forked from admin/PlantAI-rag-new
jerryandClaude Fable 5
5024a12947
- 加密工具双模式往返验证通过(字段级 properties_json / 整文件 parquet) - 取消真实加密执行:数据库未定版,中间副本已清理,kb.key 保留 - tooling/KB_ENCRYPT_GUIDE.md:完整操作步骤/踩坑记录/解密验证/流水线接入 - 踩坑固化:Qdrant 必须 snapshot API(禁 rsync 活动卷);Neo4j 5.15 community 不支持在线 dump,走 frozen 目录冷拷;canonical 库不在 KB 交付内 Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
37 lines
1.7 KiB
YAML
37 lines
1.7 KiB
YAML
# knowledge/manifest.yaml —— 向量知识库打包定义(数据不入 git,仅元信息)
|
|
# 2026-08-31 P5 核实版:真实数据源与加密语义
|
|
version: 2.0.0
|
|
sources:
|
|
qdrant:
|
|
collection: plant_srt_pc2025_v3_20260817_normalized
|
|
upstream_port: 27333
|
|
container: qdrant-plant-srt-pc2025-v3-20260817-normalized
|
|
size_gb: 70
|
|
export: snapshot API + docker cp
|
|
neo4j:
|
|
# KB 交付 = normalized 库(断言检索主库,QA 唯一依赖);canonical 18788 属 SDK KG 浏览,不打包
|
|
normalized_container: neo4j-plant-srt-pc2025-v3-20260817-normalized
|
|
normalized_bolt: bolt://127.0.0.1:19788
|
|
normalized_size_gb: 8.2
|
|
note: 5.15 community 不支持在线 dump;frozen 数据目录(08-24 起无写入)可冷拷
|
|
assertions:
|
|
raw_export: staging/frozen_inputs/.../baseline_assertions/raw_export.jsonl(9.5G)
|
|
parquet: staging/frozen_inputs/.../baseline_assertions/assertions.parquet(2.7G)
|
|
registry: 主项目 data/knowledge_base/paper_metadata_registry_v1_20260717(17M,仅论文元数据,无断言文本)
|
|
encryption:
|
|
schedule: 数据库定版后执行(定版前数据持续增长,不做真实加密;工具已验证,见 tooling/KB_ENCRYPT_GUIDE.md)
|
|
vectors: plaintext # 检索数学需要
|
|
assertion_export_jsonl: AES-256-GCM # raw_export.jsonl properties_json 字段
|
|
assertion_export_parquet: AES-256-GCM # 整文件加密
|
|
graph_dump: plaintext-in-tar # 存储引擎限制
|
|
qdrant_snapshot: plaintext # 存储引擎限制(断言文本经导出文件已加密)
|
|
expected_counts:
|
|
papers: 31207
|
|
canonical_entities: 3820996
|
|
assertions: 8246875
|
|
normalized_entities: 6316654
|
|
qdrant_points: 12963472
|
|
neo4j_asserts: 12963472
|
|
neo4j_supported_by: 13012368
|
|
neo4j_papers: 96648
|