A universal API client for managing knowledge bases and performing Retrieval-Augmented Generation (RAG) within self-hosted Ragflow instances.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install ragflow
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install ragflow using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Ragflow API Client?
The Ragflow API Client is a robust integration designed for developers who utilize self-hosted Retrieval-Augmented Generation (RAG) platforms. By incorporating this into your Openclaw Skills library, you gain the ability to programmatically interface with Ragflow's ecosystem to create datasets, manage documents, and execute complex retrieval queries. This skill serves as a bridge between your local development environment and your private knowledge bases, ensuring high-performance AI responses derived from your specific data.
Built to handle the technical heavy lifting of RAG operations, this tool simplifies the lifecycle of document management. It allows AI agents to interact directly with datasets, making it an essential component for anyone building privacy-conscious search or research applications. Using Openclaw Skills like this one ensures that your AI agents remain contextually aware and data-driven without sacrificing the security of a self-hosted infrastructure.
Ragflow API Client Use Cases
- Automating the creation and organization of knowledge base datasets for specific projects.
- Seamlessly uploading local Markdown or text files to a central RAG platform for indexing.
- Building AI-driven research tools that query private document repositories for accurate answers.
- Managing document parsing and chunking workflows to optimize search relevance.
How Ragflow API Client Works
- The skill initializes by connecting to your self-hosted Ragflow instance via a secure API key and URL configuration.
- Users can create specialized datasets through the CLI or programmatic API to categorize different knowledge domains.
- Files or raw text are uploaded to these datasets, where the skill triggers the internal Ragflow parsing engine.
- Documents are segmented into searchable chunks, allowing for high-precision vector search indexing.
- The skill executes chat queries by retrieving relevant context from the datasets and returning synthesized answers.
Ragflow API Client Setup
To get started with this skill, you must provide your Ragflow instance details in your environment configuration. Ensure you have Node.js installed on your system.
Edit your .env file to include:
RAGFLOW_URL=https://your-ragflow-instance.com
RAGFLOW_API_KEY=your-api-key
You can then verify the setup by listing your existing datasets:
node scripts/ragflow.js datasets
Ragflow API Client Data Schema & Taxonomy
The Ragflow skill manages data through a structured relationship between datasets and documents. The following table describes the primary data entities:
| Entity | Description |
|---|---|
| Dataset | The top-level container for organizing knowledge bases. |
| Document | The source files (e.g., .md, .pdf) uploaded for processing. |
| Chunk | The processed segments of documents used for semantic retrieval. |
| Retrieval Query | The request parameters used to fetch context-aware answers from the vector store. |
Ragflow API Client Advanced Features
- Programmatic integration support for custom Node.js applications and automation scripts.
- Manual chunk management allowing users to trigger parsing sequences for specific documents.
- Multi-dataset support enabling AI agents to switch between different knowledge silos dynamically.
- Full compatibility with the Openclaw Skills framework for building sophisticated multi-agent workflows.
SKILL.md
Loading
Related Openclaw Skills
PMC Harvest
A specialized utility for searching and harvesting full-text scientific articles and metadata from PubMed Central using official NCBI APIs.
Mealie
A powerful API client for Mealie that lets you manage recipes, meal plans, and shopping lists through AI-driven workflows.
Crawl4AI Web Scraper
A powerful web scraping skill for AI agents that leverages local Crawl4AI instances to extract full-page content with JavaScript rendering.
Cozi Family Organizer
A powerful integration that allows AI agents to interact directly with the Cozi Family Organizer for managing shared schedules and lists.
Stirling-PDF
A comprehensive self-hosted PDF manipulation suite providing over 60 tools for document processing via a robust REST API.
Research Swarm TNBC Research Skill
A collaborative multi-agent skill for conducting and reviewing scientific research on Triple-Negative Breast Cancer.
METADATA
Featured*
