- JSON Schema : Supports empty arrays and escape characters in strings - Regex : Performance improvement in some cases - Added `UnionParser` and `SequenceParser` to allow combining parsers
0.5.1
- Made it easier to report bugs in the library
0.5.0
- Introduced FormatEnforcerAnalyzer to allow all inference engines to be analyzed in a unified way. (Was previously only available for transformers) - Added support for the analyser in llama.cpp, updated example notebook - JsonSchemaParser now take list min/max items into consideration
0.4.3
- Improved JsonSchemaParser whitespace support - Improved RegexParser performance, especially in regular expressions with `.+` and `.*` sections.
0.4.2
- Modified example in main README to be able to run end to end in Google Colab
0.4.1
- Added integration with the `LlamaIndex` library (huggingface and llama.cpp backends) via sample notebook.