add data generator with cohere

.gitignore

@@ -0,0 +1,161 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.DS_Store
+.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/

app.py

@@ -0,0 +1,51 @@
+import gradio as gr
+import cohere
+import os
+from dotenv import load_dotenv, find_dotenv
+
+_ = load_dotenv(find_dotenv()) # read local .env file
+cohere_api_key = os.environ['COHERE_API']
+co = cohere.Client(cohere_api_key)
+
+
+def generate_data(data_src):
+
+    command_prompt= f'''This is a sample dataset in csv below, and I want you to help me generate more data with different variations (at least 100 examples) 
+
+    ```csv
+    {data_src}
+    ```'''
+
+    response = co.generate(
+                  model='command',
+                  prompt=command_prompt,
+                  max_tokens=2606,
+                  temperature=0.9,
+                  k=0,
+                  stop_sequences=[],
+                  return_likelihoods='NONE')
+    
+    txt_response = response.generations[0].text
+    txt_split_1 = txt_response.split("```csv")
+    txt_split_2 = txt_split_1[1].split("```")
+    data_text = txt_split_2[0]
+
+    return data_text
+
+
+data_example = '''QUERY_TEXT,POSITIVE,NEGATIVE
+desserts, shakes,veggie burger with cheeese
+sushi, thai chef fresh rolls, meat lasagna
+acai bowl, acai bowl delivered, mint chocolate chip polar pizza
+cupcake, carrot, buffalo chicken'''
+
+
+demo = gr.Interface(fn=generate_data,
+                    inputs=[gr.Textbox(label="Paste your sample data here", lines=3)],
+                    outputs=[gr.Textbox(label="Data Generated Here", lines=5)],
+                    title="Data Generator with Cohere",
+                    description="Generating new dataset using the Cohere API under the hood!",
+                    allow_flagging="never",
+                    #Here we introduce a new tag, examples, easy to use examples for your application
+                    examples=[data_example])
+demo.launch()

requirements.txt

@@ -0,0 +1,3 @@
+cohere 
+gradio
+python-dotenv