v0.19.0

Added

• Tool calling support in DocumentLLM.chat(...).

v0.18.0

Added

• Chat: Added optional chat_session parameter (accepts a ChatSession) to preserve message history across turns in DocumentLLM.chat(). When this parameter is omitted, chat is single-turn, without message history.

v0.17.1

Changed

• DocxConverter: Conversion speed improved by ~2X, significantly reducing processing time for DOCX files.

v0.17.0

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.

v0.16.1

Fixed

• Added support for "minimal" reasoning effort for gpt-5 models.

v0.16.0

Added

• Reasoning-aware extraction prompts: Automatically enables private chain-of-thought guidance on models that support reasoning, yielding higher-quality outputs (no change for other models).

v0.15.0

Added

• Auto-pricing for LLMs: enable via auto_pricing=True to automatically estimate costs using pydantic's genai-prices; optional auto_pricing_refresh=True refreshes cached price data at runtime.

Refactor

• Public API made more consistent and stable: user-facing classes are now thin, well-documented facades over internal implementations. No behavior changes.
• Internal reorganization for maintainability and future-proofing.

Docs

• Added guidance for configuring auto-pricing for LLMs.

v0.14.4

Fixed

• Suppressed noisy LiteLLM proxy missing-dependency error logs (prompting to install litellm[proxy]) emitted by litellm>=1.75.2 during LLM API calls. ContextGem does not require LiteLLM proxy features. Suppression is scoped to LiteLLM loggers.

v0.14.3

Fixed

• Enabled reasoning_effort parameter for gpt-5 models by explicitly forwarding it via allowed_openai_params, since litellm.get_supported_openai_params() does not yet include this parameter for gpt-5 models.

v0.14.2

Added

• Added warning for gpt-oss models used with lm_studio/ provider due to performance issues (according to tests), with a recommendation to use Ollama as a working alternative (e.g., ollama_chat/gpt-oss:20b).