wangweiandCopilot 4f6cc4812e revert: disable Cross-Encoder reranker ...

Live verification via POST /status/models/ping (after confirming the
gateway itself is reachable -- embedding role succeeded, 1.5s latency)
shows http://6.86.80.4:30080/v1/rerank returns a fast, reproducible
'503 Service Unavailable' -- not a timeout/fluke. The gateway's model
catalog (19 models: deepseek-*, glm-*, kimi-*, qwen3*, text-embedding-v3/4)
contains no cross-encoder/rerank-capable model, confirming no reranker
service is deployed behind this gateway today. Leaving RERANKER_ENABLED=true
would be a permanent no-op (graceful fallback to unranked order every call)
plus a misleading permanent error badge on the Status page. Revert until a
reranker model is actually deployed on the gateway.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

2026-07-23 14:09:33 +08:00

.superpowers/brainstorm

update for 1. 优化 2.中英切换

2026-06-10 11:10:36 +08:00

aliyun_parser

@

2026-06-03 16:58:35 +08:00

backend

feat: record streaming token usage in TrackedLLMClient.stream_chat

2026-07-23 13:42:33 +08:00

docker

update for 1. 优化 2.中英切换

2026-06-10 11:10:36 +08:00

docs

docs: add implementation plan for System Status AI model usage tracking

2026-07-02 14:13:58 +08:00

frontend

Add LLM token

2026-07-02 22:03:39 +08:00

Prototype

@

2026-06-03 16:58:35 +08:00

scripts

1. Add 登陆功能

2026-06-05 18:00:31 +08:00

tests

fix: normalize LLM provider key lookup and skip disabled HyDE ping (final review)

2026-07-02 21:24:22 +08:00

.env

revert: disable Cross-Encoder reranker

2026-07-23 14:09:33 +08:00

.env.development

update for 1. 优化 2.中英切换

2026-06-10 11:10:36 +08:00

.env.example

Add LLM token

2026-07-02 22:03:39 +08:00

.gitignore

Add LLM token

2026-07-02 22:03:39 +08:00

01_Architecture.html

@

2026-06-03 16:58:35 +08:00

02_Architecture_Detail.html

@

2026-06-03 16:58:35 +08:00

AGENTS.md

feat: implement new layout components and routing structure

2026-05-25 16:19:18 +08:00

AI_Regulations_Architecture.docx

@

2026-06-03 16:58:35 +08:00

AI_Regulations_Report.pptx

@

2026-06-03 16:58:35 +08:00

Bosch_Workshop_2026_March_AI.pdf

@

2026-06-03 16:58:35 +08:00

dev.bat

Fix SSE route dependency and align architecture docs

2026-05-18 16:32:42 +08:00

dev.sh

1. Add 登陆功能

2026-06-05 18:00:31 +08:00

docs_dump.txt

1. Add 登陆功能

2026-06-05 18:00:31 +08:00

download_model.sh

first commit

2026-04-28 11:29:33 +08:00

pip.conf

first commit

2026-04-28 11:29:33 +08:00

pyproject.toml

update for 1. 优化 2.中英切换

2026-06-10 11:10:36 +08:00

QUICK_DEPLOY.md

Add LLM token

2026-07-02 22:03:39 +08:00

requirements.txt

update for 1. 优化 2.中英切换

2026-06-10 11:10:36 +08:00

skills-lock.json

feat: implement new layout components and routing structure

2026-05-25 16:19:18 +08:00

test_api.sh

first commit

2026-04-28 11:29:33 +08:00

test_upload.sh

first commit

2026-04-28 11:29:33 +08:00

uv.lock

Fix centered content layout widths

2026-05-26 12:34:12 +08:00

S

Description

AIRegulation-DocAnalysis-Demo

12 MiB

Languages

Python 55.2%

HTML 22.7%

TypeScript 16.2%

CSS 2.8%

Shell 1.4%

Other 1.6%