mcpField
A
alicloud-ai-search-rerank

alicloud-ai-search-rerank

github.com/cinienceData & databases39692 installsUpdated 11w ago
Repository

About alicloud-ai-search-rerank

A provider skill for preparing reranking requests with Alibaba Model Studio models. It is intended for search pipelines that reorder candidates after embedding or vector retrieval.

Key features

  1. 01Prepares reranking request payloads
  2. 02Supports six specified reranker models
  3. 03Handles multilingual reranking scenarios

Use cases

  1. 01Reordering candidates after vector retrieval
  2. 02Ranking documents across languages

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/cinience/alicloud-skills --skill alicloud-ai-search-rerank

After installing, type/alicloud-ai-search-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/alicloud-ai-search-rerank
python -m py_compile skills/ai/search/alicloud-ai-search-rerank/scripts/prepare_rerank_request.py && echo "py_compile_ok" > output/alicloud-ai-search-rerank/validate.txt

Pass criteria: command exits 0 and output/alicloud-ai-search-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/alicloud-ai-search-rerank/scripts/prepare_rerank_request.py \
  --query "cloud vector database" \
  --output output/alicloud-ai-search-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