mirror of
https://github.com/danny-avila/LibreChat.git
synced 2025-09-22 06:00:56 +02:00
Enhanced ChatGPT Clone: Features Agents, MCP, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Presets, open-source for self-hosting. Active.
https://librechat.ai/
aianthropicartifactsawsazurechatgptchatgpt-cloneclaudeclonedeepseekgeminigooglegpt-5librechatmcpo1openairesponses-apivisionwebui
dade7b450f
* feat: Add clear button to search bar This commit introduces a clear button to the SearchBar component using the X icon from Lucide-React. When the user enters a query in the input field, the clear button appears allowing them to easily remove the search term. The clear button is hidden when there is no search term entered. * Refactor SearchBar component to improve user experience Changed SearchBar's input field to add padding on the left side and an absolute positioned search icon. Also, added absolute positioned X icon on the right side when there is an input value, ensuring a better user experience. * Refactor SearchBar component to show Clear Search icon dynamically This commit makes changes to the SearchBar React component to render the Clear Search X icon only when the input field has a value. A showClearIcon state using useState hook is added and updated every time the input value changes. The useEffect hook is used to handle the case when the user clears the input value. This allows better UX by providing clear intent to the user that the icon is clickable and will clear the search query. * Improve UX: Add styling to clear button & export button This commit modifies the NavLinks component to improve user experience by removing a rounded styling to the "Clear conversations" and "Export conversations" buttons. Prior to this change, the buttons had a rounded styling. * Refactor submit button styling for improved accessibility and readability. Changed submit button styling for better accessibility and readability, including adjustments to padding and hover effects. The new styles ensure that the button is easily clickable for all users, while also improving its visual appearance. * hotfix * Improve UI styling in Conversation component Changed the background color and hover effect of the conversation link in Conversation component to make it more visually appealing. The previous background color was '#2A2B32' and now it's 'gray-800'. The 'px-4' class has also been changed to 'hover:pr-4' for better readability. --------- Co-authored-by: Danny Avila <110412045+danny-avila@users.noreply.github.com> |
||
|---|---|---|
| .github | ||
| .husky | ||
| api | ||
| client | ||
| docs | ||
| e2e | ||
| images | ||
| .dockerignore | ||
| .eslintrc.js | ||
| .gitignore | ||
| .prettierrc.js | ||
| CHANGELOG.md | ||
| CODE_OF_CONDUCT.md | ||
| CONTRIBUTING.md | ||
| docker-compose.yml | ||
| Dockerfile | ||
| LICENSE.md | ||
| lint-staged.config.js | ||
| package-lock.json | ||
| package.json | ||
| README.md | ||
| SECURITY.md | ||
ChatGPT Clone
All AI Conversations under One Roof.
Assistant AIs are the future and OpenAI revolutionized this movement with ChatGPT. While numerous UIs exist, this app commemorates the original styling of ChatGPT, with the ability to integrate any current/future AI models, while integrating and improving upon original client features, such as conversation/message search and prompt templates (currently WIP). Through this clone, you can avoid ChatGPT Plus in favor of free or pay-per-call APIs. I will soon deploy a demo of this app. Feel free to contribute, clone, or fork. Currently dockerized.
Features
- Response streaming identical to ChatGPT through server-sent events
- UI from original ChatGPT, including Dark mode
- AI model selection (through 3 endpoints: OpenAI API, BingAI, and ChatGPT Browser)
- Create, Save, & Share custom presets for OpenAI and BingAI endpoints - More info on customization here
- Edit and Resubmit messages just like the official site (with conversation branching)
- Search all messages/conversations - More info here
- Integrating plugins soon
Sponsors
Sponsored by @DavidDev1334, @mjtechguy, @Pharrcyde, & @fuegovic
Google's PaLM 2 is now supported as of v0.4.3
How to Setup PaLM 2 (via Google Cloud Vertex AI API)
- Enable the Vertex AI API on Google Cloud: - - https://console.cloud.google.com/vertex-ai - Create a Service Account: - - https://console.cloud.google.com/projectselector/iam-admin/serviceaccounts/create?walkthrough_id=iam--create-service-account#step_index=1 - Make sure to click 'Create and Continue' to give at least the 'Vertex AI User' role. - Create a JSON key, rename as 'auth.json' and save it in /api/data/.Alternatively
- In your ./api/.env file, set PALM_KEY as "user_provided" to allow the user to provide a Service Account key JSON from the UI.
- They will follow the steps above except for renaming the file, simply importing the JSON when prompted.
- The key is sent to the server but never saved except in your local storage
Note:
- Vertex AI does not (yet) support response streaming for text generations, so response may seem to take long when generating a lot of text.
- Text streaming is simulated
Read all Latest Updates here
Table of Contents
Getting Started
General Information
Features
Cloud Deployment
Contributions
Star History
Contributors
Contributions and suggestions bug reports and fixes are welcome! Please read the documentation before you do!
For new features, components, or extensions, please open an issue and discuss before sending a PR.
- Join the Discord community