* Improve UI with style changes and add Settings button
- Improved the UI of the `Input` and `Message` components.
- Added a `Settings` button to the `NavLinks` component.
- Introduced a `Settings` component to handle user settings.
- Refactored the `Dialog` component for consistency.
* Revert not needed changes
* Updated style.css to only work for select
* feat: Remove Dark Mode component and add theme selection feature
This commit removes the Dark Mode component from the navigation bar and replaces it with a theme selection dropdown menu in the Settings dialog. The implementation of the theme selection feature includes a function that allows the user to set the theme based on the system, light, or dark mode.
* Add auto theme setting to Settings component.
This commit adds a new state variable to keep track of whether the auto theme is enabled or not. It also registers an event listener to update the theme based on system preference changes. The event listener is removed when the component is unmounted.
* Improve user experience by allowing customized themes
- Create `selectedOption` state to track user-selected theme
- Remove unused `isAutoTheme` state variable
* feat(Nav): Add SVG icon to settings gear
This commit adds an SVG icon to the settings gear in the Navigation component's Settings file. The new SVG icon replaces the previous GearIcon component.
* refactor(ui): Update overlay background color
This commit updates the background color of the overlay in the AlertDialog and Dialog components by changing the classes applied to the elements. The new color is a transition from `bg-black/50 backdrop-blur-sm` to `bg-gray-500/90 dark:bg-gray-800/90`. This change improves the readability of the dialog boxes.
* Refactor ThemeContext to include system theme and fix bug in Settings
The ThemeContext now includes a "system" theme and ClearConvos no longer relies on the "selected option" state to update the theme. The bug is now fixed if the system theme changes.
* Refactor DialogTemplate styles and color scheme
Adjusted the color scheme of the DialogTemplate component to dark mode, updated the background color to gray-900 and removed unnecessary classes.
* Refactor: Change button logic to require confirmation before clearing convos
This commit refactors the code by adding a confirmation dialog to prompt for a user's confirmation before clearing all conversations in the Settings.jsx file. The change ensures the user is aware of the irreversible action before initiating the clearConvos function. Additionally, the commit updates the clear chat button's class name and changes the button's onClick logic to call the confirmClearConvos function instead of directly invoking the clearConvos method.
* Refactor component name to reflect functionality change.
- Changed component name from ClearConvos to Settings to support potential future use cases.
* Refactor conversation clearing functionality in `Settings.jsx`
This commit optimizes the conversation clearing functionality in the `Settings.jsx` component by removing the `confirmClearConvos` function and directly calling the `clearConvos` function on confirmation. This change will simplify the code and improve the user experience.
* Refactor Input component UI styles
Simplify Input component styles by simplifying the gradient background, removing border color styles, and updating button styles.
* feat: Add e2e test for Settings modal
This commit adds an e2e test to verify whether the Settings modal is displayed on the landing page. It uses a headless browser to navigate to the page and interacts with it to verify if the dialog and its components are visible.
* test: Add Navigation and Settings tests
Add Navigation and Settings tests to verify that the navigation bar and Settings button are visible and that the Settings modal displays the expected content. The settings modal verification includes checking whether the modal is visible, if the modal title, tab list, clear conversation button and theme are present, and if the theme option can be selected to change the mode.
* Quick fix
* feat(navbar): Add confirmation before clearing conversations
Adding confirmation modal to prevent accidentally clearing conversations. Before, once you clicked on the "Clear" button it immediately clears all conversations. With this change, if you click on "Clear" the first time, it will change the text to "Confirm Clear" and if you click it again, it will clear all conversations.
* Add click functionality to the navigation bar and improve UI design
The code introduced click functionality to the nav bar and improved the user interface. It also used the new theme select feature to change the theme to dark.
* test: Add test for dark mode theme change
Refactor the test for Navigation suite to check for the 'dark' class in the HTML element when the 'dark' theme is selected in the modal. This ensures that the dark mode theme change works correctly, and improves test coverage.
* Improve navigation test clarity
This commit improves code clarity and adds more detailed test assertions to the navigation suite. New assert statements are added to check whether the modal theme selection changes the theme and that the HTML element receives the 'dark' class. A new function `changeMode` was introduced to avoid code repetition. A short description was added to the commit message to adhere to best practices.
* Improve navigation test clarity
This commit improves code clarity and adds more detailed test assertions to the navigation suite. New assert statements are added to check whether the modal theme selection changes the theme and that the HTML element receives the 'dark' class. A new function `changeMode` was introduced to avoid code repetition. A short description was added to the commit message to adhere to best practices.
* Hotfix
* Removed repetation
* Refactor: Change text-gray-400 to text-white/50 to make tailwind more cleaner
* style: Update CSS classes to improve the conversation UI
- Update Conversation component to improve UX
- Changed styling for group hover effect using shades of gray
- Improved color contrast of the Message component for easy readability
- Replaced class names in buildTree.js with a new class name
- Added a new color theme (gray-1000) in tailwind.config to replace an old background color.
* Refactor EndpointItem, EndpointItems, and NewConversationMenu for better user experience
- The `EndpointItem` component now accepts an `isSelected` prop instead of `onSelect` to better reflect its usage in `EndpointItems` and `NewConversationMenu`.
- `EndpointItems` component now has a `selectedEndpoint` prop to highlight the selected item in the list.
- `NewConversationMenu` now has a gap between the endpoint options to improve user experience.
* Added error messages
* refactor: Improve endpoint menu highlighting and error handling
In the UI, when the user selects an endpoint, the active class is now properly set. In the error handling function, `isJson` is now a private function called by `getError`, which provides better parsing of error messages, and returns more succinct messages upon encountering specific errors. Finally, a new end-to-end test has been added to check if the active class is properly set on selecting an endpoint in the new conversation menu.
* test: Add Conversation and Change Path of Auth JSON
In the Landing spec, test the functionality to create conversations and check that the number of items has increased. In the Popup spec, change the path of the Auth JSON used by the context.
* Fixed logo issues
* Make everything not rounded
* Added time
---------
Co-authored-by: Danny Avila <110412045+danny-avila@users.noreply.github.com>
* refactor(askGoogle.js): extract saveConvo function call to a separate function
feat(askGoogle.js): add endpoint property to the conversation object
refactor(handleSubmit.js): rename chatGptLabel to modelLabel in useMessageHandler function
* refactor(askGoogle.js): remove unused endpointOption spread operator
* fix: tokenizer will count completion tokens correctly, remove global var, will allow unofficial models for alternative endpoints
* refactor(askBingAI.js, Settings.jsx, types.ts, cleanupPreset.js, getDefaultConversation.js, handleSubmit.js): change default toneStyle to 'creative' instead of 'fast' for Bing AI endpoint.
* fix(SiblingSwitch): correctly appears now
style(HoverButtons.jsx): add 'active' class to hover buttons
* chore(client): update lucide-react package to version 0.220.0
style(client): change color of MessageHeader component text to gray-500
style(client): change color of nav-close-button to gray-400 and nav-open-button to gray-500
feat(client): add Panel component to replace svg icons in Nav component
* fix: forwardRef errors in Nav Menu
* refactor(SearchBar.jsx): change clearSearch prop destructuring to props destructuring
refactor(SearchBar.jsx): add ref prop to SearchBar component
refactor(getIcon.jsx): remove unused imports
refactor(getIcon.jsx): add nullish coalescing operator to user.name and user.avatar properties
* fix (NavLinks): modals no longer close on nav menu close
* style(ExportModel.jsx): remove unnecessary z-index property from a div element
* style(ExportModel.jsx): remove trailing whitespace in input element
* refactor(Message.jsx): remove unused cancelled variable
fix(Message.jsx): fix error message length exceeding 512 characters
refactor(MenuItem.jsx): remove unused MenuItem component
* build/refactor: move lint/prettier packages to project root, install husky, add pre-commit hook
* refactor: reformat files
* build: put full eslintrc back with all rules
* Added functionality to allow users to set custom api keys
* Added error handling
* Changed token to apiKey
* Changed apiKey to oaiApiKey
* added azure openai ui
* Removed logging
* Changed configure to Use
* Made checked position more rounded
* Made setting api key optional if it is openai
* Modified error handling
* Add support for insufficient_quota errors
* Fixed faulty error detection
* removed logging
* Release 0.4.5
* Update @waylaidwanderer/node-chatgpt-api to latest version
* Update dockerfiles to use workspaces and ensure packages are @ latest
* Remove package-lock.json files from workspace directories as no longer needed
* refactor(api): remove deprecated text-davinci-002-render-paid model from CHATGPT_MODELS
refactor(api/client): change model comparison to use startsWith() instead of === for GPT-4 models
* feat(api): add googleapis package to package.json
feat(api): add reqDemo.js file to make a request to Google Cloud AI Platform API to get a response from a chatbot model.
* feat: add PaLM2 support
* feat(conversationPreset.js): add support for topP and topK for google endpoint
feat(askGoogle.js): add support for topP and topK for google endpoint
feat(ask/index.js): add google endpoint
feat(endpoints.js): add google endpoint
feat(MessageHeader.jsx): add support for modelLabel for google endpoint
feat(PresetItem.jsx): add support for modelLabel for google endpoint
feat(HoverButtons.jsx): add support for google endpoint
feat(createPayload.ts): add google endpoint
feat(types.ts): add google endpoint
feat(store/endpoints.js): add google endpoint
feat(cleanupPreset.js): add support for topP and topK for google endpoint
feat(getDefaultConversation.js): add support for topP and topK for google endpoint
feat(handleSubmit.js): add support for topP and topK for google endpoint
* fix: messages payload
* refactor(GoogleClient.js): set maxContextTokens based on isTextModel value
feat(GoogleClient.js): add delay option to TextStream constructor
feat(getIcon.jsx): add support for google endpoint and PaLM2 model label
* feat: palm frontend changes
* feat(askGoogle.js): set default example to empty input and output
feat(Examples.jsx): add ability to add and remove examples
refactor(Settings.jsx): remove examples from props and setOption function
style(GoogleOptions): remove unnecessary whitespace after Settings2 import
feat(GoogleOptions): add addExample and removeExample functions to manage examples
fix(cleanupPreset): set default example to [{ input: '', output: ''}]
fix(getDefaultConversation): set default example to [{ input: '', output: ''}]
fix(handleSubmit): set default example to [{ input: '', output: ''}]
* style(client): adjust height of settings and examples components to 350px
fix(client): fix path to palm.png image in getIcon.jsx file
* style(EndpointOptionsPopover.jsx, Examples.jsx, Settings.jsx): improve button styles and update input placeholders
* feat (palm): finalize examples on the frontend
* feat(GoogleClient.js): filter out empty examples in options
feat(GoogleClient.js): add support for promptPrefix in buildPayload method
feat(GoogleClient.js): add support for examples in buildPayload method
feat(conversationPreset.js): add maxOutputTokens field to conversation preset schema
feat(presetSchema.js): add examples field to preset schema
feat(askGoogle.js): add support for examples and promptPrefix in endpointOption
feat(EditPresetDialog.jsx): add Examples component for Google endpoint
feat(EditPresetDialog.jsx): add button to show/hide Examples component
feat(EditPresetDialog.jsx): add functionality to add, remove, and edit examples in Examples component
feat(EndpointOptionsDialog.jsx): change endpoint name to PaLM for Google endpoint
feat(Settings.jsx): add maxHeight prop to limit height of Settings component in EditPresetDialog and EndpointOptionsDialog
fix(Settings.jsx): add examples prop to ChatGPTBrowser component
fix(EndpointItem.jsx): add alternate name for google endpoint
fix(MessageHeader.jsx): change title for google endpoint to PaLM
feat(endpoints.js): add google endpoint to endpointsConfig
fix(cleanupPreset.js): add missing comma in examples array
* chore: change endpoint order
* feat(PaLM 2): complete for testing
* fix(PaLM): handle blocked messages
* server-side JWT auth implementation
* move oauth routes and strategies, fix bugs
* backend modifications for wiring up the frontend login and reg forms
* Add frontend data services for login and registration
* Add login and registration forms
* Implment auth context, functional client side auth
* protect routes with jwt auth
* finish local strategy (using local storage)
* Start setting up google auth
* disable token refresh, remove old auth middleware
* refactor client, add ApiErrorBoundary context
* disable google and facebook strategies
* fix: fix presets not displaying specific to user
* fix: fix issue with browser refresh
* fix: casing issue with User.js (#11)
* delete user.js to be renamed
* fix: fix casing issue with User.js
* comment out api error watcher temporarily
* fix: issue with api error watcher (#12)
* delete user.js to be renamed
* fix: fix casing issue with User.js
* comment out api error watcher temporarily
* feat: add google auth social login
* fix: make google login url dynamic based on dev/prod
* fix: bug where UI is briefly displayed before redirecting to login
* fix: fix cookie expires value for local auth
* Update README.md
* Update LOCAL_INSTALL structure
* Add local testing instructions
* Only load google strategy if client id and secret are provided
* Update .env.example files with new params
* fix issue with not redirecting to register form
* only show google login button if value is set in .env
* cleanup log messages
* Add label to button for google login on login form
* doc: fix client/server url values in .env.example
* feat: add error message details to registration failure
* Restore preventing paste on confirm password
* auto-login user after registering
* feat: forgot password (#24)
* make login/reg pages look like openai's
* add password reset data services
* new form designs similar to openai, add password reset pages
* add api's for password reset
* email utils for password reset
* remove bcrypt salt rounds from process.env
* refactor: restructure api auth code, consolidate routes (#25)
* add api's for password reset
* remove bcrypt salt rounds from process.env
* refactor: consolidate auth routes, use controller pattern
* refactor: code cleanup
* feat: migrate data to first user (#26)
* refactor: use /api for auth routes
* fix: use user id instead of username
* feat: migrate data to first user on register
* fix: fix social login routes after refactor (#27)
* refactor: use /api for auth routes
* fix: use user id instead of username
* feat: migrate data to first user on register
* fix: fix social login routes
* fix: issue with auto-login when logging out then logging in with new browser window (#28)
* refactor: use /api for auth routes
* fix: use user id instead of username
* feat: migrate data to first user on register
* fix: fix social login routes
* fix: fix issue with auto-login in new tab
* doc: Update README and .env.example files with user system information (#29)
* refactor: use /api for auth routes
* fix: use user id instead of username
* feat: migrate data to first user on register
* fix: fix social login routes
* fix: fix issue with auto-login in new tab
* doc: update README and .env.example files
* Fixup: LOCAL_INSTALL.md PS instructions (#200) (#30)
Co-authored-by: alfredo-f <alfredo.fomitchenko@mail.polimi.it>
* feat: send user with completion to protect against abuse (#31)
* Fixup: LOCAL_INSTALL.md PS instructions (#200)
* server-side JWT auth implementation
* move oauth routes and strategies, fix bugs
* backend modifications for wiring up the frontend login and reg forms
* Add frontend data services for login and registration
* Add login and registration forms
* Implment auth context, functional client side auth
* protect routes with jwt auth
* finish local strategy (using local storage)
* Start setting up google auth
* disable token refresh, remove old auth middleware
* refactor client, add ApiErrorBoundary context
* disable google and facebook strategies
* fix: fix presets not displaying specific to user
* fix: fix issue with browser refresh
* fix: casing issue with User.js (#11)
* delete user.js to be renamed
* fix: fix casing issue with User.js
* comment out api error watcher temporarily
* feat: add google auth social login
* fix: make google login url dynamic based on dev/prod
* fix: bug where UI is briefly displayed before redirecting to login
* fix: fix cookie expires value for local auth
* Only load google strategy if client id and secret are provided
* Update .env.example files with new params
* fix issue with not redirecting to register form
* only show google login button if value is set in .env
* cleanup log messages
* Add label to button for google login on login form
* doc: fix client/server url values in .env.example
* feat: add error message details to registration failure
* Restore preventing paste on confirm password
* auto-login user after registering
* feat: forgot password (#24)
* make login/reg pages look like openai's
* add password reset data services
* new form designs similar to openai, add password reset pages
* add api's for password reset
* email utils for password reset
* remove bcrypt salt rounds from process.env
* refactor: restructure api auth code, consolidate routes (#25)
* add api's for password reset
* remove bcrypt salt rounds from process.env
* refactor: consolidate auth routes, use controller pattern
* refactor: code cleanup
* feat: migrate data to first user (#26)
* refactor: use /api for auth routes
* fix: use user id instead of username
* feat: migrate data to first user on register
* fix: fix social login routes after refactor (#27)
* refactor: use /api for auth routes
* fix: use user id instead of username
* feat: migrate data to first user on register
* fix: fix social login routes
* fix: issue with auto-login when logging out then logging in with new browser window (#28)
* refactor: use /api for auth routes
* fix: use user id instead of username
* feat: migrate data to first user on register
* fix: fix social login routes
* fix: fix issue with auto-login in new tab
* doc: Update README and .env.example files with user system information (#29)
* refactor: use /api for auth routes
* fix: use user id instead of username
* feat: migrate data to first user on register
* fix: fix social login routes
* fix: fix issue with auto-login in new tab
* doc: update README and .env.example files
* Send user id to openai to protect against abuse
* add meilisearch to gitignore
* Remove webpack
---------
Co-authored-by: alfredo-f <alfredo.fomitchenko@mail.polimi.it>
---------
Co-authored-by: Danny Avila <110412045+danny-avila@users.noreply.github.com>
Co-authored-by: Alfredo Fomitchenko <alfredo.fomitchenko@mail.polimi.it>
feat(askOpenAI.js): add abort endpoint to cancel requests
feat(MessageHandler): add abort functionality to cancel requests
feat(submission.js): add lastResponse and source atoms to store
feat(handleSubmit.js): add stopGenerating function to cancel requests
feat: support OPENAI_REVERSE_PROXY
feat: support set availModels in env file
fix: chatgpt Browser send logic refactor.
fix: title wrong usage of responseMessage
BREAKING: some env paramaters has been changed!
feat(FileUpload.jsx): add support for importing JSON files and fetching presets after import
feat(NewConversationMenu.jsx): add FileUpload component to select and import JSON files
feat(fetchers.js): add handleFileSelected function to handle importing JSON files and uploading presets to the server
feat(conversationPreset.js): add context and systemMessage fields to conversation preset schema
feat(askBingAI.js): pass context and systemMessage parameters to ask function
feat(Settings.jsx): add toneStyle prop to BingAISettings component
feat(BingAIOptions/index.jsx): add useEffect to check if advanced mode is needed
feat(cleanupPreset.js): add context and systemMessage fields to cleaned up preset object
feat(getDefaultConversation.js): add context and systemMessage fields to default conversation object
feat(handleSubmit.js): add context and systemMessage fields to message object
feat(BingAI): convert toneStyle to lowercase before setting it in state
feat(BingAI): pass setToneStyle function to Settings component
refactor(BingAI): remove unused import and change setOption to setToneStyle in Settings component
refactor(fetchers.js): add axiosPost function for debounced axios post requests
This commit adds support for multiple GPT models in the chatGPT-browser
client. The available models are now stored in a Map object, which maps
the model label to its corresponding model.
The commit adds a new component, ChatGPTOptions, to the client
UI to allow the user to select the GPT model to use in the chat. The
component is only displayed when the chatGPT-browser endpoint is
selected.
