Make deployment truth and remaining graduation gates explicit
Some checks failed
verify / verify (push) Has been cancelled

Document the runnable Docker workflow, expected one-shot container exits, server-controlled Bailian namespace switch, current earned progress, and the security and evaluation work that still blocks private-data or graduation release claims.

Constraint: Current local Bailian credentials are rejected by the configured workspace

Rejected: Mark the project complete from synthetic metrics | would overstate provider, OCR, authorization, and blind-evaluation readiness

Confidence: high

Scope-risk: narrow

Directive: Keep progress evidence task-based and distinguish synthetic engineering validation from real geological efficacy

Tested: make verify-design; Markdown links; secret scan; diff checks

Not-tested: Final thesis review and live provider authorization
This commit is contained in:
2026-07-13 05:58:39 +08:00
parent ecdb10c37a
commit 63279cf213
7 changed files with 214 additions and 109 deletions

View File

@@ -2,7 +2,7 @@
本仓库用于“基于 RAG 的地质找矿知识问答系统构建与应用”毕业设计。系统计划采用 Python/FastAPI 后端、React/TypeScript 前端、PostgreSQL + pgvector 向量存储,以及阿里云百炼的 `text-embedding-v4``qwen3-rerank``deepseek-v4-flash`
当前处于 Stage 1“模型与数据库 PoC”设计基线、离线 pgvector/适配器/seed、FastAPI 和 React/Nginx 可视化检索演示均可运行;真实百炼 smoke 仍待轮换后的新 Key正式知识库、文档入库和生成问答尚未实现。完整方案、状态和评测方法见 [docs/README.md](docs/README.md),仓库不会把离线演示伪装成已经完成的产品
核心 synthetic 产品链现已在 Docker 中多次端到端通过文档上传、本地解析、manifest 人工审核、向量写库、原子激活、正式检索和带引用问答均可运行React 已提供 `/documents``/retrieval``/chat` 页面。固定 fixture 的两次入库使用相同身份version/chunk/assignment/jobs/invocations 计数稳定为 `1/1/1/2/1`;最新 fresh + replay smoke 还证明当前 Worker 执行与幂等重放均有效。当前质量门禁记录为 296 项后端测试、53 项前端测试。真实百炼的 `text-embedding-v4``qwen3-rerank``deepseek-v4-flash` 仍全部返回 401PDF/OCR、正式认证与多租户、300 题盲测、备份恢复/压测、论文和答辩仍未完成,因此本仓库不会把 synthetic 闭环描述为毕业验收完成
## 目录
@@ -45,6 +45,9 @@
- [全生命周期 TODO 与进度](docs/04-project-todo.md)
- [Stage 1 PoC 运行手册](docs/05-stage1-runbook.md)
- [React 离线检索演示运行手册](docs/06-frontend-demo-runbook.md)
- [正式检索、Worker 与评测运行手册](docs/07-retrieval-worker-evaluation-runbook.md)
- [Grounded Chat 运行与引用验证手册](docs/08-grounded-chat-runbook.md)
- [文档上传、审核、向量化与检索运行手册](docs/09-document-ingestion-indexing-runbook.md)
- [架构决策记录](docs/adr/README.md)
## 当前可运行入口
@@ -52,11 +55,11 @@
```bash
make setup-hooks
bash scripts/init-local-secrets.sh
docker compose up -d --build web
docker compose --profile tools run --rm seed-demo-offline
make up
make seed-offline
make smoke-document
curl http://127.0.0.1:8000/health/ready
curl http://127.0.0.1:8000/api/v1/demo/status
make verify
```
这组命令不需要百炼 Key只使用 20 条虚构数据验证 pgvector 写入检索重排、引用编号和同源 Web 交互。`web` 会依次启动数据库、迁移、内部 API 和 gateway启动后访问 <http://127.0.0.1:8000/> 使用 React 演示,或访问 <http://127.0.0.1:8000/docs> 查看 FastAPI Swagger。真实模型运行必须先轮换聊天中已暴露的旧 Key再按 [Stage 1 运行手册](docs/05-stage1-runbook.md) 操作。
这组命令不需要有效百炼 Key只使用公开虚构数据验证上传、解析、审批、向量化、pgvector 写入和正式检索/重排Chat 引用与同源 Web 交互由测试套件及对应页面单独验证。`migrate``upload-init` 是成功后正常显示 `Exited (0)` 的一次性任务,不是服务暂停。启动后访问 <http://127.0.0.1:8000/documents> 完成文档入库与审核,访问 <http://127.0.0.1:8000/retrieval> 查看正式检索页,访问 <http://127.0.0.1:8000/chat> 查看 Grounded Chat或访问 <http://127.0.0.1:8000/docs> 查看 Swagger。详细操作见 [文档入库运行手册](docs/09-document-ingestion-indexing-runbook.md)。真实模型运行必须先轮换聊天中已暴露的旧 Key再按 [Stage 1 运行手册](docs/05-stage1-runbook.md) 操作;真实 Key 永远不得提交到 Git