prismAId uses generative AI models to extract data from scientific literature.
It offers simple-to-use, efficient, and replicable methods for analyzing literature when conducting systematic reviews.
No coding skills are required to use prismAId.
- Review protocol: Designed to support any literature review protocol with a preference for Prisma 2020, which inspired our project name.
- Distribution: Go package, Python package, R package, Julia package, and 'no-coding' binaries compatible with Windows, MacOS, and Linux operating systems on AMD64 and ARM64 platforms.
- Supported LLMs:
- OpenAI: GPT-3.5 Turbo, GPT-4 Turbo, GPT-4o, and GPT-4o Mini.
- GoogleAI: Gemini 1.0 Pro, Gemini 1.5 Pro, and Gemini 1.5 Flash.
- Cohere: Command, Command Light, Command R, and Command R+.
- Anthropic: Claude 3 Sonnet, Claude 3 Opus, Claude 3 Haiku, Claude 3.5 Haiku, Claude 3.5 Sonnet.
- Output format: Outputs data in CSV or JSON formats.
- Performance: Designed to process extensive datasets efficiently with minimal user setup and no coding required.
- Programming Language: Developed in Go.
All the information to install, use, and improve prismAId can be found at open-and-sustainable.github.io/prismaid.
Riccardo Boero - ribo@nilu.no
This project was initiated with the generous support of a SIS internal project from NILU. Their support was crucial in starting this research and development effort. Further, acknowledgment is due for the research credits received from the OpenAI Researcher Access Program and the Cohere For AI Research Grant Program, both of which have significantly contributed to the advancement of this work.
GNU AFFERO GENERAL PUBLIC LICENSE, Version 3
Contributions are welcome! Please follow guidelines at open-and-sustainable.github.io/prismaid/research-development.html.
Boero, R. (2024). prismAId - Open Science AI Tools for Systematic, Protocol-Based Literature Reviews. Zenodo. DOI: 10.5281/zenodo.11210796