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:
+6
-2
@@ -15,8 +15,9 @@ path = "src/main.rs"
|
||||
name = "health_check"
|
||||
path = "src/bin/health_check.rs"
|
||||
|
||||
|
||||
|
||||
[[bin]]
|
||||
name = "astroresearch_cli"
|
||||
path = "src/bin/cli.rs"
|
||||
[dependencies]
|
||||
tokio = { version = "1", features = ["full"] }
|
||||
axum = { version = "0.7", features = ["macros", "multipart"] }
|
||||
@@ -47,6 +48,9 @@ uuid = { version = "1.23.2", features = ["v4"] }
|
||||
tracing-appender = "0.2.5"
|
||||
obscura-browser = { path = "libs/obscura/crates/obscura-browser", optional = true }
|
||||
obscura-net = { path = "libs/obscura/crates/obscura-net", optional = true }
|
||||
libsqlite3-sys = { version = "0.27.0", features = ["bundled"] }
|
||||
sqlite-vec = "0.1.9"
|
||||
clap = { version = "4", features = ["derive"] }
|
||||
|
||||
[features]
|
||||
default = []
|
||||
|
||||
Reference in New Issue
Block a user