> ## Documentation Index
> Fetch the complete documentation index at: https://asyncfunc.mintlify.app/llms.txt
> Use this file to discover all available pages before exploring further.
# Introduction to DeepWiki-Open
> AI-powered documentation generator that creates beautiful, interactive wikis for any GitHub, GitLab, or BitBucket repository
**DeepWiki-Open** is an innovative AI-powered documentation generator that automatically creates comprehensive, interactive wikis for any GitHub, GitLab, or BitBucket repository. Transform your codebase into beautiful, navigable documentation in seconds.
## What is DeepWiki-Open?
DeepWiki-Open analyzes your repository's code structure, understands the relationships between components, and generates:
Comprehensive documentation with code analysis and explanations
Automatic Mermaid diagrams showing architecture and data flow
RAG-powered Q\&A system to chat with your repository
Multi-turn AI research for complex code analysis
## Key Features
### 🚀 Instant Documentation Generation
Simply enter a repository URL and DeepWiki will analyze the code structure, generate comprehensive documentation, and create visual diagrams to explain how everything works.
### 🔐 Private Repository Support
Securely access private repositories with personal access tokens from GitHub, GitLab, or BitBucket.
### 🤖 Multiple AI Model Providers
Choose from leading AI providers:
* **Google Gemini** (default: gemini-2.0-flash)
* **OpenAI** (gpt-4o, o1, o3, o4-mini)
* **OpenRouter** (access to Claude, Llama, Mistral, and more)
* **Azure OpenAI** (enterprise-grade deployment)
* **Ollama** (local open-source models)
* **Amazon Bedrock** (AWS-hosted models)
* **DashScope** (Alibaba Qwen models)
### 💬 Intelligent Q\&A System
The **Ask Feature** uses Retrieval Augmented Generation (RAG) to provide accurate answers based on your repository's actual code.
### 🔍 Advanced Research Capabilities
**DeepResearch** conducts multi-turn investigations for complex topics, providing comprehensive analysis through multiple research iterations.
### 🌍 International Support
Built-in support for 10+ languages including English, Chinese, Japanese, Spanish, Korean, Vietnamese, Portuguese, French, and Russian.
## How It Works
DeepWiki clones and analyzes your repository structure, including private repos with token authentication.
Creates embeddings of the code for smart retrieval and uses AI to generate documentation with context-aware understanding.
Generates Mermaid diagrams to explain code relationships and system architecture.
Organizes everything into a structured, navigable wiki with intelligent Q\&A capabilities.
## Architecture Overview
```mermaid theme={null}
graph TD
A[User inputs GitHub/GitLab/BitBucket repo] --> AA{Private repo?}
AA -->|Yes| AB[Add access token]
AA -->|No| B[Clone Repository]
AB --> B
B --> C[Analyze Code Structure]
C --> D[Create Code Embeddings]
D --> M{Select Model Provider}
M -->|Google Gemini| E1[Generate with Gemini]
M -->|OpenAI| E2[Generate with OpenAI]
M -->|OpenRouter| E3[Generate with OpenRouter]
M -->|Local Ollama| E4[Generate with Ollama]
M -->|Azure| E5[Generate with Azure]
E1 --> E[Generate Documentation]
E2 --> E
E3 --> E
E4 --> E
E5 --> E
D --> F[Create Visual Diagrams]
E --> G[Organize as Wiki]
F --> G
G --> H[Interactive DeepWiki]
classDef process stroke-width:2px;
classDef data stroke-width:2px;
classDef result stroke-width:2px;
classDef decision stroke-width:2px;
class A,D data;
class AA,M decision;
class B,C,E,F,G,AB,E1,E2,E3,E4,E5 process;
class H result;
```
## Project Structure
The DeepWiki-Open project consists of:
```
src/
├── app/ # Next.js app directory
│ ├── page.tsx # Main application page
│ └── api/ # API routes
├── components/ # React components
│ ├── Ask.tsx # Q&A interface
│ ├── Mermaid.tsx # Diagram renderer
│ └── ...
└── utils/ # Utility functions
```
```
api/
├── main.py # API entry point
├── api.py # FastAPI implementation
├── rag.py # RAG system
├── data_pipeline.py # Data processing
├── config/ # Configuration files
│ ├── generator.json # Model configurations
│ ├── embedder.json # Embedding settings
│ └── repo.json # Repository settings
└── requirements.txt # Python dependencies
```
## Quick Start
Ready to get started? Choose your preferred setup method:
Get up and running in minutes with Docker Compose
Install and configure manually for development
You'll need API keys from your chosen AI provider (Google, OpenAI, etc.) to get started. See the [Environment Variables](/getting-started/environment-variables) guide for details.
## Next Steps
Get DeepWiki running in under 5 minutes
Configure your AI model providers
Learn about all DeepWiki features
Explore the REST API endpoints