简体中文
# MCP Server servers: retriever: servers/retriever # MCP Client Pipeline pipeline: - retriever.retriever_init - retriever.retriever_deploy_service
ultrarag build examples/deploy_retriever.yaml
retriever: corpus_path: data/sample_hotpotqa_corpus_5.jsonl cuda_devices: 0,1 faiss_use_gpu: true index_path: index/index.index infinity_kwargs: batch_size: 1024 bettertransformer: false device: cuda pooling_method: auto retriever_path: openbmb/MiniCPM-Embedding-Light retriever_url: http://localhost:8080
retriever_url
http://<host>:<port>
127.0.0.1:5112
0.0.0.0:<port>
后台方式
# 使用 screen 启动并挂起服务 screen -S retriever ultrarag run examples/deploy_retriever.yaml # 按 Ctrl + A + D 挂起 # 后续恢复:screen -r retriever
nohup ultrarag run examples/deploy_retriever.yaml > retriever.log 2>&1 &
retriever.retriever_deploy_search
servers: retriever: servers/retriever benchmark: servers/benchmark # MCP Client Pipeline pipeline: - benchmark.get_data - retriever.retriever_deploy_search
此页面对您有帮助吗?