PromptSource
github.com
Spec sheet
- Purpose
- PromptSource is a toolkit for creating, sharing, and using natural language prompts.Read 9 Oct 2026 · github.com
- API
- The API provides Template, Metadata, DatasetTemplates, and TemplateCollection classes to store, manipulate, and use prompts and metadata.Read 9 Oct 2026 · github.com
- License
- The public repository is licensed under Apache-2.0.Read 9 Oct 2026 · github.com
- App modes
- The app has Sourcing, Prompted dataset viewer, and Helicopter view modes.Read 9 Oct 2026 · github.com
- Dataset integration
- Prompts can be applied to examples from the Hugging Face Datasets library.Read 9 Oct 2026 · github.com
- Hosted access
- The README links to hosted versions for browsing existing prompts and notes that the BigScience hosted app disables Sourcing mode.Read 9 Oct 2026 · github.com
- Hosted version
- The README links to a hosted version for browsing existing prompts and says its Sourcing mode is disabled.Read 9 Oct 2026 · github.com
- Installation
- The README gives pip install promptsource as an installation command for users who do not intend to create new prompts.Read 9 Oct 2026 · github.com
- Intended audience
- The package metadata lists developers as the intended audience.Read 9 Oct 2026 · github.com
- 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.Read 9 Oct 2026 · github.com
- Local app
- The README says to launch the app locally with streamlit run promptsource/app.py after completing setup.Read 9 Oct 2026 · github.com
- Local install
- The README gives pip install promptsource as an installation option and documents launching the app locally with Streamlit.Read 9 Oct 2026 · github.com
- Manual dataset setup
- Some datasets require manual download into ~/.cache/promptsource by default, and the path can be changed with PROMPTSOURCE_MANUAL_DATASET_DIR.Read 9 Oct 2026 · github.com
- Manual datasets
- Some datasets require manual download into ~/.cache/promptsource by default, and the location can be overridden with PROMPTSOURCE_MANUAL_DATASET_DIR.Read 9 Oct 2026 · github.com
- Prompt collection
- The README describes a collection of about 2,000 English prompts for more than 170 English datasets as of January 20, 2022.Read 9 Oct 2026 · github.com
- Prompt editor
- Its web-based GUI lets developers write prompts in a templating language and view outputs on examples.Read 9 Oct 2026 · github.com
- Prompt format
- Prompts are stored in standalone structured files and written in Jinja.Read 9 Oct 2026 · github.com
- 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.Read 9 Oct 2026 · github.com
- Prompt metadata
- Prompt metadata can include the original task flag, whether answer choices appear in the prompt, and evaluation metrics.Read 9 Oct 2026 · github.com
- Runtime requirement
- The package metadata specifies Python >=3.7,<4.0, and the README says creating prompts through the interface currently requires Python 3.7 for stability.Read 9 Oct 2026 · github.com
Where Specifiction places it
- Prompting Tool#9 of 256.9
- AI Prompt Generators#22 of 287.0
- Prompt Management Software#25 of 267.0