mcpField
A
aliyun-qwen-rerank

aliyun-qwen-rerank

github.com/cinienceData & databases39657 installsUpdated 11w ago
Repository

About aliyun-qwen-rerank

A skill for preparing reranking requests for Alibaba Cloud Model Studio models. It is used after embedding or vector retrieval to reorder candidate results, including multilingual searches.

Key features

  1. 01Prepare reranking request payloads
  2. 02Choose from listed reranker models
  3. 03Reorder retrieved candidates
  4. 04Support multilingual reranking

Use cases

  1. 01Reorder vector-search results
  2. 02Rerank candidates across query and document languages

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/cinience/alicloud-skills --skill aliyun-qwen-rerank

After installing, type/aliyun-qwen-rerankin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

agents/
openai.yaml
references/
sources.md
scripts/
prepare_rerank_request.py

Details

From the project README

Category: provider

Model Studio Rerank

Validation

mkdir -p output/aliyun-qwen-rerank
python -m py_compile skills/ai/search/aliyun-qwen-rerank/scripts/prepare_rerank_request.py && echo "py_compile_ok" > output/aliyun-qwen-rerank/validate.txt

Pass criteria: command exits 0 and output/aliyun-qwen-rerank/validate.txt is generated.

Critical model names

Use one of these exact model strings:

  • gte-rerank-v2
  • gte-rerank
  • gte-multilingual-rerank
  • qwen3-reranker-8b
  • qwen3-reranker-4b
  • qwen3-reranker-0.6b

Quick start

python skills/ai/search/aliyun-qwen-rerank/scripts/prepare_rerank_request.py \
  --query "cloud vector database" \
  --output output/aliyun-qwen-rerank/request.json

Notes

  • Use after embedding/vector retrieval to reorder candidates.
  • Prefer multilingual rerankers when query/document languages differ.

References

  • references/sources.md

Comments

Markdown supported