This repository has been archived by the owner on Sep 15, 2024. It is now read-only.
forked from ChatGPTNextWeb/ChatGPT-Next-Web
-
Notifications
You must be signed in to change notification settings - Fork 8
H0llyW00dzZ doing experimental while developing hahahaha #52
Draft
H0llyW00dzZ
wants to merge
358
commits into
main
Choose a base branch
from
3.0.0
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
[+] feat(openai.ts): add support for legacy models in ChatGPTApi class
Bumps [zod](https://github.com/colinhacks/zod) from 3.21.4 to 3.22.3. - [Release notes](https://github.com/colinhacks/zod/releases) - [Changelog](https://github.com/colinhacks/zod/blob/master/CHANGELOG.md) - [Commits](colinhacks/zod@v3.21.4...v3.22.3) --- updated-dependencies: - dependency-name: zod dependency-type: indirect ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Reason : not really needed This reverts commit b967b9443f56b15da1e7a3e5e8eefa50b91dc306.
[+] fix(openai.ts): remove duplicate model assignment in request payload [+] feat(openai.ts): add support for DALL-E-3 model in conditionals [+] fix(openai.ts): remove commented out code for image payload [+] feat(openai.ts): update model name in conditionals for DALL-E-2-BETA-INSTRUCT-0613 [+] fix(openai.ts): update model name in conditionals for DALL-E-2-BETA-INSTRUCT-0613 [+] fix(constant.ts): update model names to lowercase [+] fix(chat.ts): update model names in conditionals to lowercase
[+] chore(config.ts): update DEFAULT_CONFIG with DALL·E model configuration options [+] chore(config.ts): update version to 4.1 for DALL·E Models [+] chore(config.ts): add migration logic for DALL·E model configuration options
[+] fix(openai.ts): update max_tokens value to Math.max(modelConfig.max_tokens, 1024)
[+] fix(openai.ts): change condition to check if defaultModel starts with "dall-e" instead of includes "dall-e" [+] refactor(openai.ts): simplify condition to check if defaultModel starts with "dall-e" [+] refactor(openai.ts): simplify condition to check if defaultModel starts with "dall-e" and ends with "-vision"
[+] fix(openai.ts): refactor model check logic to use startsWith and endsWith methods instead of includes method
This reverts commit cc5f57b. Reason : So bad using max_tokens for old models (include gpt-4) openai lmao
[+] chore(config.ts): update version number to 4.2 in useAppConfig [+] docs(config.ts): add comment about version 4.2 in useAppConfig migrate function
[+] refactor(openai.ts): move getNewStuff method out of nested scope and make it a member of ChatGPTApi class [+] feat(openai.ts): add support for isNewModel flag in getNewStuff method [+] refactor(openai.ts): remove unused commented code in getModelForInstructVersion method [+] feat(openai.ts): add magicPayload parameter to chat method for TypeScript payload [+] refactor(openai.ts): simplify console log statements in chat method [+] refactor(openai.ts): remove unused variables in chat method [+] feat(openai.ts): add getModelForInstructVersion method for DALL·E Instruct support [+] feat(openai.ts): add comment for DALL·E Instruct section
[+] fix(openai.ts): add support for generating image description for dall-e-3 models
[+] refactor(model-config): add comments to indicate future refactor for DALL·E 3 models configuration style [+] feat(model-config): add input fields for configuring number of images, quality of images, size of images, and style of images for DALL·E 3 models [+] feat(config): add validation functions for number of images, quality of images, size of images, style of images, and system fingerprint
[+] fix(openai.ts): remove unnecessary condition for InstrucModel assignment [+] feat(chat.ts): simplify condition for topicModel and summarizeModel assignment
[+] chore(chat.ts): add 'stream' property to config object in useChatStore function [+] refactor(chat.ts): destructure 'max_tokens' property from modelConfig object in useChatStore function [+] feat(chat.ts): show toast notification on successful summarize [+] fix(chat.ts): show toast notification on summarize error
[+] feat(model-config.tsx): add support for selecting size and style options in ModelConfigList component [+] fix(model-config.tsx): fix typo in ModelConfigList component [+] refactor(model-config.tsx): refactor the configuration style for the DALL·E 3 models in ModelConfigList component
[+] fix(model-config.tsx): update onChange event handlers to use ModalConfigValidator for quality, size, and style values
[+] chore(constant.ts): fix OPENAI_BASE_URL to remove trailing slash [+] feat(constant.ts): add ServiceProvider enum with OpenAI and Azure options [+] feat(constant.ts): add Azure.ExampleEndpoint constants
[+] fix(chat.tsx): change accessStore token property to openaiApiKey
[+] refactor(auth.tsx): rename access variable to accessStore for better clarity and readability [+] feat(auth.tsx): update accessStore state using immer produce function for resetAccessCode and input onChange events
[+] chore(server.ts): refactor server configuration file
[+] refactor(hi.ts): remove unused CustomModel translations
[+] feat(model-config): add temperature input range to ModelConfigList component
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
*draft
Logs :
Refactor Mask UI Page [Masks] ChatGPTNextWeb#2993
Fix typo in sync.ts ChatGPTNextWeb#2992
fix: ChatGPTNextWeb#2981 full screen button not works ChatGPTNextWeb#2983 (already merged to main branch)
Feat Build Setup
(Docs) Add support for Llama2, Claude, Palm, Cohere, Replicate (100+ LLMs) ChatGPTNextWeb#3000
(Docs) 提供同步聊天记录教程,同时翻译多国语言 ChatGPTNextWeb#2996
(Docs) docs: fix typo in app/masks/en.ts ChatGPTNextWeb#3003
more : https://github.com/H0llyW00dzZ/ChatGPT-Next-Web/pull/52/commits