Releases: whylabs/langkit
v0.0.25
LangKit release v0.0.25
π LangKit: An open-source toolkit for monitoring Language Learning Models (LLMs). π Extracts signals from prompts & responses, ensuring safety & security. π‘οΈ Features include text quality, relevance metrics, & sentiment analysis. π A comprehensive tool for LLM observability. π
This version includes:
- Optionally disable CUDA for Encoder metric modules #191 [@richard-rogers]
- Update release workflow to use whylabs automator #190 [@jamie256]
- Add conditional CUDA support with env variable #189 [@richard-rogers]
- Preliminary benchmarking #185 [@richard-rogers]
- Bump version: 0.0.23 β 0.0.24 #187 [@jamie256]
v0.0.24
LangKit release v0.0.24
π LangKit: An open-source toolkit for monitoring Language Learning Models (LLMs). π Extracts signals from prompts & responses, ensuring safety & security. π‘οΈ Features include text quality, relevance metrics, & sentiment analysis. π A comprehensive tool for LLM observability. π
This version includes:
- Add langkit metadata to schema for inclusion in whylogs profiles #186 [@jamie256]
- security features doc update to include hallucinations #182 [@FelipeAdachi]
- Link reference paper for Hallucinations metric module doc. #181 [@jamie256]
- Add hallucinations to README and update modules list to fix formatting #180 [@jamie256]
- add hallucination docs #179 [@FelipeAdachi]
- Bump version: 0.0.22 β 0.0.23 #183 [@jamie256]
v0.0.23
LangKit release v0.0.23
π LangKit: An open-source toolkit for monitoring Language Learning Models (LLMs). π Extracts signals from prompts & responses, ensuring safety & security. π‘οΈ Features include text quality, relevance metrics, & sentiment analysis. π A comprehensive tool for LLM observability. π
This version includes:
- Fix duplicate init ResolverSpec registration warning in has_patterns #178 [@jamie256]
- cleanup push-release workflow #176 [@jamie256]
- Allow regexes UDF metric name to be configured in LangKitConfig #173 [@jamie256]
- Fix typo in classname for langkit/response_hallucination.py #172 [@richard-rogers]
- Update injection examples and tests #170 [@jamie256]
- Align injections score name with column it is targeting #168 [@jamie256]
- Hallucination example - small fixes #167 [@FelipeAdachi]
- Bump version: 0.0.21 β 0.0.22 #169 [@jamie256]
v0.0.22
LangKit release v0.0.22
π LangKit: An open-source toolkit for monitoring Language Learning Models (LLMs). π Extracts signals from prompts & responses, ensuring safety & security. π‘οΈ Features include text quality, relevance metrics, & sentiment analysis. π A comprehensive tool for LLM observability. π
This version includes:
- Add nltk.download of punkt to the response_hallucination init #166 [@jamie256]
- response_hallucination v0 #163 [@FelipeAdachi]
- Remove xformers as it breaks injections module on mac #162 [@jamie256]
- Choosing an LLM example notebook #165 [@jamie256]
- Update guardrails_openai_example_llm_schema.py #164 [@murilommen]
- Bump version: 0.0.20 β 0.0.21 #160 [@w0-automator]
v0.0.21
LangKit release v0.0.21
π LangKit: An open-source toolkit for monitoring Language Learning Models (LLMs). π Extracts signals from prompts & responses, ensuring safety & security. π‘οΈ Features include text quality, relevance metrics, & sentiment analysis. π A comprehensive tool for LLM observability. π
This version includes:
v0.0.20
LangKit release v0.0.20
π LangKit: An open-source toolkit for monitoring Language Learning Models (LLMs). π Extracts signals from prompts & responses, ensuring safety & security. π‘οΈ Features include text quality, relevance metrics, & sentiment analysis. π A comprehensive tool for LLM observability. π
This version includes:
- Injection refactor #154 [@FelipeAdachi]
- add FrequentItemsMetric on blocked column #152 [@richard-rogers]
- Add homepage link to pyproject.toml #151 [@jamie256]
- More config cleanup #145 [@richard-rogers]
- docs refactor #144 [@FelipeAdachi]
- bump to 0.0.19 #149 [@FelipeAdachi]
v0.0.19
LangKit release v0.0.19
π LangKit: An open-source toolkit for monitoring Language Learning Models (LLMs). π Extracts signals from prompts & responses, ensuring safety & security. π‘οΈ Features include text quality, relevance metrics, & sentiment analysis. π A comprehensive tool for LLM observability. π
This version includes:
- rolling logger in safeguards example from 30 min to 5 min #148 [@FelipeAdachi]
v0.0.18
LangKit release v0.0.18
π LangKit: An open-source toolkit for monitoring Language Learning Models (LLMs). π Extracts signals from prompts & responses, ensuring safety & security. π‘οΈ Features include text quality, relevance metrics, & sentiment analysis. π A comprehensive tool for LLM observability. π
This version includes:
- guardrails example with openai api #146 [@FelipeAdachi]
- Add configuration example notebook #139 [@richard-rogers]
- Add test for empty string on toxicity #142 [@jamie256]
v0.0.17
LangKit release v0.0.17
π LangKit: An open-source toolkit for monitoring Language Learning Models (LLMs). π Extracts signals from prompts & responses, ensuring safety & security. π‘οΈ Features include text quality, relevance metrics, & sentiment analysis. π A comprehensive tool for LLM observability. π
This version includes:
- Safeguard example refactor #140 [@FelipeAdachi]
- Quieter logs in LanKit test suite #135 [@richard-rogers]
- safeguard example fix #137 [@FelipeAdachi]
v0.0.16
LangKit release v0.0.16
π LangKit: An open-source toolkit for monitoring Language Learning Models (LLMs). π Extracts signals from prompts & responses, ensuring safety & security. π‘οΈ Features include text quality, relevance metrics, & sentiment analysis. π A comprehensive tool for LLM observability. π
This version includes: