@jupyter-ai/core - npm Package Versions

2.21.0

(Full Changelog)

Enhancements made

• Add optional configurable message footer #942 (@dlqqq)
• Add support for Azure Open AI Embeddings to Jupyter AI #940 (@gsrikant7)
• Make help message template configurable #938 (@dlqqq)
• Add latest Bedrock models (Titan, Llama 3.1 405b, Mistral Large 2, Jamba Instruct) #923 (@gabrielkoo)
• Add support for custom/provisioned models in Bedrock #922 (@dlqqq)
• Settings section improvement #918 (@andrewfulton9)

Bugs fixed

• Bind reject method to promise, improve typing #949 (@krassowski)
• Fix sending empty input with Enter #946 (@michaelchia)
• Fix saving chat settings #935 (@dlqqq)

Documentation improvements

• Add documentation on how to use Amazon Bedrock #936 (@srdas)
• Update copyright template #925 (@srdas)

Contributors to this release

(GitHub contributors page for this release)

@andrewfulton9 | @dlqqq | @gabrielkoo | @gsrikant7 | @krassowski | @michaelchia | @srdas

2.20.0

(Full Changelog)

Enhancements made

• Respect selected persona in chat input placeholder #916 (@dlqqq)
• Migrate to langchain-aws for AWS providers #909 (@dlqqq)
• Added new Bedrock Llama 3.1 models and gpt-4o-mini #908 (@srdas)
• Rework selection inclusion; new Send button UX #905 (@dlqqq)

Contributors to this release

(GitHub contributors page for this release)

@dlqqq | @JasonWeill | @srdas

2.19.1

(Full Changelog)

Enhancements made

• Allow overriding the Ollama base URL #904 (@jtpio)
• Make magic aliases user-customizable #901 (@krassowski)

Bugs fixed

• Trim leading whitespace when processing #900 (@krassowski)
• Fix python<3.10 compatibility #899 (@michaelchia)

Maintenance and upkeep improvements

Documentation improvements

• Add notebooks to the documentation #906 (@andrewfulton9)
• Update docs to reflect Python 3.12 support #898 (@dlqqq)

Contributors to this release

(GitHub contributors page for this release)

@andrewfulton9 | @dlqqq | @jtpio | @krassowski | @michaelchia | @pre-commit-ci

2.19.0

This is a significant release that implements LLM response streaming in Jupyter AI along with several other enhancements & fixes listed below. Special thanks to @krassowski for his generous contributions this release!

(Full Changelog)

Enhancements made

• Upgrade to langchain~=0.2.0 and langchain_community~=0.2.0 #897 (@dlqqq)
• Rework selection replacement #895 (@dlqqq)
• Ensure all slash commands support -h/--help #878 (@krassowski)
• Add keyboard shortcut command to focus chat input #876 (@krassowski)
• Implement LLM response streaming #859 (@dlqqq)
• Add Ollama #646 (@jtpio)

Bugs fixed

• Fix streaming in HuggingFaceHub provider #894 (@krassowski)
• Fix removal of pending messages on error #888 (@krassowski)
• Ensuring restricted access to the /learn index directory #887 (@krassowski)
• Make preferred-dir the default read/write directory for slash commands #881 (@andrewfulton9)
• Fix prefix removal when streaming inline completions #879 (@krassowski)
• Limit chat input height to 20 lines #877 (@krassowski)
• Do not redefine refreshCompleterState on each render #875 (@krassowski)
• Remove unused toolbars/menus from schema #873 (@krassowski)
• Fix plugin ID format #872 (@krassowski)
• Address error on /learn after change of embedding model #870 (@srdas)
• Fix pending message overlapping text #857 (@michaelchia)
• Fixes error when allowed or blocked model list is passed in config #855 (@3coins)
• Fixed /export for timestamp, agent name #854 (@srdas)

Maintenance and upkeep improvements

• Update to actions/checkout@v4 #893 (@jtpio)
• Upload jupyter-releaser built distributions #892 (@jtpio)
• Updated integration tests workflow #890 (@krassowski)

Contributors to this release

(GitHub contributors page for this release)

@3coins | @andrewfulton9 | @brichet | @dannongruver | @dlqqq | @JasonWeill | @jtpio | @krassowski | @lalanikarim | @michaelchia | @pedrogutobjj | @srdas

2.18.1

(Full Changelog)

Enhancements made

• Add claude sonnet 3.5 models #847 (@srdas)
• Update clear slash command to use HelpChatHandler to reinstate the help menu #846 (@srdas)

Bugs fixed

• Fix send via keyboard after sending slash command with arguments #850 (@dlqqq)
• Fix Cohere models by using new langchain-cohere partner package #848 (@dlqqq)

Contributors to this release

(GitHub contributors page for this release)

@dlqqq | @srdas

2.18.0

(Full Changelog)

Enhancements made

• Add new Cohere models #834 (@srdas)
• Group messages with their replies #832 (@michaelchia)
• Support Notebook 7 #827 (@jtpio)
• Support pending/loading message while waiting for response #821 (@michaelchia)

Bugs fixed

• Fix compatibility with Python 3.8 #844 (@krassowski)

Documentation improvements

• Updates end of maintenance messaging to be in the past tense #843 (@JasonWeill)

Contributors to this release

(GitHub contributors page for this release)

@dlqqq | @JasonWeill | @jtpio | @krassowski | @michaelchia | @srdas

2.17.0

(Full Changelog)

Enhancements made

• Add /fix slash command #828 (@dlqqq)
• Add support for MistralAI #823 (@jtpio)
• Document supported file types for /learn #816 (@JasonWeill)
• Refactor split function with tests #811 (@srdas)
• Autocomplete UI for slash commands #810 (@dlqqq)

Bugs fixed

• Update chat handling to clear chat and show help; small fix to /export #826 (@srdas)

Maintenance and upkeep improvements

• Prevent overriding server_settings on base provider class #825 (@krassowski)
• Fix import deprecations #824 (@jtpio)

Documentation improvements

• Document supported file types for /learn #816 (@JasonWeill)
• Document how to create completions using full notebook content #777 (@krassowski)

Contributors to this release

(GitHub contributors page for this release)

@dlqqq | @JasonWeill | @jtpio | @krassowski | @srdas

2.16.0

(Full Changelog)

Enhancements made

• Added gpt-4o #793 (@srdas)
• Add code toolbar to Jupyter AI chat #789 (@dlqqq)

Bugs fixed

• Fix Azure OpenAI authentication from UI #794 (@dlqqq)
• Updated Hugging Face chat and magics processing with new APIs, clients #784 (@srdas)

Contributors to this release

(GitHub contributors page for this release)

@dlqqq | @JasonWeill | @srdas

2.15.0

(Full Changelog)

Enhancements made

• Add Titan embedding model v2 #778 (@srdas)
• Save chat history to Jupyter Lab's root directory #770 (@srdas)
• Add new Bedrock model IDs #764 (@srdas)
• learn arxiv tex files #742 (@srdas)
• Distinguish between completion and chat models #711 (@krassowski)

Bugs fixed

• Save chat history to Jupyter Lab's root directory #770 (@srdas)
• change unsupported_slash_commands default value from dict to set #768 (@michaelchia)
• Switch to langchain_community #758 (@srdas)

Documentation improvements

• Add JL3 end-of-maintenance notice to README and RTD #760 (@dlqqq)

Contributors to this release

(GitHub contributors page for this release)

@3coins | @dlqqq | @krassowski | @michaelchia | @srdas