概览
dsh-semantic-search
源码级技术说明A DeepSeek Harness (dsh) plugin for local semantic code search. Builds a fragment-level index of a workspace (symbol-aware chunking for many languages), computes local embeddings (lightweight lexical TF-IDF feature vectors by default, or a configurable OpenAI-compatible embedding endpoint), and answers natural-language queries with hybrid retrieval (vector cosine + BM25, fused with reciprocal-rank fusion). Ships dsh tools sema_search / sema_reindex / sema_stats plus a stand-alone CLI.收起技术说明
A DeepSeek Harness (dsh) plugin for local semantic code search. Builds a fragment-level index of a workspace (symbol-aware chunking for many languages), computes local embeddings (lightweight lexical TF-IDF feature vectors by default, or a configurable OpenAI-compatible embedding endpoint), and answers natural-language queries with hybrid retrieval (vector cosine + BM25, fused with reciprocal-rank fusion). Ships dsh tools sema_search / sema_reindex / sema_stats plus a stand-alone CLI.
README / ZH
插件文档
目录摘要
A DeepSeek Harness (dsh) plugin for local semantic code search. Builds a fragment-level index of a workspace (symbol-aware chunking for many languages), computes local embeddings (lightweight lexical TF-IDF feature vectors by default, or a configurable OpenAI-compatible embedding endpoint), and answers natural-language queries with hybrid retrieval (vector cosine + BM25, fused with reciprocal-rank fusion). Ships dsh tools sema_search / sema_reindex / sema_stats plus a stand-alone CLI.
dsh.pub 核对固定版本的组合包契约、运行时事实与分发语义；完整 README 请查看源仓库。
在 GitHub 阅读完整 README