Skip to content

Latest commit

 

History

History
222 lines (185 loc) · 8.64 KB

README.md

File metadata and controls

222 lines (185 loc) · 8.64 KB

logo

DeepChat

Dolphins are good friends of whales, and DeepChat is your good assistant

中文 / English / 日本語

Reasoning

Search

Latex

Artifacts support

Main Features

  • 🌐 Supports multiple cloud LLM providers: DeepSeek, OpenAI, Silicon Flow, Grok, Gemini, Anthropic, etc.
  • 🏠 Supports local model deployment: Ollama, with comprehensive management capabilities, allowing control and management of Ollama model downloads, deployments, and runs without command-line operations.
  • 🚀 Rich and easy-to-use chatbot capabilities
    • Complete Markdown rendering with excellent code block display.
    • Native support for simultaneous multi-session conversations; start new sessions without waiting for model generation to finish, maximizing efficiency.
    • Supports Artifacts rendering for diverse result presentation, significantly saving token consumption after MCP integration.
    • Messages support retry to generate multiple variations; conversations can be forked freely, ensuring there's always a suitable line of thought.
    • Supports rendering images, Mermaid diagrams, and other multi-modal content; includes Gemini's text-to-image capabilities.
    • Supports highlighting external information sources like search results within the content.
  • 🔍 Robust search extension capabilities
    • Built-in integration with leading search APIs like Brave Search via MCP mode, allowing the model to intelligently decide when to search.
    • Supports mainstream search engines like Google, Bing, Baidu, and Sogou Official Accounts search by simulating user web browsing, enabling the LLM to read search engines like a human.
    • Supports reading any search engine; simply configure a search assistant model to connect various search sources, whether internal networks, API-less engines, or vertical domain search engines, as information sources for the model.
  • 🔧 Excellent MCP (Model Controller Platform) support
    • Extremely user-friendly configuration interface.
    • Aesthetically pleasing and clear tool call display.
    • Detailed tool call debugging window with automatic formatting of tool parameters and return data.
    • Built-in Node.js runtime environment; npx-like services require no extra configuration.
    • Supports StreamableHTTP/SSE/Stdio protocols.
    • Supports inMemory services with built-in utilities like code execution, web information retrieval, and file operations; ready for most common use cases out-of-the-box without secondary installation.
    • Converts visual model capabilities into universally usable functions for any model via the built-in MCP service.
  • 💻 Multi-platform support: Windows, macOS, Linux.
  • 🎨 Beautiful and user-friendly interface, user-oriented design, meticulously themed light and dark modes.
  • 🔗 Rich DeepLink support: Initiate conversations via links for seamless integration with other applications. Also supports one-click installation of MCP services for simplicity and speed.
  • 🚑 Security-first design: Chat data and configuration data have reserved encryption interfaces and code obfuscation capabilities.
  • 🛡️ Privacy protection: Supports screen projection hiding, network proxies, and other privacy protection methods to reduce the risk of information leakage.
  • 💰 Business-friendly, embraces open source, based on the Apache License 2.0 protocol.

Currently Supported Model Providers


Ollama
Deepseek
Silicon
QwenLM

Doubao
MiniMax
Fireworks
PPIO

OpenAI
Gemini
GitHub Models
Moonshot

OpenRouter
Azure OpenAI
Qiniu
Grok

Compatible with any model provider in OpenAI/Gemini/Anthropic API format

Other Features

  • Support for local model management with Ollama
  • Support for local file processing
  • Artifacts support
  • Customizable search engines (parsed through models, no API adaptation required)
  • MCP support (built-in npx, no additional node environment installation needed)
  • Support for multimodality models
  • Local chat data backup and recovery
  • Compatibility with any model provider in OpenAI, Gemini, and Anthropic API formats

Development

Please read the Contribution Guidelines Windows and Linux are packaged by GitHub Action. For Mac-related signing and packaging, please refer to the Mac Release Guide.

Install dependencies

$ npm install
$ npm run installRuntime
# if got err: No module named 'distutils'
$ pip install setuptools
# for windows x64
$ npm install --cpu=x64 --os=win32 sharp
# for mac apple silicon
$ npm install --cpu=arm64 --os=darwin sharp
# for mac intel
$ npm install --cpu=x64 --os=darwin sharp
# for linux x64
$ npm install --cpu=x64 --os=linux sharp

Start development

$ npm run dev

Build

# For windows
$ npm run build:win

# For macOS
$ npm run build:mac

# For Linux
$ npm run build:linux

# Specify architecture packaging
$ npm run build:win:x64
$ npm run build:win:arm64
$ npm run build:mac:x64
$ npm run build:mac:arm64
$ npm run build:linux:x64
$ npm run build:linux:arm64

Star History

Star History Chart

Contributors

Thank you for considering contributing to deepchat! The contribution guide can be found in the Contribution Guidelines.

📃 License

LICENSE