chore: bump version to 0.4.44

Author: Sirsho1997

CHANGELOG.md

@@ -2,6 +2,27 @@
 
 All notable changes to this project will be documented in this file.
 
+## [0.4.44]
+
+### Added
+- Added support for textInference task type (TEXT_INFERENCE in ETaskType enum)
+- Added `ITextInferenceMessage` with role and content for chat messages
+- Added `ITextInferenceUsage` for token usage (promptTokens, completionTokens, totalTokens, thinkingTokens)
+- Added `IGoogleTextProviderSettings` with thinkingLevel for Gemini
+- Added `TextProviderSettings` type alias for text inference provider settings
+- Added `ITextInference` for requests (model, messages, taskUUID, deliveryMethod, maxTokens, temperature, topP, topK, seed, stopSequences, includeCost, providerSettings)
+- Added `IText` for responses (taskType, taskUUID, text, finishReason, usage, cost, status)
+- Added `textInference()` to Runware
+- Added `_buildTextRequest`, `_requestText`, `_handleInitialTextResponse` in base
+- Added `_addTextProviderSettings` for provider settings (matching image/video/audio pattern)
+- Added `getResponse()` support for `List[IText]` when polling textInference tasks
+- Added `TEXT_INITIAL_TIMEOUT` for async delivery (configurable via RUNWARE_TEXT_INITIAL_TIMEOUT)
+- Added `TEXT_POLLING_DELAY` for polling cadence (configurable via RUNWARE_TEXT_POLLING_DELAY)
+- Added `IVideoInference.scheduler: Optional[str] = None`
+
+### Changed
+- Enabled async delivery for text inference (returns IAsyncTaskResponse and uses getResponse() for polling)
+
 ## [0.4.43]
 
 ### Added

runware/__init__.py

@@ -6,4 +6,4 @@
 from .async_retry import *
 
 __all__ = ["Runware"]
-__version__ = "0.4.43"
+__version__ = "0.4.44"

setup.py

@@ -6,7 +6,7 @@
 setup(
     name="runware",
     license="MIT",
-    version="0.4.43",
+    version="0.4.44",
     author="Runware Inc.",
     author_email="python.sdk@runware.ai",
     description="The Python Runware SDK is used to interact with the Runware API, powered by the Runware inference platform. It supports image generation, video generation, image upscale, video upscale, image caption, video caption, image background removal, video background removal, audio generation, and more. It also allows the use of an existing gallery of models or selecting any model or LoRA from the CivitAI gallery. The API also supports inpainting, outpainting, and a series of other ControlNet models.",