ApeRAG is a production-ready RAG (Retrieval-Augmented Generation) platform that combines Graph RAG, vector search, and full-text search with advanced AI agents. Build sophisticated AI applications with hybrid retrieval, multimodal document processing, intelligent agents, and ente
How to install aperag?
apecloud/aperag
$git clone https://github.com/apecloud/aperagInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install aperag by running `git clone https://github.com/apecloud/aperag`, then use it for the current task and follow its documentation at https://github.com/apecloud/aperag.
README.md
| 1 | # ApeRAG |
| 2 | [](https://archestra.ai/mcp-catalog/apecloud__aperag) |
| 3 | |
| 4 |  |
| 5 | |
| 6 |  |
| 7 | |
| 8 | |
| 9 | ApeRAG is a production-ready RAG (Retrieval-Augmented Generation) platform that combines Graph RAG, vector search, and full-text search with advanced AI agents. Build sophisticated AI applications with hybrid retrieval, multimodal document processing, intelligent agents, and enterprise-grade management features. |
| 10 | |
| 11 | ApeRAG is the best choice for building your own Knowledge Graph, Context Engineering, and deploying intelligent AI agents that can autonomously search and reason across your knowledge base. |
| 12 | |
| 13 | [阅读中文文档](README-zh.md) |
| 14 | |
| 15 | - [Quick Start](#quick-start) |
| 16 | - [Key Features](#key-features) |
| 17 | - [Kubernetes Deployment (Recommended for Production)](#kubernetes-deployment-recommended-for-production) |
| 18 | - [Development](./docs/en-US/development-guide.md) |
| 19 | - [Build Docker Image](./docs/en-US/build-docker-image.md) |
| 20 | - [Acknowledgments](#acknowledgments) |
| 21 | - [License](#license) |
| 22 | |
| 23 | ## Quick Start |
| 24 | |
| 25 | > Before installing ApeRAG, make sure your machine meets the following minimum system requirements: |
| 26 | > |
| 27 | > - CPU >= 2 Core |
| 28 | > - RAM >= 4 GiB |
| 29 | > - Docker & Docker Compose |
| 30 | |
| 31 | The easiest way to start ApeRAG is through Docker Compose. Before running the following commands, make sure that [Docker](https://docs.docker.com/get-docker/) and [Docker Compose](https://docs.docker.com/compose/install/) are installed on your machine: |
| 32 | |
| 33 | ```bash |
| 34 | git clone https://github.com/apecloud/ApeRAG.git |
| 35 | cd ApeRAG |
| 36 | cp envs/env.template .env |
| 37 | docker-compose up -d --pull always |
| 38 | ``` |
| 39 | |
| 40 | After running, you can access ApeRAG in your browser at: |
| 41 | - **Web Interface**: http://localhost:3000/web/ |
| 42 | - **API Documentation**: http://localhost:8000/docs |
| 43 | |
| 44 | #### MCP (Model Context Protocol) Support |
| 45 | |
| 46 | ApeRAG supports [MCP (Model Context Protocol)](https://modelcontextprotocol.io/) integration, allowing AI assistants to interact with your knowledge base directly. After starting the services, configure your MCP client with: |
| 47 | |
| 48 | ```json |
| 49 | { |
| 50 | "mcpServers": { |
| 51 | "aperag-mcp": { |
| 52 | "url": "http://localhost:8000/mcp/", |
| 53 | "headers": { |
| 54 | "Authorization": "Bearer your-api-key-here" |
| 55 | } |
| 56 | } |
| 57 | } |
| 58 | } |
| 59 | ``` |
| 60 | |
| 61 | **Authentication** (by priority): |
| 62 | 1. **HTTP Authorization Header** (Recommended): `Authorization: Bearer your-api-key` |
| 63 | 2. **Environment Variable** (Fallback): `APERAG_API_KEY=your-api-key` |
| 64 | |
| 65 | **Important**: Use your deployed API origin if not local (e.g. `https://your-host/mcp/`). Replace `your-api-key-here` with a valid API key from your ApeRAG settings. |
| 66 | |
| 67 | The MCP server provides: |
| 68 | - **Collection browsing**: List and explore your knowledge collections |
| 69 | - **Hybrid search**: Search using vector, full-text, and graph methods |
| 70 | - **Intelligent querying**: Ask natural language questions about your documents |
| 71 | |
| 72 | #### Enhanced Document Parsing |
| 73 | |
| 74 | For enhanced document parsing capabilities, ApeRAG supports an **advanced document parsing service** powered by MinerU, which provides superior parsing for complex documents, tables, and formulas. |
| 75 | |
| 76 | <details> |
| 77 | <summary><strong>Enhanced Document Parsing Commands</strong></summary> |
| 78 | |
| 79 | ```bash |
| 80 | # Enable advanced document parsing service |
| 81 | DOCRAY_HOST=http://aperag-docray:8639 docker compose --profile docray up -d |
| 82 | |
| 83 | # Enable advanced parsing with GPU acceleration |
| 84 | DOCRAY_HOST=http://aperag-docray-gpu:8639 docker compose --profile docray-gpu up -d |
| 85 | ``` |
| 86 | |
| 87 | Or use the Makefile shortcuts (requires [GNU Make](https://www.gnu.org/software/make/)): |
| 88 | ```bash |
| 89 | # Enable advanced document parsing service |
| 90 | make compose-up WITH_DOCRAY=1 |
| 91 | |
| 92 | # Enable advanced parsing with GPU acceleration (recommended) |
| 93 | make compose-up WITH_DOCRAY=1 WITH_GPU=1 |
| 94 | ``` |
| 95 | |
| 96 | </details> |
| 97 | |
| 98 | #### Development & Contributing |
| 99 | |
| 100 | For developers interested in source code development, advanced configurations, or contributing to ApeRAG, please refer to our [Development Guide](./docs/en-US/development-guide. |
Related
6 picksType
- langchain-mcp-adaptersMake Anthropic Model Context Protocol (MCP) tools compatible with LangChain and LangGraph agents.Jul 2026
- mcporterTypeScript runtime and CLI for connecting to configured Model Context Protocol servers.Jul 2026
- mcp-proxyA MCP server which proxies requests to a remote MCP server over streamable HTTP or SSE.Jul 2026
- mcp-atlassianThe Model Context Protocol (MCP) Atlassian integration is an open-source implementation that bridges Atlassian products (Jira and Confluence) with AI language models following Anthropic's MCP specification.Jul 2026
- open-webuiOpen WebUIJul 2026
- rulesyncUnified AI rules management CLI tool that generates configuration files for various AI development toolsJul 2026
