build: v0.17.0

Author: SergiiShcherbak

CHANGELOG.md

@@ -5,6 +5,10 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 
 - **Refactor**: Code reorganization that doesn't change functionality but improves structure or maintainability
 
+## [0.17.0](https://github.com/shcherbak-ai/contextgem/releases/tag/v0.17.0) - 2025-08-24
+### Added
+- Multimodal LLM roles (`"extractor_multimodal"` and `"reasoner_multimodal"`) to support extraction of multimodal document-level concepts from both text and images. Previously, only text and vision roles were supported, requiring choosing either text or image context for extraction, not both.
+
 ## [0.16.1](https://github.com/shcherbak-ai/contextgem/releases/tag/v0.16.1) - 2025-08-19
 ### Fixed
 - Added support for `"minimal"` reasoning effort for gpt-5 models.

contextgem/__init__.py

@@ -20,7 +20,7 @@
 ContextGem - Effortless LLM extraction from documents
 """
 
-__version__ = "0.16.1"
+__version__ = "0.17.0"
 __author__ = "Shcherbak AI AS"
 
 from contextgem.public import (

docs/source/conf.py

@@ -25,7 +25,7 @@
 project = "ContextGem"
 copyright = "2025, Shcherbak AI AS"
 author = "Sergii Shcherbak"
-release = "0.16.1"
+release = "0.17.0"
 
 
 # Add path to the package

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "contextgem"
-version = "0.16.1"
+version = "0.17.0"
 description = "Effortless LLM extraction from documents"
 authors = [{ name = "shcherbak-ai", email = "[email protected]" }]
 requires-python = ">=3.10,<3.14"