AI 分析

核心用途是实现跨会话的语义搜索。适合需要对所有历史消息进行实时向量索引、本地存储，并向 Agent 暴露 rag_search 工具以检索历史记忆的用户。

包名

dsh-plugin-rag

版本

0.1.0

许可证

MIT

Configuration reference

Key	Default	Contract
`enabled`	`true`	Whether indexing and the `rag_search` tool are active.
`provider`	`soclaas-bge-m3`	`soclaas-bge-m3` · `openai-3-small` · `openai-3-large` · `ollama-nomic` · `custom`
`model`	`bge-m3`	Model string sent to the endpoint (overrides the preset's model).
`endpoint`	`https://soclaas-api.comp.nus.edu.sg/v1`	OpenAI-compatible embeddings base URL.
`apiKey`	`""`	API key; empty reads `apiKeyEnv`.
`apiKeyEnv`	`SOCLAAS_API_KEY`	Environment variable for the key.
`topK`	`5`	Default result count (1–50).
`dataDir`	`""`	Index directory; empty means `~/.dsh/rag`.
`includeToolResults`	`true`	Index tool results.
`includeReasoning`	`false`	Index reasoning blocks.
`maxChunkChars`	`4000`	Max characters per chunk (256–16000).