v1.1.30

Added

• Add get_explanation() API for TLM, TrustworthyRAG and TLMChatCompletions

v1.1.29

Added

• Improve exception handling of HTTP errors for VPC ChatCompletion module
• Add custom VPCTLMOptions class that defines model provider option

v1.1.28

Added

• Support model_provider in TLMOptions for VPC ChatCompletion module

v1.1.27

Added

• TLMOptions includes disable_persistence option.

v1.1.26

Added

• TrustworthyRAG now skips response-based evaluations when tool calls are detected in the response text.

v1.1.25

Added

• Add support for explanations for VPC ChatCompletion module

Fixed

• Unittest logic for quality preset changes
• Typing in chat.py for new openai versions

v1.1.24

Added

• Add new OpenAI models: gpt-5, gpt-5-mini, gpt-5-nano

v1.1.23

Changed

• Updated TLMOptions to support disable_trustworthiness parameter
  • Skips trustworthiness scoring when disable_trustworthiness is True, assuming either custom evaluation criteria (TLM) or RAG Evals (TrustworthyRAG) are provided

v1.1.22

Added

• Added TLMResponses module, providing support for trust scoring with OpenAI Responses object

v1.1.21

Changed

• Updated the VPC version of TLMChatCompletion to accept request_headers parameter, which is forwarded to the TLM app as part of API requests