RAGFlow

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding. It combines cutting-edge RAG technology with agent capabilities to create an excellent contextual layer for lifecycle management (LLM). It provides streamlined RAG workflows that can adapt to enterprises of all sizes. Powered by a unified context engine and prebuilt agent templates, RAGFlow enables developers to transform complex data into high-fidelity, production-ready AI systems with exceptional efficiency and precision. To help everyone make better use of RAGFlow, we have prepared a detailed tutorial. From environment configuration to connecting to 『Interface AI』, this guide will teach you how to get started with RAGFlow in 3 minutes!

​

1. Configure prerequisites

​

(1) Register and obtain an API key

Register and log in to JieKou.AI. Enter the invitation code【YGHNZ0】during registration to receive a $2 signup reward. Open the【API key】management page, click the add button, enter a custom key name, and generate an API key.

​

(2) Generate and save the API key

!Note: The key is encrypted and stored on the server. After creation, it cannot be viewed again. Please keep the key safe. If it is lost, you need to delete it in the console and create a new key.

​

(3) Obtain the model ID you need to use

Find the model you want to use in the JieKou.AI Model Marketplace, then copy the modelid and base URL.

• Gemini-3-pro-preview
• Gemini-2.5-pro
• Claude-sonnet-4-5
• Gpt-5.1
• Gpt-4o

For other model IDs, maximum context lengths, and pricing, refer to: Model Marketplace

​

2. Add and configure an LLM in RAGFlow

​

(1) Visit the RAGFlow official website

​

(2) Add a model

Select【Model Provider】, find【OpenAI-API-Compatible】, and click【Add Model】

​

(3) Select and fill in the corresponding configuration.

​

(4) Added successfully.

For more configuration details about RAGFlow, you can refer to the RAGFlow documentation.