ fi
@@ -0,0 +1,232 @@
1
+ # Byte-compiled / optimized / DLL files
2
+ __pycache__/
3
+ *.py[codz]
4
+ *$py.class
5
+
6
+ # C extensions
7
+ *.so
8
+
9
+ # Distribution / packaging
10
+ .Python
11
+ build/
12
+ develop-eggs/
13
+ dist/
14
+ downloads/
15
+ eggs/
16
+ .eggs/
17
+ lib/
18
+ lib64/
19
+ parts/
20
+ sdist/
21
+ var/
22
+ wheels/
23
+ share/python-wheels/
24
+ *.egg-info/
25
+ .installed.cfg
26
+ *.egg
27
+ MANIFEST
28
+
29
+ # PyInstaller
30
+ # Usually these files are written by a python script from a template
31
+ # before PyInstaller builds the exe, so as to inject date/other infos into it.
32
+ *.manifest
33
+ *.spec
34
+
35
+ # Installer logs
36
+ pip-log.txt
37
+ pip-delete-this-directory.txt
38
+
39
+ # Unit test / coverage reports
40
+ htmlcov/
41
+ .tox/
42
+ .nox/
43
+ .coverage
44
+ .coverage.*
45
+ .cache
46
+ nosetests.xml
47
+ coverage.xml
48
+ *.cover
49
+ *.py.cover
50
+ .hypothesis/
51
+ .pytest_cache/
52
+ cover/
53
+
54
+ # Translations
55
+ *.mo
56
+ *.pot
57
+
58
+ # Django stuff:
59
+ *.log
60
+ local_settings.py
61
+ db.sqlite3
62
+ db.sqlite3-journal
63
+
64
+ # Flask stuff:
65
+ instance/
66
+ .webassets-cache
67
+
68
+ # Scrapy stuff:
69
+ .scrapy
70
+
71
+ # Sphinx documentation
72
+ docs/_build/
73
+
74
+ # PyBuilder
75
+ .pybuilder/
76
+ target/
77
+
78
+ # Jupyter Notebook
79
+ .ipynb_checkpoints
80
+
81
+ # IPython
82
+ profile_default/
83
+ ipython_config.py
84
+
85
+ # pyenv
86
+ # For a library or package, you might want to ignore these files since the code is
87
+ # intended to run in multiple environments; otherwise, check them in:
88
+ # .python-version
89
+
90
+ # pipenv
91
+ # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
92
+ # However, in case of collaboration, if having platform-specific dependencies or dependencies
93
+ # having no cross-platform support, pipenv may install dependencies that don't work, or not
94
+ # install all needed dependencies.
95
+ # Pipfile.lock
96
+
97
+ # UV
98
+ # Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
99
+ # This is especially recommended for binary packages to ensure reproducibility, and is more
100
+ # commonly ignored for libraries.
101
+ # uv.lock
102
+
103
+ # poetry
104
+ # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
105
+ # This is especially recommended for binary packages to ensure reproducibility, and is more
106
+ # commonly ignored for libraries.
107
+ # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
108
+ # poetry.lock
109
+ # poetry.toml
110
+
111
+ # pdm
112
+ # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
113
+ # pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
114
+ # https://pdm-project.org/en/latest/usage/project/#working-with-version-control
115
+ # pdm.lock
116
+ # pdm.toml
117
+ .pdm-python
118
+ .pdm-build/
119
+
120
+ # pixi
121
+ # Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
122
+ # pixi.lock
123
+ # Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
124
+ # in the .venv directory. It is recommended not to include this directory in version control.
125
+ .pixi
126
+
127
+ # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
128
+ __pypackages__/
129
+
130
+ # Celery stuff
131
+ celerybeat-schedule
132
+ celerybeat.pid
133
+
134
+ # Redis
135
+ *.rdb
136
+ *.aof
137
+ *.pid
138
+
139
+ # RabbitMQ
140
+ mnesia/
141
+ rabbitmq/
142
+ rabbitmq-data/
143
+
144
+ # ActiveMQ
145
+ activemq-data/
146
+
147
+ # SageMath parsed files
148
+ *.sage.py
149
+
150
+ # Environments
151
+ .env
152
+ .envrc
153
+ .venv
154
+ env/
155
+ venv/
156
+ ENV/
157
+ env.bak/
158
+ venv.bak/
159
+ creds.py
160
+
161
+ # Spyder project settings
162
+ .spyderproject
163
+ .spyproject
164
+
165
+ # Rope project settings
166
+ .ropeproject
167
+
168
+ # mkdocs documentation
169
+ /site
170
+
171
+ # mypy
172
+ .mypy_cache/
173
+ .dmypy.json
174
+ dmypy.json
175
+
176
+ # Pyre type checker
177
+ .pyre/
178
+
179
+ # pytype static type analyzer
180
+ .pytype/
181
+
182
+ # Cython debug symbols
183
+ cython_debug/
184
+
185
+ # PyCharm
186
+ # JetBrains specific template is maintained in a separate JetBrains.gitignore that can
187
+ # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
188
+ # and can be added to the global gitignore or merged into this file. For a more nuclear
189
+ # option (not recommended) you can uncomment the following to ignore the entire idea folder.
190
+ # .idea/
191
+
192
+ # Abstra
193
+ # Abstra is an AI-powered process automation framework.
194
+ # Ignore directories containing user credentials, local state, and settings.
195
+ # Learn more at https://abstra.io/docs
196
+ .abstra/
197
+
198
+ # Visual Studio Code
199
+ .vscode/*
200
+ !.vscode/settings.json
201
+ !.vscode/tasks.json
202
+ !.vscode/launch.json
203
+ !.vscode/extensions.json
204
+ !.vscode/*.code-snippets
205
+ !*.code-workspace
206
+
207
+ # Built Visual Studio Code Extensions
208
+ *.vsix
209
+
210
+ # Temporary file for partial code execution
211
+ tempCodeRunnerFile.py
212
+
213
+ # Ruff stuff:
214
+ .ruff_cache/
215
+
216
+ # PyPI configuration file
217
+ .pypirc
218
+
219
+ # Marimo
220
+ marimo/_static/
221
+ marimo/_lsp/
222
+ __marimo__/
223
+
224
+ # Streamlit
225
+ .streamlit/secrets.toml
226
+
227
+
228
+ # Dev Containers
229
+ .devcontainer
230
+ .devcontainer/*
231
+
232
+ summaries/*
@@ -0,0 +1,10 @@
1
+ # Default ignored files
2
+ /shelf/
3
+ /workspace.xml
4
+ # Editor-based HTTP Client requests
5
+ /httpRequests/
6
+ # Ignored default folder with query files
7
+ /queries/
8
+ # Datasource local storage ignored files
9
+ /dataSources/
10
+ /dataSources.local.xml
@@ -0,0 +1,14 @@
1
+ <?xml version="1.0" encoding="UTF-8"?>
2
+ <module external.system.id="pyproject.toml" type="PYTHON_MODULE" version="4">
3
+ <component name="NewModuleRootManager">
4
+ <content url="file://$MODULE_DIR$">
5
+ <excludeFolder url="file://$MODULE_DIR$/.venv" />
6
+ </content>
7
+ <orderEntry type="jdk" jdkName="~/PycharmProjects/ai-data-summarizer/.venv" jdkType="Python SDK" />
8
+ <orderEntry type="sourceFolder" forTests="false" />
9
+ </component>
10
+ <component name="PyDocumentationSettings">
11
+ <option name="format" value="PLAIN" />
12
+ <option name="myDocStringFormat" value="Plain" />
13
+ </component>
14
+ </module>
@@ -0,0 +1,6 @@
1
+ <component name="InspectionProjectProfileManager">
2
+ <settings>
3
+ <option name="USE_PROJECT_PROFILE" value="false" />
4
+ <version value="1.0" />
5
+ </settings>
6
+ </component>
@@ -0,0 +1,8 @@
1
+ <?xml version="1.0" encoding="UTF-8"?>
2
+ <project version="4">
3
+ <component name="ProjectModuleManager">
4
+ <modules>
5
+ <module fileurl="file://$PROJECT_DIR$/.idea/ai-data-summarizer.iml" filepath="$PROJECT_DIR$/.idea/ai-data-summarizer.iml" />
6
+ </modules>
7
+ </component>
8
+ </project>
@@ -0,0 +1,6 @@
1
+ <?xml version="1.0" encoding="UTF-8"?>
2
+ <project version="4">
3
+ <component name="VcsDirectoryMappings">
4
+ <mapping directory="" vcs="Git" />
5
+ </component>
6
+ </project>