它是ChatGPT (OpenAI API) 的桌面客户端，Prompt 调试与管理工具，支持 Win、Mac 和 Linux。
◎ 特性
• 更自由、更强大的 prompt 能力
• 数据存储在本地，不会丢失
• 支持 GPT-4 和其他模型
• 支持自定义域名代理
下载地址-https://github.com/Bin-Huang/chatbox/releases
项目地址-https://github.com/Bin-Huang/chatbox
-------------
Chatbox-开源跨平台的ChatGPT客户端程序
Chatbox，一款开源跨平台的ChatGPT客户端，Prompt 的调试与管理工具，基于 ChatGPT API (OpenAI API) 开发的桌面客户端，支持 GPT-4 和其他模型，并且数据存储在本地，响应速度和 ChatGPT Plus 一样快，支持 Windows、Mac 和 Linux，还支持Markdown、消息引用、字数与token估算等等，不过使用需要自备ChatGPT API key的，工具开源免费。
开源跨平台的ChatGPT客户端下载
下载页：https://github.com/Bin-Huang/chatbox/releases
GitHub页面：https://github.com/Bin-Huang/chatbox
api key获取地址（需要自备ChatGPT账号的哈）：https://platform.openai.com/account/api-keys
----------------------------------------------------------------
Powerful AI Client
chatboxai.app
This is the repository for the Chatbox Community Edition, open-sourced under the GPLv3 license.
Chatbox is going open-source Again!
We regularly sync code from the pro repo to this repo, and vice versa.
| Windows | MacOS | Linux | |
 Setup.exe |  Intel | Apple Silicon |  AppImage |
.APKFor more information: chatboxai.app
- Download the appropriate installer for your platform from the releases page
- Install and launch Chatbox
- Configure your AI provider (OpenAI, Claude, etc.) in settings
- Start chatting!
| Platform | Minimum Version | Architecture |
|---|---|---|
| Windows | Windows 10 | x64 |
| macOS | macOS 11 (Big Sur) | Intel/Apple Silicon |
| Linux | Ubuntu 20.04+ / AppImage supported distros | x64 |
Your Ultimate AI Copilot on the Desktop.
Chatbox is a desktop client for ChatGPT, Claude and other LLMs, available on Windows, Mac, Linux
Support for Multiple LLM Providers
⚙️ Seamlessly integrate with a variety of cutting-edge language models:- OpenAI (ChatGPT)
- Azure OpenAI
- Claude
- Google Gemini Pro
- Ollama (enable access to local models like llama2, Mistral, Mixtral, codellama, vicuna, yi, and solar)
- ChatGLM-6B
Image Generation with Dall-E-3
🎨 Create the images of your imagination with Dall-E-3.Enhanced Prompting
💬 Advanced prompting features to refine and focus your queries for better responses.
Local Data Storage
💾 Your data remains on your device, ensuring it never gets lost and maintains your privacy.No-Deployment Installation Packages
📦 Get started quickly with downloadable installation packages. No complex setup necessary!Ergonomic UI & Dark Theme
🌑 A user-friendly interface with a night mode option for reduced eye strain during extended use.Keyboard Shortcuts
⌨️ Stay productive with shortcuts that speed up your workflow.Streaming Reply
▶️ Provide rapid responses to your interactions with immediate, progressive replies.
Markdown, Latex & Code Highlighting
📜 Generate messages with the full power of Markdown and Latex formatting, coupled with syntax highlighting for various programming languages, enhancing readability and presentation.Prompt Library & Message Quoting
📚 Save and organize prompts for reuse, and quote messages for context in discussions.
- Team Collaboration
👥 Collaborate with ease and share OpenAI API resources among your team. Learn More
Cross-Platform Desktop
💻 Chatbox is ready for Windows, Mac, and Linux users.Web Version
🌐 Use the web application on any device with a browser, anywhere.Mobile Apps
☎️ Native iOS and Android applications for on-the-go access.
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
📝 NOTE: OpenAssistant is completed, and the project is now finished. Thank you to everyone who contributed! Check out our blog post for more information. The final published oasst2 dataset can be found on HuggingFace at OpenAssistant/oasst2
Open Assistant is a project meant to give everyone access to a great chat based large language model.
We believe that by doing this we will create a revolution in innovation in language. In the same way that stable-diffusion helped the world make art and images in new ways we hope Open Assistant can help improve the world by improving language itself.
The chat frontend is now live here. Log in and start chatting! Please try to react with a thumbs up or down for the assistant's responses when chatting.
The data collection frontend is now live here. Log in and start taking on tasks! We want to collect a high volume of quality data. By submitting, ranking, and labelling model prompts and responses you will be directly helping to improve the capabilities of Open Assistant.
You do not need to run the project locally unless you are contributing to the development process. The website link above will take you to the public website where you can use the data collection app and the chat.
If you would like to run the data collection app locally for development, you can set up an entire stack needed to run Open-Assistant, including the website, backend, and associated dependent services, with Docker.
To start the demo, run this in the root directory of the repository (check this FAQ if you have problems):
docker compose --profile ci up --build --attach-dependenciesNote: when running on MacOS with an M1 chip you have to use:
DB_PLATFORM=linux/x86_64 docker compose ...
Then, navigate to http://localhost:3000 (It may take some time to boot up) and
interact with the website.
Note: If an issue occurs with the build, please head to the FAQ and check out the entries about Docker.
Note: When logging in via email, navigate to
http://localhost:1080to get the magic email login link.
Note: If you would like to run this in a standardized development environment (a "devcontainer") using vscode locally or in a web browser using GitHub Codespaces, you can use the provided
.devcontainerfolder.
You do not need to run the project locally unless you are contributing to the development process. The website link above will take you to the public website where you can use the data collection app and the chat.
Also note that the local setup is only for development and is not meant to be used as a local chatbot, unless you know what you are doing.
If you do know what you are doing, then see the inference folder for getting
the inference system up and running, or have a look at --profile inference in
addition to --profile ci in the above command.
We are not going to stop at replicating ChatGPT. We want to build the assistant of the future, able to not only write email and cover letters, but do meaningful work, use APIs, dynamically research information, and much more, with the ability to be personalized and extended by anyone. And we want to do this in a way that is open and accessible, which means we must not only build a great assistant, but also make it small and efficient enough to run on consumer hardware.
We want to get to an initial MVP as fast as possible, by following the 3-steps outlined in the InstructGPT paper
- Collect high-quality human generated Instruction-Fulfillment samples (prompt + response), goal >50k. We design a crowdsourced process to collect and reviewed prompts. We do not want to train on flooding/toxic/spam/junk/personal information data. We will have a leaderboard to motivate the community that shows progress and the most active users. Swag will be given to the top-contributors.
- For each of the collected prompts we will sample multiple completions. Completions of one prompt will then be shown randomly to users to rank them from best to worst. Again this should happen crowd-sourced, e.g. we need to deal with unreliable potentially malicious users. At least multiple votes by independent users have to be collected to measure the overall agreement. The gathered ranking-data will be used to train a reward model.
- Now follows the RLHF training phase based on the prompts and the reward model.
We can then take the resulting model and continue with completion sampling step 2 for a next iteration.
from https://github.com/LAION-AI/Open-Assistant
No comments:
Post a Comment