RankGPT Dify Plugin

LLM-based RankGPT reranker plugin for Dify, supporting OpenAI, Google Gemini, and Anthropic.

Author: ki3nd
Type: model
Github Repo: https://github.com/ki3nd/rankgpt-dify-plugin
Github Issues: issues

Overview

This plugin adds a to Dify and uses an LLM to reorder retrieved documents by query relevance.

Features

• Supports OpenAI, Google Gemini, and Anthropic providers
• RankGPT-style permutation reranking
• Sliding-window reranking for longer document lists
• Rank-based pseudo-score output ()

Configure In Dify

When configuring the provider in Dify:

How Reranking Works

1. The plugin builds a RankGPT-style prompt with the query and indexed passages.
2. The LLM returns a ranking order (e.g. ).
3. The plugin parses the order, removes duplicates and invalid indices, and applies a safe fallback for missing ones.
4. Results are returned to Dify as .

Notes

• LLM-based reranking — latency and cost depend on model choice and document count.
• For large document sets, tune and to avoid oversized prompts.
• applies to a rank-based pseudo-score, not a true relevance probability.