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
+132
@@ -71,6 +71,56 @@ dependencies = [
|
||||
"libc",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "anstream"
|
||||
version = "1.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "824a212faf96e9acacdbd09febd34438f8f711fb84e09a8916013cd7815ca28d"
|
||||
dependencies = [
|
||||
"anstyle",
|
||||
"anstyle-parse",
|
||||
"anstyle-query",
|
||||
"anstyle-wincon",
|
||||
"colorchoice",
|
||||
"is_terminal_polyfill",
|
||||
"utf8parse",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "anstyle"
|
||||
version = "1.0.14"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "940b3a0ca603d1eade50a4846a2afffd5ef57a9feac2c0e2ec2e14f9ead76000"
|
||||
|
||||
[[package]]
|
||||
name = "anstyle-parse"
|
||||
version = "1.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "52ce7f38b242319f7cabaa6813055467063ecdc9d355bbb4ce0c68908cd8130e"
|
||||
dependencies = [
|
||||
"utf8parse",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "anstyle-query"
|
||||
version = "1.1.5"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "40c48f72fd53cd289104fc64099abca73db4166ad86ea0b4341abe65af83dadc"
|
||||
dependencies = [
|
||||
"windows-sys 0.61.2",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "anstyle-wincon"
|
||||
version = "3.0.11"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "291e6a250ff86cd4a820112fb8898808a366d8f9f58ce16d1f538353ad55747d"
|
||||
dependencies = [
|
||||
"anstyle",
|
||||
"once_cell_polyfill",
|
||||
"windows-sys 0.61.2",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "anyhow"
|
||||
version = "1.0.102"
|
||||
@@ -85,11 +135,13 @@ dependencies = [
|
||||
"axum",
|
||||
"base64 0.22.1",
|
||||
"chrono",
|
||||
"clap",
|
||||
"dotenvy",
|
||||
"flate2",
|
||||
"futures-util",
|
||||
"hmac 0.12.1",
|
||||
"html2md",
|
||||
"libsqlite3-sys",
|
||||
"obscura-browser",
|
||||
"obscura-net",
|
||||
"quick-xml",
|
||||
@@ -99,6 +151,7 @@ dependencies = [
|
||||
"serde",
|
||||
"serde_json",
|
||||
"sha1 0.10.6",
|
||||
"sqlite-vec",
|
||||
"sqlx",
|
||||
"thiserror 1.0.69",
|
||||
"tokio",
|
||||
@@ -527,6 +580,46 @@ dependencies = [
|
||||
"libloading",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "clap"
|
||||
version = "4.6.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "1ddb117e43bbf7dacf0a4190fef4d345b9bad68dfc649cb349e7d17d28428e51"
|
||||
dependencies = [
|
||||
"clap_builder",
|
||||
"clap_derive",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "clap_builder"
|
||||
version = "4.6.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "714a53001bf66416adb0e2ef5ac857140e7dc3a0c48fb28b2f10762fc4b5069f"
|
||||
dependencies = [
|
||||
"anstream",
|
||||
"anstyle",
|
||||
"clap_lex",
|
||||
"strsim",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "clap_derive"
|
||||
version = "4.6.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "f2ce8604710f6733aa641a2b3731eaa1e8b3d9973d5e3565da11800813f997a9"
|
||||
dependencies = [
|
||||
"heck 0.5.0",
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
"syn 2.0.117",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "clap_lex"
|
||||
version = "1.1.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "c8d4a3bb8b1e0c1050499d1815f5ab16d04f0959b233085fb31653fbfc9d98f9"
|
||||
|
||||
[[package]]
|
||||
name = "cmake"
|
||||
version = "0.1.58"
|
||||
@@ -542,6 +635,12 @@ version = "0.5.4"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "0c9ea0ac24bc397ab3c98583a3c9ba74fa56b09a4449bbe172b9b1ddb016027a"
|
||||
|
||||
[[package]]
|
||||
name = "colorchoice"
|
||||
version = "1.0.5"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "1d07550c9036bf2ae0c684c4297d503f838287c83c53686d05370d0e139ae570"
|
||||
|
||||
[[package]]
|
||||
name = "combine"
|
||||
version = "4.6.7"
|
||||
@@ -1768,6 +1867,12 @@ version = "2.12.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "d98f6fed1fde3f8c21bc40a1abb88dd75e67924f9cffc3ef95607bad8017f8e2"
|
||||
|
||||
[[package]]
|
||||
name = "is_terminal_polyfill"
|
||||
version = "1.70.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "a6cb138bb79a146c1bd460005623e142ef0181e3d0219cb493e02f7d08a35695"
|
||||
|
||||
[[package]]
|
||||
name = "itertools"
|
||||
version = "0.13.0"
|
||||
@@ -2289,6 +2394,12 @@ version = "1.21.4"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "9f7c3e4beb33f85d45ae3e3a1792185706c8e16d043238c593331cc7cd313b50"
|
||||
|
||||
[[package]]
|
||||
name = "once_cell_polyfill"
|
||||
version = "1.70.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "384b8ab6d37215f3c5301a95a4accb5d64aa607f1fcb26a11b5303878451b4fe"
|
||||
|
||||
[[package]]
|
||||
name = "openssl-macros"
|
||||
version = "0.1.1"
|
||||
@@ -3256,6 +3367,15 @@ dependencies = [
|
||||
"unicode_categories",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "sqlite-vec"
|
||||
version = "0.1.9"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "d0ba424237a9a5db2f6071f193319e2b6a32f7f3961debb2fbbfe67067abce3f"
|
||||
dependencies = [
|
||||
"cc",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "sqlx"
|
||||
version = "0.7.4"
|
||||
@@ -3511,6 +3631,12 @@ dependencies = [
|
||||
"unicode-properties",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "strsim"
|
||||
version = "0.11.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "7da8b5736845d9f2fcb837ea5d9e2628564b3b043a70948a3f0b778838c5fb4f"
|
||||
|
||||
[[package]]
|
||||
name = "strum"
|
||||
version = "0.27.2"
|
||||
@@ -4122,6 +4248,12 @@ version = "1.0.4"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "b6c140620e7ffbb22c2dee59cafe6084a59b5ffc27a8859a5f0d494b5d52b6be"
|
||||
|
||||
[[package]]
|
||||
name = "utf8parse"
|
||||
version = "0.2.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "06abde3611657adf66d383f00b093d7faecc7fa57071cce2578660c9f1010821"
|
||||
|
||||
[[package]]
|
||||
name = "uuid"
|
||||
version = "1.23.2"
|
||||
|
||||
Reference in New Issue
Block a user