$npx -y skills add cinience/alicloud-skills --skill aliyun-qwen-rerankUse when reranking search candidates is needed with Alibaba Cloud Model Studio rerank models, including hybrid retrieval, top-k refinement, and multilingual relevance sorting.
| 1 | Category: provider |
| 2 | |
| 3 | # Model Studio Rerank |
| 4 | |
| 5 | ## Validation |
| 6 | |
| 7 | ```bash |
| 8 | mkdir -p output/aliyun-qwen-rerank |
| 9 | 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 |
| 10 | ``` |
| 11 | |
| 12 | Pass criteria: command exits 0 and `output/aliyun-qwen-rerank/validate.txt` is generated. |
| 13 | |
| 14 | ## Critical model names |
| 15 | |
| 16 | Use one of these exact model strings: |
| 17 | - `gte-rerank-v2` |
| 18 | - `gte-rerank` |
| 19 | - `gte-multilingual-rerank` |
| 20 | - `qwen3-reranker-8b` |
| 21 | - `qwen3-reranker-4b` |
| 22 | - `qwen3-reranker-0.6b` |
| 23 | |
| 24 | ## Quick start |
| 25 | |
| 26 | ```bash |
| 27 | python skills/ai/search/aliyun-qwen-rerank/scripts/prepare_rerank_request.py \ |
| 28 | --query "cloud vector database" \ |
| 29 | --output output/aliyun-qwen-rerank/request.json |
| 30 | ``` |
| 31 | |
| 32 | ## Notes |
| 33 | |
| 34 | - Use after embedding/vector retrieval to reorder candidates. |
| 35 | - Prefer multilingual rerankers when query/document languages differ. |
| 36 | |
| 37 | ## References |
| 38 | |
| 39 | - `references/sources.md` |