feat: RAG 文献问答、天体目标识别、解析器模块化与批量管线扩展
核心新增：
- RAG 问答系统：Markdown 安全切片器 (LaTeX 保护) + 向量化 + sqlite-vec 检索 + LLM 生成
- 天体目标识别：IAU 标准正则提取 15+ 星表标识符，CDS SIMBAD/Sesame 查询与本地缓存
- 多模态 LLM：chat_completion_with_image 支持图表视觉分析
- CLI Skills Agent (cli.rs)：对外暴露 rag/target/ingest 等 5 个子命令
- 解析器模块化重构：单体 778 行 → 按期刊拆分 (A&A/ar5iv/IOP/Generic/PDF) +
common.rs 静态正则工具库
管线与 Schema：
- AssetSync→AssetBatch 重命名，批量管线新增 embed/target 两个处理阶段
- 新增 paper_chunks_content (RAG 切片) 和 paper_targets (天体缓存) 两张表
- StandardPaper 新增 has_vector 字段，所有查询同步更新
前端：
- 新增 AI 助手侧边栏 (RAG 问答 + 来源跳转高亮)
- 最近浏览文献列表 (localStorage 持久化)、跨面板无缝导航
- SyncPanel 批量阶段扩展为下拉选项，支持向量化/天体识别
测试与清理：
- 集成测试合并至 ads.rs 和 llm.rs，新增 chunker + target 单元测试 15 个
- 删除旧单体 parser.rs、独立测试文件及过期 scratch 脚本
This commit is contained in:
Generated
+94
@@ -17,6 +17,8 @@
|
||||
"react-dom": "^19.2.6",
|
||||
"react-markdown": "^10.1.0",
|
||||
"rehype-katex": "^7.0.1",
|
||||
"rehype-raw": "^7.0.0",
|
||||
"rehype-sanitize": "^6.0.0",
|
||||
"remark-gfm": "^4.0.1",
|
||||
"remark-math": "^6.0.0",
|
||||
"tailwind-merge": "^3.6.0"
|
||||
@@ -2449,6 +2451,44 @@
|
||||
"url": "https://opencollective.com/unified"
|
||||
}
|
||||
},
|
||||
"node_modules/hast-util-raw": {
|
||||
"version": "9.1.0",
|
||||
"resolved": "https://registry.npmjs.org/hast-util-raw/-/hast-util-raw-9.1.0.tgz",
|
||||
"integrity": "sha512-Y8/SBAHkZGoNkpzqqfCldijcuUKh7/su31kEBp67cFY09Wy0mTRgtsLYsiIxMJxlu0f6AA5SUTbDR8K0rxnbUw==",
|
||||
"dependencies": {
|
||||
"@types/hast": "^3.0.0",
|
||||
"@types/unist": "^3.0.0",
|
||||
"@ungap/structured-clone": "^1.0.0",
|
||||
"hast-util-from-parse5": "^8.0.0",
|
||||
"hast-util-to-parse5": "^8.0.0",
|
||||
"html-void-elements": "^3.0.0",
|
||||
"mdast-util-to-hast": "^13.0.0",
|
||||
"parse5": "^7.0.0",
|
||||
"unist-util-position": "^5.0.0",
|
||||
"unist-util-visit": "^5.0.0",
|
||||
"vfile": "^6.0.0",
|
||||
"web-namespaces": "^2.0.0",
|
||||
"zwitch": "^2.0.0"
|
||||
},
|
||||
"funding": {
|
||||
"type": "opencollective",
|
||||
"url": "https://opencollective.com/unified"
|
||||
}
|
||||
},
|
||||
"node_modules/hast-util-sanitize": {
|
||||
"version": "5.0.2",
|
||||
"resolved": "https://registry.npmjs.org/hast-util-sanitize/-/hast-util-sanitize-5.0.2.tgz",
|
||||
"integrity": "sha512-3yTWghByc50aGS7JlGhk61SPenfE/p1oaFeNwkOOyrscaOkMGrcW9+Cy/QAIOBpZxP1yqDIzFMR0+Np0i0+usg==",
|
||||
"dependencies": {
|
||||
"@types/hast": "^3.0.0",
|
||||
"@ungap/structured-clone": "^1.0.0",
|
||||
"unist-util-position": "^5.0.0"
|
||||
},
|
||||
"funding": {
|
||||
"type": "opencollective",
|
||||
"url": "https://opencollective.com/unified"
|
||||
}
|
||||
},
|
||||
"node_modules/hast-util-to-jsx-runtime": {
|
||||
"version": "2.3.6",
|
||||
"resolved": "https://registry.npmjs.org/hast-util-to-jsx-runtime/-/hast-util-to-jsx-runtime-2.3.6.tgz",
|
||||
@@ -2475,6 +2515,24 @@
|
||||
"url": "https://opencollective.com/unified"
|
||||
}
|
||||
},
|
||||
"node_modules/hast-util-to-parse5": {
|
||||
"version": "8.0.1",
|
||||
"resolved": "https://registry.npmjs.org/hast-util-to-parse5/-/hast-util-to-parse5-8.0.1.tgz",
|
||||
"integrity": "sha512-MlWT6Pjt4CG9lFCjiz4BH7l9wmrMkfkJYCxFwKQic8+RTZgWPuWxwAfjJElsXkex7DJjfSJsQIt931ilUgmwdA==",
|
||||
"dependencies": {
|
||||
"@types/hast": "^3.0.0",
|
||||
"comma-separated-tokens": "^2.0.0",
|
||||
"devlop": "^1.0.0",
|
||||
"property-information": "^7.0.0",
|
||||
"space-separated-tokens": "^2.0.0",
|
||||
"web-namespaces": "^2.0.0",
|
||||
"zwitch": "^2.0.0"
|
||||
},
|
||||
"funding": {
|
||||
"type": "opencollective",
|
||||
"url": "https://opencollective.com/unified"
|
||||
}
|
||||
},
|
||||
"node_modules/hast-util-to-text": {
|
||||
"version": "4.0.2",
|
||||
"resolved": "https://registry.npmjs.org/hast-util-to-text/-/hast-util-to-text-4.0.2.tgz",
|
||||
@@ -2542,6 +2600,15 @@
|
||||
"url": "https://opencollective.com/unified"
|
||||
}
|
||||
},
|
||||
"node_modules/html-void-elements": {
|
||||
"version": "3.0.0",
|
||||
"resolved": "https://registry.npmjs.org/html-void-elements/-/html-void-elements-3.0.0.tgz",
|
||||
"integrity": "sha512-bEqo66MRXsUGxWHV5IP0PUiAWwoEjba4VCzg0LjFJBpchPaTfyfCKTG6bc5F8ucKec3q5y6qOdGyYTSBEvhCrg==",
|
||||
"funding": {
|
||||
"type": "github",
|
||||
"url": "https://github.com/sponsors/wooorm"
|
||||
}
|
||||
},
|
||||
"node_modules/https-proxy-agent": {
|
||||
"version": "5.0.1",
|
||||
"resolved": "https://registry.npmjs.org/https-proxy-agent/-/https-proxy-agent-5.0.1.tgz",
|
||||
@@ -4273,6 +4340,33 @@
|
||||
"katex": "cli.js"
|
||||
}
|
||||
},
|
||||
"node_modules/rehype-raw": {
|
||||
"version": "7.0.0",
|
||||
"resolved": "https://registry.npmjs.org/rehype-raw/-/rehype-raw-7.0.0.tgz",
|
||||
"integrity": "sha512-/aE8hCfKlQeA8LmyeyQvQF3eBiLRGNlfBJEvWH7ivp9sBqs7TNqBL5X3v157rM4IFETqDnIOO+z5M/biZbo9Ww==",
|
||||
"dependencies": {
|
||||
"@types/hast": "^3.0.0",
|
||||
"hast-util-raw": "^9.0.0",
|
||||
"vfile": "^6.0.0"
|
||||
},
|
||||
"funding": {
|
||||
"type": "opencollective",
|
||||
"url": "https://opencollective.com/unified"
|
||||
}
|
||||
},
|
||||
"node_modules/rehype-sanitize": {
|
||||
"version": "6.0.0",
|
||||
"resolved": "https://registry.npmjs.org/rehype-sanitize/-/rehype-sanitize-6.0.0.tgz",
|
||||
"integrity": "sha512-CsnhKNsyI8Tub6L4sm5ZFsme4puGfc6pYylvXo1AeqaGbjOYyzNv3qZPwvs0oMJ39eryyeOdmxwUIo94IpEhqg==",
|
||||
"dependencies": {
|
||||
"@types/hast": "^3.0.0",
|
||||
"hast-util-sanitize": "^5.0.0"
|
||||
},
|
||||
"funding": {
|
||||
"type": "opencollective",
|
||||
"url": "https://opencollective.com/unified"
|
||||
}
|
||||
},
|
||||
"node_modules/remark-gfm": {
|
||||
"version": "4.0.1",
|
||||
"resolved": "https://registry.npmjs.org/remark-gfm/-/remark-gfm-4.0.1.tgz",
|
||||
|
||||
Reference in New Issue
Block a user