English | 简体中文 | Update Log
ChatWiki is an open-source knowledge base AI question-and-answer system. The system is built upon Large Language Models (LLM) and Retrieval-Augmented Generation (RAG) technology, offering out-of-the-box capabilities for data processing and model invocation. It can assist enterprises in rapidly constructing their own knowledge base AI question-and-answer systems.
1. Exclusive AI Question-and-Answer System
By importing existing corporate knowledge to build a knowledge base, AI robots can use the associated knowledge base to answer questions, rapidly constructing an enterprise-specific AI question-and-answer system.
2. One-Click Model Integration
ChatWiki supports more than 20 mainstream models globally. Simply configure the model API key and other information for successful model integration.
3. Automatic Data Preprocessing
ChatWiki offers various data import methods such as automatic segmentation, QA segmentation, manual input, and CSV. It automatically preprocesses, vectorizes, or QA segments the imported text data.
4. Simple and User-Friendly Usage
ChatWiki features an intuitive visual interface design. With straightforward and easy-to-understand steps, users can effortlessly create AI question-and-answer robots and knowledge bases.
5. Adaptable to Different Business Scenarios
ChatWiki provides different channels for AI question-and-answer robots, supporting WebAPP, website embedding, desktop clients, etc., to meet the diverse usage requirements of different business scenarios.
Before installing ChatWiki, you need to prepare a Linux server with internet connectivity and ensure that the server meets the minimum system requirements:
-
CPU: At least 2 cores
-
RAM: At least 4GB
Installation
ChatWiki Community Edition is deployed using Docker. Please ensure that Docker is already installed on your server. If not, you can install it with the following command:
sudo curl -sSL https://get.docker.com/ | CHANNEL=stable sh
After installing Docker, follow the steps below to install ChatWiki Community Edition:
(1). Clone or download the ChatWiki project code
git clone https://github.com/zhimaAi/chatwiki.git(2). Use Docker Compose to build and start the project
cd chatwiki/docker
docker compose up -dDeployment Manual
If you encounter any problems or have suggestions during the installation and deployment, you can contact us for help, or refer to the following documentation:
- One-click Deployment of ChatWiki Community Edition
- How to Configure Model Providers and Supported Models
- Local Model Deployment
- How to Configure External Services and Domain Names for Receiving Push Notifications
- Docker-Free Deployment of ChatWiki
- How to Obtain the Large Model ApiKey
- Frontend: vue.js
- Backend: golang + python
- Database: PostgreSQL 16 + pgvector + zhparser
- Caching: redis 5.0
- Web Service: nginx
- Asynchronous Queue: nsq
- Process Management: supervisor
- Models: Supports models from OpenAI, Google Gemini, Claude3, Tongyi Qianwen, Wenxin Yiyi, Xunfei Xinghuo, Baichuan, Tencent Hunyuan, etc.
We welcome you to contact us for assistance or to provide suggestions to help us improve ChatWiki. You can reach us through the following methods:
-
WeChat: Join the ChatWiki Technical Exchange Group by Scanning the WeChat QR Code
-
Email: You can email us at [email protected] to get in touch.
This repository is governed by the ChatWiki Open Source License, which is based on the Apache License 2.0 but includes some additional restrictions:
- Commercial use as a backend service is allowed, but it cannot be used in a multi-tenant SAAS mode.
- Unless you obtain a specific commercial license, you may not remove the copyright information and ChatWiki logo from any commercial service pages.
For the complete license, please review the ChatWiki Open Source License. If you need to obtain an additional commercial license, please contact us.