Skip to content

Latest commit

 

History

History
1438 lines (854 loc) · 118 KB

CHANGELOG.md

File metadata and controls

1438 lines (854 loc) · 118 KB
Raw

Changelog

2.28.0

(Full Changelog)

Release summary

This release notably includes the following changes:

  • Models from the Anthropic and ChatAnthropic providers are now merged in the config UI, so all Anthropic models are shown in the same place in the "Language model" dropdown.

  • Anthropic Claude v1 LLMs have been removed, as the models are retired and no longer available from the API.

  • The chat system prompt has been updated to encourage the LLM to express dollar quantities in LaTeX, i.e. the LLM should prefer returning \(\$100\) instead of $100. For the latest LLMs, this generally fixes a rendering issue when multiple dollar quantities are given literally in the same sentence.

    • Note that the issue may still persist in older LLMs, which do not respect the system prompt as frequently.

  • /export has been fixed to include streamed replies, which were previously omitted.

  • Calling non-chat providers with history has been fixed to behave properly in magics.

Enhancements made

  • Remove retired models and add new Haiku-3.5 model in Anthropic #1092 (@srdas)
  • Reduced padding in cell around code icons in code toolbar #1072 (@srdas)
  • Merge Anthropic language model providers #1069 (@srdas)
  • Add examples of using Fields and EnvAuthStrategy to developer documentation #1056 (@alanmeeson)

Bugs fixed

  • Continue to allow $ symbols to delimit inline math in human messages #1094 (@dlqqq)
  • Fix /export by including streamed agent messages #1077 (@mcavdar)
  • Fix magic commands when using non-chat providers w/ history #1075 (@alanmeeson)
  • Allow $ to literally denote quantities of USD in chat #1068 (@dlqqq)

Documentation improvements

  • Improve installation documentation and clarify provider dependencies #1087 (@srdas)
  • Added Ollama to the providers table in user docs #1064 (@srdas)

Contributors to this release

(GitHub contributors page for this release)

@alanmeeson | @dlqqq | @krassowski | @mcavdar | @srdas

2.27.0

(Full Changelog)

Enhancements made

Documentation improvements

  • Added Developer documentation for streaming responses #1051 (@srdas)

Contributors to this release

(GitHub contributors page for this release)

@dlqqq | @pre-commit-ci | @srdas

2.26.0

This release notably includes the addition of a "Stop streaming" button, which takes over the "Send" button when a reply is streaming and the chat input is empty. While Jupyternaut is streaming a reply to a user, the user has the option to click the "Stop streaming" button to interrupt Jupyternaut and stop it from streaming further. Thank you @krassowski for contributing this feature! 🎉

(Full Changelog)

Enhancements made

Bugs fixed

Maintenance and upkeep improvements

Documentation improvements

Contributors to this release

(GitHub contributors page for this release)

@dlqqq | @JasonWeill | @jlsajfj | @krassowski | @michaelchia | @pre-commit-ci

2.25.0

(Full Changelog)

Enhancements made

  • Export context hooks from NPM package entry point #1020 (@dlqqq)
  • Add support for optional telemetry plugin #1018 (@dlqqq)
  • Add back history and reset subcommand in magics #997 (@akaihola)

Maintenance and upkeep improvements

Contributors to this release

(GitHub contributors page for this release)

@akaihola | @dlqqq | @jtpio | @pre-commit-ci

2.24.1

(Full Changelog)

Enhancements made

Bugs fixed

Contributors to this release

(GitHub contributors page for this release)

@andrewfulton9 | @dlqqq | @hockeymomonow

2.24.0

(Full Changelog)

This release notably introduces a new context command @file:<file-path> to the chat UI, which includes the content of the target file with your prompt when sent. This allows you to ask questions like:

  • What does @file:src/components/ActionButton.tsx do?
  • Can you refactor @file:src/index.ts to use async/await syntax?
  • How do I add an optional dependency to @file:pyproject.toml?

The context command feature also includes an autocomplete menu UI to help navigate your filesystem with fewer keystrokes.

Thank you @michaelchia for developing this feature!

Enhancements made

Bugs fixed

Maintenance and upkeep improvements

  • Upgrade to actions/upload-artifact@v4 in workflows #992 (@dlqqq)

Contributors to this release

(GitHub contributors page for this release)

@akaihola | @andrewfulton9 | @dlqqq | @ellisonbg | @hockeymomonow | @krassowski | @michaelchia | @srdas

2.23.0

(Full Changelog)

Enhancements made

Bugs fixed

Contributors to this release

(GitHub contributors page for this release)

@dlqqq | @krassowski | @michaelchia | @srdas

2.22.0

(Full Changelog)

Enhancements made

  • Add 'Generative AI' submenu #971 (@dlqqq)
  • Add Gemini 1.5 to the list of chat options #964 (@trducng)
  • Allow configuring a default model for cell magics (and line error magic) #962 (@krassowski)
  • Make chat memory size traitlet configurable + /clear to reset memory #943 (@michaelchia)

Maintenance and upkeep improvements

Documentation improvements

  • Update documentation to cover installation of all dependencies #961 (@srdas)

Contributors to this release

(GitHub contributors page for this release)

@dlqqq | @krassowski | @michaelchia | @pre-commit-ci | @srdas | @trducng

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

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

Bugs fixed

Maintenance and upkeep improvements

Documentation improvements

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

Bugs fixed

Maintenance and upkeep improvements

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

Bugs fixed

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

Bugs fixed

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

Maintenance and upkeep improvements

Documentation improvements

Contributors to this release

(GitHub contributors page for this release)

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

2.16.0

(Full Changelog)

Enhancements made

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

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

2.14.1

(Full Changelog)

Bugs fixed

Contributors to this release

(GitHub contributors page for this release)

@3coins | @dlqqq | @michaelchia

2.14.0

(Full Changelog)

Enhancements made

  • Handle single files, pdfs, errors from missing loader dependencies in /learn #733 (@srdas)
  • Move methods generating completion replies to the provider #717 (@krassowski)
  • Handle Single Files and also enable html, pdf file formats for /learn #712 (@srdas)

Bugs fixed

  • Catch embedding model validation errors on extension init #735 (@dlqqq)
  • Require jupyter_ai_magics 2.13.0 to fix Persona import #731 (@krassowski)
  • Fixes help slash command. #729 (@3coins)
  • Remove trailing Markdown code tags in completion suggestions #726 (@bartleusink)
  • Update Azure OpenAI fields #722 (@cloutier)
  • Handle Single Files and also enable html, pdf file formats for /learn #712 (@srdas)

Contributors to this release

(GitHub contributors page for this release)

@3coins | @bartleusink | @cloutier | @dlqqq | @krassowski | @srdas | @welcome

2.13.0

(Full Changelog)

Enhancements made

Bugs fixed

  • Fix rendering of model IDs with a colon in their name #704 (@dlqqq)
  • Update Anthropic providers to use langchain_anthropic partner package #700 (@dlqqq)
  • Use new langchain-openai partner package #653 (@startakovsky)

Contributors to this release

(GitHub contributors page for this release)

@apurvakhatri | @aroffe99 | @dlqqq | @lumberbot-app | @srdas | @startakovsky | @welcome

2.12.0

(Full Changelog)

Enhancements made

Bugs fixed

  • Fix selecting models with a colon in their ID #682 (@dlqqq)
  • Use regex in TeX replace function to catch repeating symbol occurrences #675 (@andrii-i)
  • Resolves chat panel initialization error #660 (@abbott)
  • fix bug: check before using the variables #656 (@ya0guang)

Documentation improvements

Contributors to this release

(GitHub contributors page for this release)

@abbott | @andrii-i | @apurvakhatri | @dlqqq | @giswqs | @lumberbot-app | @MahdiDavari | @srdas | @welcome | @ya0guang

2.11.0

This release notably includes a significant UI improvement for the chat side panel. The chat UI now uses the native JupyterLab frontend to render Markdown, code blocks, and TeX markup instead of a third party package. Thank you to @andrii-i for building this feature!

(Full Changelog)

Enhancements made

Bugs fixed

  • Unifies parameters to instantiate llm while incorporating model params #632 (@JasonWeill)

Documentation improvements

Contributors to this release

(GitHub contributors page for this release)

@andrii-i | @dlqqq | @droumis | @EduardDurech | @JasonWeill | @jtpio | @krassowski | @lalanikarim | @lumberbot-app | @welcome | @Wzixiao

2.10.0

This is the first public release of Jupyter AI inline completion, initially developed by @krassowski. Inline completion requires jupyterlab==4.1.0 to work, so make sure you have that installed if you want to try it out! 🎉

(Full Changelog)

Enhancements made

Bugs fixed

Documentation improvements

Other merged PRs

  • Correction to default models configuration. #605 (@3coins)

Contributors to this release

(GitHub contributors page for this release)

@3coins | @adriens | @aws-khatria | @dlqqq | @garsonbyte | @JasonWeill | @krassowski | @lumberbot-app | @stevie-35 | @Tom-A-Lynch | @welcome

2.10.0-beta.1

(Full Changelog)

Bugs fixed

Contributors to this release

(GitHub contributors page for this release)

@krassowski

2.10.0-beta.0

(Full Changelog)

Enhancements made

Contributors to this release

(GitHub contributors page for this release)

@dlqqq | @jtpio | @krassowski

2.9.1

(Full Changelog)

Enhancements made

Bugs fixed

Contributors to this release

(GitHub contributors page for this release)

@dlqqq | @JasonWeill | @jtpio | @welcome

2.9.0

(Full Changelog)

Enhancements made

Contributors to this release

(GitHub contributors page for this release)

@dlqqq | @JasonWeill | @krassowski | @lumberbot-app

2.8.1

(Full Changelog)

Bugs fixed

Contributors to this release

(GitHub contributors page for this release)

@dlqqq | @JasonWeill | @krassowski

2.8.0

(Full Changelog)

Enhancements made

  • Add gpt-4-1106-preview model from openai #540 (@jamesjun)
  • Adds multi-environment variable authentication, Baidu Qianfan ERNIE-bot provider #531 (@JasonWeill)

Bugs fixed

Maintenance and upkeep improvements

Documentation improvements

Contributors to this release

(GitHub contributors page for this release)

@dlqqq | @ellisonbg | @jamesjun | @JasonWeill | @krassowski | @sundaraa-deshaw | @welcome | @Zsailer

2.7.1

(Full Changelog)

Enhancements made

Bugs fixed

  • Handle LLMs lacking concurrency support in Chat UI #506 (@dlqqq)

Maintenance and upkeep improvements

Documentation improvements

Contributors to this release

(GitHub contributors page for this release)

@andrii-i | @dlqqq | @JasonWeill | @krassowski | @lumberbot-app

2.7.0

(Full Changelog)

Enhancements made

Bugs fixed

  • Make links from Jupyter AI chat open in new tab (vs in the same tab currently) #474 (@andrii-i)

Maintenance and upkeep improvements

Documentation improvements

Contributors to this release

(GitHub contributors page for this release)

@3coins | @Adithya4720 | @andrii-i | @dlqqq | @JasonWeill | @krassowski | @welcome | @Zsailer

2.6.0

(Full Changelog)

Enhancements made

Bugs fixed

  • If model_provider_id or embeddings_provider_id is not associated with models, set it to None #459 (@andrii-i)
  • Add gpt4all local models, including an embedding provider #454 (@3coins)
  • Ensure initials appear in collaborative mode #443 (@aychang95)

Documentation improvements

Contributors to this release

(GitHub contributors page for this release)

@3coins | @andrii-i | @aychang95 | @dlqqq | @JasonWeill | @welcome

2.5.0

(Full Changelog)

Enhancements made

  • Model allowlist and blocklists #446 (@dlqqq)
  • DOC: Render hugging face url as link #432 (@arokem)
  • Log exceptions in /generate to a file #431 (@dlqqq)
  • Model parameters option to pass in model tuning, arbitrary parameters #430 (@3coins)
  • /learn skips hidden files/dirs by default, unless "-a" is specified #427 (@JasonWeill)

Bugs fixed

  • Model parameters option to pass in model tuning, arbitrary parameters #430 (@3coins)
  • Rename Bedrock and Bedrock chat providers in docs #429 (@JasonWeill)

Documentation improvements

Contributors to this release

(GitHub contributors page for this release)

@3coins | @arokem | @dlqqq | @ellisonbg | @JasonWeill | @jtpio | @krassowski | @welcome | @Wzixiao

2.4.0

(Full Changelog)

Hey Jupyternauts! We're excited to announce the 2.4.0 release of Jupyter AI, which includes better support for Bedrock Anthropic models. Thanks to @krassowski for providing a new feature in Jupyter AI that let's admins specify allowlists and blocklists to filter the list of providers available in the chat settings panel.

Enhancements made

Bugs fixed

  • Refactor generate for better stability with all providers/models #407 (@3coins)

Maintenance and upkeep improvements

Contributors to this release

(GitHub contributors page for this release)

@3coins | @krassowski | @pre-commit-ci

2.3.0

(Full Changelog)

Hey Jupyternauts! We're excited to announce the 2.3.0 release of Jupyter AI, which includes better support for Anthropic models and integration with Amazon Bedrock.

There is also a significant change to how Jupyter AI settings are handled (see #353). The most significant changes are:

  1. API key values can no longer be read from the client. This was taken as a security measure to prevent accidental leakage of keys. You can still update existing API keys if you do decide to change your key in the future.
  2. The settings can not be updated if they were updated by somebody else after you opened the settings panel. This prevents different users connecting to the same server from clobbering updates from each other.
  3. There is now a much better UI for updating and deleting API keys. We hope you enjoy it.

Updating to 2.3.0 shouldn't require any changes on your end. However, if you notice an error, please submit a bug report with the server logs emitted in the terminal from the jupyter lab process. Renaming the config file $JUPYTER_DATA_DIR/jupyter_ai/config.json to some other name and then restarting jupyter lab may fix the issue if it is a result of the new config changes.

Enhancements made

Bugs fixed

  • Upgraded LangChain, fixed prompts for Bedrock #401 (@3coins)
  • Adds chat anthropic provider, new models #391 (@3coins)

Maintenance and upkeep improvements

Documentation improvements

Contributors to this release

(GitHub contributors page for this release)

@3coins | @andrii-i | @dlqqq | @JasonWeill | @krassowski

2.2.0

(Full Changelog)

Enhancements made

Bugs fixed

Maintenance and upkeep improvements

  • Upgrades LangChain to 0.0.277 #375 (@3coins)
  • relax pinning on importlib_metadata, typing_extensions #363 (@minrk)

Documentation improvements

Contributors to this release

(GitHub contributors page for this release)

@3coins | @andrii-i | @JasonWeill | @krassowski | @michaelchia | @minrk | @welcome

2.1.0

(Full Changelog)

Enhancements made

Documentation improvements

Contributors to this release

(GitHub contributors page for this release)

@3coins | @anammari | @bjornjorgensen | @dlqqq | @JasonWeill | @krassowski | @welcome

2.0.1

(Full Changelog)

Enhancements made

Bugs fixed

Maintenance and upkeep improvements

Documentation improvements

Other merged PRs

Contributors to this release

(GitHub contributors page for this release)

@dlqqq | @eltociear | @JasonWeill | @jmkuebler | @pre-commit-ci | @welcome

This is currently the latest major version, and supports exclusively JupyterLab 4.

Existing users who are unable to migrate to JupyterLab 3 immediately should use v1.x. However, feature releases and bug fixes will only be backported to v1.x as we deem necessary, so we highly encourage existing Jupyter AI users to migrate to JupyterLab 4 and Jupyter AI v2 as soon as possible to enjoy all of the latest features we are currently developing.

Thank you all for your support of Jupyter AI! 🎉

2.0.0

(Full Changelog)

Enhancements made

Contributors to this release

(GitHub contributors page for this release)

@dlqqq

1.0.0

This release serves exclusively to dedicate a major version to the 1.x branch providing JupyterLab 3 support.

(Full Changelog)

Enhancements made

Contributors to this release

(GitHub contributors page for this release)

@andrii-i | @JasonWeill

0.10.1

(Full Changelog)

Bugs fixed

Contributors to this release

(GitHub contributors page for this release)

@dlqqq

0.10.0

(Full Changelog)

Enhancements made

Bugs fixed

Maintenance and upkeep improvements

Documentation improvements

Contributors to this release

(GitHub contributors page for this release)

@3coins | @dlqqq | @JasonWeill | @pre-commit-ci

0.9.0

(Full Changelog)

Bugs fixed

Maintenance and upkeep improvements

Contributors to this release

(GitHub contributors page for this release)

@3coins | @dlqqq | @JasonWeill | @pre-commit-ci

0.8.0

(Full Changelog)

Enhancements made

Bugs fixed

Maintenance and upkeep improvements

Documentation improvements

  • Add documentation for running magics in remote kernels #196 (@dlqqq)

Contributors to this release

(GitHub contributors page for this release)

@3coins | @dlqqq | @JasonWeill

0.7.3

(Full Changelog)

Enhancements made

Bugs fixed

Documentation improvements

Contributors to this release

(GitHub contributors page for this release)

@3coins | @dlqqq | @JasonWeill | @mschroering

0.7.2

(Full Changelog)

Enhancements made

Bugs fixed

Documentation improvements

Contributors to this release

(GitHub contributors page for this release)

@dlqqq | @JasonWeill

0.7.1

(Full Changelog)

Enhancements made

Bugs fixed

  • Fixes error for config, when new installation is done #161 (@3coins)

Documentation improvements

Contributors to this release

(GitHub contributors page for this release)

@3coins | @JasonWeill

0.7.0

(Full Changelog)

Enhancements made

Bugs fixed

  • Adds missing newline before closing code block #155 (@JasonWeill)
  • Runtime model configurability #146 (@dlqqq)
  • Pin LangChain version #134 (@3coins)
  • Upgraded ray version, installation instructions that work with python 3.9 and 3.10 #127 (@3coins)
  • Strips language indicator from start of code output #126 (@JasonWeill)

Documentation improvements

Contributors to this release

(GitHub contributors page for this release)

@3coins | @dlqqq | @ellisonbg | @JasonWeill | @thorhojhus | @welcome

0.6.0

(Full Changelog)

Enhancements made

Bugs fixed

Maintenance and upkeep improvements

Documentation improvements

Contributors to this release

(GitHub contributors page for this release)

@3coins | @dlqqq | @ellisonbg | @JasonWeill | @welcome

0.5.0

(Full Changelog)

Enhancements made

Bugs fixed

  • use --force-publish option for lerna version #49 (@dlqqq)

Documentation improvements

Contributors to this release

(GitHub contributors page for this release)

@3coins | @dlqqq | @ellisonbg | @JasonWeill | @welcome

0.4.0

(Full Changelog)

Enhancements made

Bugs fixed

Documentation improvements

Contributors to this release

(GitHub contributors page for this release)

@dlqqq | @JasonWeill | @welcome

0.3.0

(Full Changelog)

Enhancements made

  • implement IPython magics #18 (@dlqqq)
  • add tasks for AI modules #16 (@dlqqq)
  • Decouple tasks from model engines and introduce modalities #15 (@dlqqq)

Contributors to this release

(GitHub contributors page for this release)

@dlqqq

0.2.0

(Full Changelog)

Enhancements made

Bugs fixed

  • include root package in version bump script #12 (@dlqqq)

Contributors to this release

(GitHub contributors page for this release)

@dlqqq

0.1.1

(Full Changelog)

Bugs fixed

  • bump all project versions in bump-version #10 (@dlqqq)
  • fix insert-below-in-image insertion mode #9 (@dlqqq)

Contributors to this release

(GitHub contributors page for this release)

@dlqqq

0.1.0

(Full Changelog)

Enhancements made

  • rename NPM packages to be under @jupyter-ai org #7 (@dlqqq)
  • disable check-release for PRs #6 (@dlqqq)
  • Set up releaser configuration #3 (@dlqqq)
  • Improve development setup #1 (@dlqqq)

Bugs fixed

  • Add root package as Nx project #8 (@dlqqq)
  • Fix check-release workflow #5 (@dlqqq)

Contributors to this release

(GitHub contributors page for this release)

@dlqqq | @welcome