Files
RAG/docs/README.md
YoVinchen 75592af33a
Some checks failed
verify / verify (push) Has been cancelled
Isolate cloud model access before enabling product RAG workflows
The API and ingestion tools now use a fixed internal model gateway while
governed profiles, embedding cache assignments, traceable citations, and
stable API errors establish the boundaries required by later workflows.

Constraint: The current Alibaba Cloud workspace rejects all three live model calls with authentication failures
Rejected: Give the API or seed tools the Bailian key and direct egress | combines database access, cloud credentials, and public network access
Rejected: Mix offline and Bailian vectors in one demo namespace | makes profile activation and retrieval ambiguous
Confidence: high
Scope-risk: moderate
Reversibility: clean
Directive: Keep Bailian credentials and egress exclusive to model-gateway and create a new immutable profile hash for any embedding identity change
Tested: make verify; 121 backend tests; 14 frontend tests; fresh and populated Alembic upgrade-downgrade-upgrade; two idempotent offline seeds; Docker health and HTTP retrieval; isolated provider smoke
Not-tested: Successful live Bailian responses because the supplied workspace credential currently fails authentication
2026-07-13 04:09:06 +08:00

2.5 KiB
Raw Blame History

设计文档索引

当前进度

  • Stage 0“仓库、安全和设计基线”已完成并推送。
  • Stage 1“模型与数据库 PoC”正在进行。
  • 当前整体里程碑仍约 12%,合理区间为 10%15%;新增代码不在阶段验收前提前计入完成度。
  • 0003 的设计基线已完成后端离线链路、20 条 synthetic 数据、React 离线演示和 Nginx 单入口已验收。
  • 五层网络与独立 model-gateway 已实现:只有该服务持百炼 Key/egressAPI、seed、smoke 使用区分 API/Worker 身份的内部 token。
  • FastAPI 应用工厂、稳定 Problem/trace 契约,以及 0002_model_profiles 的 profile/cache/assignment/invocation/citation 迁移代码已落地。
  • 真实 text-embedding-v4qwen3-rerankdeepseek-v4-flash 当前仍全部返回 401真实百炼能力尚未验收。
  • Stage 2 仍为 TODOWorker 租约/fencing/reaper、上传入库、正式检索、grounded chat、评测和完整产品 UI 尚未完成。
  • 后续状态、依赖、验收证据、工期和提交节点以 项目全生命周期 TODO 为准。

文档列表

文档 内容 状态
00-overall-design.md 项目范围、总体架构、技术选型、接口、数据模型与 RAG 主流程 设计基线完成
01-data-and-evaluation.md 语料治理、解析、验证集生成、向量入库测试和论文评测 设计基线完成
02-deployment-and-security.md Docker Compose、配置、密钥、监控、备份和安全 设计基线完成
03-implementation-plan.md 阶段计划、完成定义、测试与验收清单 设计基线完成
04-project-todo.md 从当前状态到最终答辩、发布和归档的任务看板 Stage 1 进行中
05-stage1-runbook.md Secret 初始化、离线数据库/seed、真实三模型 smoke 和排障命令 Stage 1 运行手册
06-frontend-demo-runbook.md React/Nginx 离线检索演示、同源 API、开发与验收命令 离线前端运行手册
adr/ 不易逆转的架构决策记录 持续维护

文档中的工作空间地址统一使用 <workspace-id> 占位符;真实地址和凭证均属于部署配置,不写入仓库。

建议首次阅读按 00 → 01 → 02 → 03 → 04 的顺序;日常执行查看 04数据库/模型 PoC 查看 05React 演示查看 06。