| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| pix2text-1.1.3.tar.gz | 2025-04-15 | 196.8 kB | |
| pix2text-1.1.3-py3-none-any.whl | 2025-04-15 | 222.7 kB | |
| feat_ add VLM support for text and table recognition source code.tar.gz | 2025-04-15 | 14.9 MB | |
| feat_ add VLM support for text and table recognition source code.zip | 2025-04-15 | 15.0 MB | |
| README.md | 2025-04-15 | 789 Bytes | |
| Totals: 5 Items | 30.3 MB | 0 | |
Update 2025.04.15: V1.1.3 Released
Major Changes:
- Support for
VlmTableOCRandVlmTextFormulaOCRmodels based on the VLM interface (see LiteLLM documentation) allowing the use of closed-source VLM models. Installation command:pip install pix2text[vlm]. - Usage examples can be found in tests/test_vlm.py and tests/test_pix2text.py.
主要变更:
- 支持基于 VLM 接口(具体参考 LiteLLM 文档)的
VlmTableOCR和VlmTextFormulaOCR模型,可使用闭源 VLM 模型。安装命令:pip install pix2text[vlm]。 - 使用方式见 tests/test_vlm.py 和 tests/test_pix2text.py。