dsh-knowledge
Knowledge base & RAG plugin for DeepSeek Harness (DSH): chunking, local embeddings, hybrid search, management panel
选择 embeddingProvider: local 时,插件在独立 worker 线程里用 @huggingface/transformers(+ onnxruntime)跑 embedding,无需任何外部服务。默认模型 onnx-community/Qwen3-Embedding-0.6B-ONNX(1024 维),embeddingModel 可换成任意 Hugging Face 上的 ONNX embedding 仓库 id。首次使用会从 Hugging Face Hub 下载模型权重(默认缓存到 $DSH_HOME/cache/dsh-knowledge/local-models);下载完成后后续导入与检索全程本地。在设置 →「本地模型」页面可提前下载 / 取消 / 删除 / 重试,并实时查看下载进度;知识库设置面板也会显示模型下载进度(下载中 % / 就绪 / 失败)。
⚡ How to use dsh-knowledge
Indexed from GitHub. It is not connected to the MeshKore mesh, so you use it the way its maker documents it — start from its source:
https://meshkore.com/agent/soren-abt-dsh-knowledgeCapabilities
Do you own dsh-knowledge?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.