What's new
Since v1.0.1, we haven't been very active when it comes to releases 😇 However, we worked hard on the application itself 💪
The current release **1.1.0** thus brings **many significant improvements**, some of which are detailed below, and **many important bugfixes**.
> [!IMPORTANT]
> We recommend that you use this version only for a fresh instance. The data generated by the older version of factgenie is most probably not compatible with the current version and vice versa.
🌈 Annotation interface
- _New annotation library_ (177, 192, 194, 210): We built our own underlying JS annotation library. That allowed us to introduce better visual style, better colors, "undo" functionality, erase / select mode, overlapping annotations, and more.
[<img src="https://github.com/user-attachments/assets/af4627f2-3ada-45ed-bb9d-8bd622930496" width="200px">](https://github.com/user-attachments/assets/539d7c12-f43b-4c44-afed-ce8ca1ceba56)
- _Refactored sliders_ (216): We modified the way the sliders work. Now, they work in a more "traditional" mode, where the users can select continuous values, instead of duplicating the role of select boxes for multi-choice answering.
<img src="https://github.com/user-attachments/assets/12843eb7-a36f-4747-bc0e-0e75abf3a4ea" width="600px">
- _One-based indexing_ (193) : Human annotators now see the examples indexed from 1 instead of 0, which is more natural.
🖥️ Browse interface
- _Public mode_ (161): It is now possible to publish collected annotations online without providing access to other app parts.
- _Outputs with no inputs_ (164): It is now possible to have a dataset with no input data.
- _New highlight style_ (163, 177): The annotation highlights now follow the new style (see above).
🤖 LLM annotations
- _New LLM providers_ (189): Basing our API calls on the [LiteLLM library](https://www.litellm.ai), we now support annotations from Ollama, vLLM, OpenAI, Google AI Studio, Anthropic, and Vertex AI.
📈 Analysis
- _IAA computation_ (181, 207, 217, 218): We provide raw data for computing inter-annotator agreement, along with an accompanying Jupyter notebook and CLI interface. We also allow to compute IAA between individual groups in the same campaign.
🔧 Other
- _Better logging_ (205): The logs from factgenie are now more colorful and informative:
- _Caching_ (167): Factgenie is now much faster when handling larger amount of data.
Even though we will release a new version on [PyPI](https://pypi.org/project/factgenie), we still [recommend](https://github.com/ufal/factgenie/wiki/Setup#-installation) installing factgenie as an editable Python project.