- Home
- Prompting Tool
- PromptSource
On the recordRead 9 Oct 202620 facts
PromptSource
On the record
- API
- The API provides Template, Metadata, DatasetTemplates, and TemplateCollection classes to store, manipulate, and use prompts and metadata.github.com · read 9 Oct 2026
- App modes
- The app has Sourcing, Prompted dataset viewer, and Helicopter view modes.github.com · read 9 Oct 2026
- Dataset integration
- Prompts can be applied to examples from the Hugging Face Datasets library.github.com · read 9 Oct 2026
- Hosted access
- The README links to hosted versions for browsing existing prompts and notes that the BigScience hosted app disables Sourcing mode.github.com · read 9 Oct 2026
- Hosted version
- The README links to a hosted version for browsing existing prompts and says its Sourcing mode is disabled.github.com · read 9 Oct 2026
- Installation
- The README gives pip install promptsource as an installation command for users who do not intend to create new prompts.github.com · read 9 Oct 2026
- Intended audience
- The package metadata lists developers as the intended audience.github.com · read 9 Oct 2026
- Intended contributors
- The contribution guide says a way to grow P3 is to write prompts for new datasets and submit them in a pull request.github.com · read 9 Oct 2026
- License
- The public repository is licensed under Apache-2.0.github.com · read 9 Oct 2026
- Local app
- The README says to launch the app locally with streamlit run promptsource/app.py after completing setup.github.com · read 9 Oct 2026
- Local install
- The README gives pip install promptsource as an installation option and documents launching the app locally with Streamlit.github.com · read 9 Oct 2026
- Manual datasets
- Some datasets require manual download into ~/.cache/promptsource by default, and the location can be overridden with PROMPTSOURCE_MANUAL_DATASET_DIR.github.com · read 9 Oct 2026
- Manual dataset setup
- Some datasets require manual download into ~/.cache/promptsource by default, and the path can be changed with PROMPTSOURCE_MANUAL_DATASET_DIR.github.com · read 9 Oct 2026
- Prompt collection
- The README describes a collection of about 2,000 English prompts for more than 170 English datasets as of January 20, 2022.github.com · read 9 Oct 2026
- Prompt editor
- Its web-based GUI lets developers write prompts in a templating language and view outputs on examples.github.com · read 9 Oct 2026
- Prompt format
- Prompts are stored in standalone structured files and written in Jinja.github.com · read 9 Oct 2026
- Prompt library
- The repository describes a collection called P3, with about 2,000 English prompts for more than 170 English datasets as of January 20, 2022.github.com · read 9 Oct 2026
- Prompt metadata
- Prompt metadata can include the original task flag, whether answer choices appear in the prompt, and evaluation metrics.github.com · read 9 Oct 2026
