n8n-nodes-ragflow

This is an n8n community node for interacting with RAGFlow, an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

Features

• Dynamic Dataset Selection: Automatically fetches your RAGFlow datasets into a dropdown list.
• Smart Text Upsert:
  • Automatically appends .txt extension to text content uploads (fixing "file type not supported" errors).
  • Supports Skip or Overwrite strategies for duplicate documents.
  • Note: Triggers parsing automatically using RAGFlow's document chunking API.
• AI-Optimized Retrieval:
  • Returns a flattened context_text field ready for direct injection into LLM Prompts.
  • Provides detailed chunks array with similarity scores and document mapping.

Operations

1. Upsert Text (Email/Content): Upload text content to a dataset.
2. Retrieve (Search/Chat): Search your dataset for relevant context based on a query.

Installation

Community Node (Recommended)

1. Go to Settings > Community Nodes in your n8n instance.
2. Select Install.
3. Enter n8n-nodes-ragflow.
4. Agree to the risks and install.

Manual Installation

To install this node manually (e.g., for development):

1. Go to your n8n root directory (e.g., ~/.n8n).
2. Clone this repository or copy the files into custom/n8n-nodes-ragflow.
3. Run npm install and npm run build inside the node directory.
4. Restart n8n.

Credentials

You need a RAGFlow API Key.

1. Log in to your RAGFlow console.
2. Go to User Profile / Settings -> API Keys.
3. Create a new key.
4. In n8n, add a new RAGFlow API credential and paste the key.
   • Base URL: The URL of your RAGFlow instance (e.g., http://localhost:9380 or https://demo.ragflow.io). Do not add /api/v1 to the end, the node handles it.

Compatibility

• Tested with RAGFlow v0.16.0+ (Docker version).
• Compatible with n8n v1.0+.

License

MIT