Releases: DeepLcom/deepl-python
Releases · DeepLcom/deepl-python
v1.26.0
Added
- Added
custom_instructionsparameter totranslate_text()to customize translation behavior with up to 10 instructions (max 300 characters each). Only supported for target languages:de,en,es,fr,it,ja,ko,zhand their variants. Note: using thecustom_instructionsparameter will use thequality_optimizedmodel type as the default. Requests combiningcustom_instructionsand thelatency_optimizedmodel type will be rejected.
v1.25.0
- Added support for the
GET /v3/style_rulesendpoint in the client library, the implementation can be found in theDeepLClientclass. Please refer to the README for usage instructions - Added
style_idoption totranslate_text()which allows text translation with style rules.
v1.24.0
Changed
extra_body_parameterswill now overwrite already set HTTP parameters
v1.23.0
Added
- Added feature to add arbitrary body parameters in
translate_text
Deprecated
- Dropped support for Python 3.8 and older.
Security
- Updated
requestsminimum version to 2.32.4 to resolve security advisories
CVE-2024-47081 and CVE-2024-35195.
v1.22.0
Added
- Added support for the /v3 Glossary APIs in the client library while providing backwards compatibility for the previous /v2 Glossary endpoints. Please refer to the README for usage instructions.
v.1.21.1
Added
- (beta) optional parameter to specify timeout for document translation calls
v1.21.0
Added
- Added support for the Write API in the client library, the implementation
can be found in theDeepLClientclass. Please refer to the README for usage
instructions.
Changed
- The main functionality of the library is now also exposed via the
DeepLClient
class. Please change your code to use this over theTranslatorclass whenever
convenient.
v1.20.0
Added
- Added
model_typeoption totranslate_text()to use models with higher
translation quality (available for some language pairs), or better latency.
Options are'quality_optimized','latency_optimized', and'prefer_quality_optimized' - Added the
model_type_usedfield totranslate_text()response, that
indicates the translation model used when themodel_typeoption is
specified.
v1.19.1
Fixed
- Fixed typing issues, black-formatting and a test case failure.
v1.19.0
Added
- Added
billed_charactersto response fromtranslate_text().