bc23679c1b
bugfix
2026-07-29 11:43:26 +08:00
78dd2b0788
fix: cate.llms -> cate['llms'] — get_llms_by_catelog_to_customer returns plain dict not DictObject
2026-07-29 11:15:36 +08:00
1c25542e72
feat: cockpit-style model plaza with search, category tabs, provider sidebar
...
New layout:
- Search bar (top) with fuzzy name/description match
- Category tabs (wrapping, single-select)
- Provider sidebar (left, single-select)
- Card grid (right, sorted by name, refreshed on filter change)
- Both category/provider unselected = all published models
Added get_plaza_models() for flat filtered model listing.
Supports combined filtering: provider + category + search.
2026-07-28 17:55:17 +08:00
68dd92a353
sort: add a.name as final sort column in model listing queries
...
get_llmage_llm and get_llms_by_catelog had ORDER BY ending
at a.id — model names within same provider/catalog appeared
in arbitrary order. Added a.name as final sort key.
2026-07-28 16:23:41 +08:00
a2937d3cff
fix: strip line number corruption from 12 media DSPY files
...
The ad5d8c0 commit had line number prefixes (1|, 2|, ...) baked into
file content. Also fixed cache call bugs:
- params_kw.model or 'qwen3-max' -> params_kw.model
- 'ktv_pipeline' hardcoded -> catelogid variable
- extra tab before params_kw.llmcatelogid
- missing f-string braces in debug()
2026-07-27 10:22:34 +08:00
a4aa40faf5
fix: llm上线检查定价数据显示实际内容而非记录数
...
改用 pricing.pricing.get_pricing_display() 获取格式化定价明细，
替换原来的 select count(*) 只显示记录条数
2026-07-24 23:44:00 +08:00
287e6c5a40
fix: 修复6个v1 DSPY缓存替换造成的缩进错误
2026-07-24 16:56:50 +08:00
2d49ff9968
feat: 上线检查计费测试显示完整价格字段明细
2026-07-24 16:48:45 +08:00
e246f91e77
fix: asyncinference KeyError status→.get(status)
2026-07-24 14:34:16 +08:00
c099af6bc7
chore: 删除load_test.py
2026-07-24 11:01:48 +08:00
ad5d8c00c5
perf: 18个v1 DSPY全改用llmid缓存,去3表JOIN+DB连接
2026-07-24 11:01:40 +08:00
ef1e228f19
perf: llmid缓存(启动预热+内存查),v1/chat/completions去3表JOIN
2026-07-23 18:26:52 +08:00
5e48622e2a
bugfix
2026-07-21 14:44:27 +08:00
cf5d48d96c
bugfix
2026-07-21 14:43:15 +08:00
7f6501b700
bugfix
2026-07-21 11:11:48 +08:00
00741bbf4f
bugfix
2026-07-21 11:11:02 +08:00
6aa2f76c1e
fix: list_llms按catelogid排序-改SQL ORDER BY替代sort参数,修复同catelog被拆分成多组
2026-07-21 10:52:05 +08:00
112c86e80b
bugfix
2026-07-20 19:34:24 +08:00
7b792c03d4
bugfix
2026-07-20 19:32:48 +08:00
3ff16da646
bugfix
2026-07-20 19:20:57 +08:00
ee68fbefa7
bugfix
2026-07-20 19:19:47 +08:00
84c03a7878
bugfix
2026-07-20 19:18:17 +08:00
933085b7f3
bugfix
2026-07-20 19:13:35 +08:00
142dcbb02e
bugfix
2026-07-20 11:29:06 +08:00
5ea0291af7
feat: 添加 kimi-k3 模型的 llm 和 llm_api_map 配置
...
- 新增 llm 表记录: kimi-k3-llm (月之暗面 Kimi K3)
- 新增 llm_api_map 映射: t2t (纯文本) + vision/tm2t (多模态)
- uapiio 记录已存在，无需新增
完成 kimi-k3 模型的完整数据库配置
2026-07-20 11:19:02 +08:00
e0855b6415
refactor: 将 kimi-k3 多模态内容构建改为纯 Jinja2 模板
...
- 删除 build_kimi_content() Python 函数
- 在 SQL data 模板中用纯 Jinja2 语法构建 content 数组
- 新增 file_to_b64() 和 file_mime() 辅助函数注册到 ServerEnv
- 保持向后兼容，功能不变
2026-07-20 10:48:22 +08:00
ce17c48022
feat: build_kimi_content 迁入 llimage/utils.py，自含 webpath→base64 转换
2026-07-17 18:12:17 +08:00
c8b7d0cd07
refactor: kimi_t2t data 模板 — build_kimi_content 一行搞定多模态
2026-07-17 17:58:09 +08:00
f1930af597
feat: kimi_t2t 支持多模态 — 图片/视频通过 webpath_to_base64 转 data URI
2026-07-17 17:52:07 +08:00
afced72c3c
fix: kimi uapi 补全 uapiio 定义，移除所有占位符
2026-07-17 17:42:07 +08:00
20833b8e90
feat: Kimi K3 API 接入 — 对话补全+文件管理 6 个 uapi
2026-07-17 17:35:18 +08:00
3d47867bd3
revert(llmage): undo unauthorized model_plaza modification
2026-07-17 16:35:24 +08:00
d82a8b554f
feat(llmage): add pricing query tab to model plaza
2026-07-17 16:10:24 +08:00
929dd017f9
fix(llmage): model_pricing returns widget tree, simplified UI
2026-07-17 16:09:12 +08:00
233b5db481
feat(llmage): model pricing query page — select model, display pricing table
2026-07-17 16:08:08 +08:00
6ab53eca2b
fix: llm_create.dspy 补充 ownerid 自动注入（logined_userorgid 对自定义端点不生效）
2026-07-14 18:22:11 +08:00
3a2da1e636
fix: retry accounting button - add credentials:include to fetch call
2026-07-14 14:18:02 +08:00
83e1fa8ba3
feat: load_product_category_product返回providerid
...
将llm.providerid传递给product_management的导入流程
2026-07-13 14:53:46 +08:00
e5f55fc3f3
fix: model codes table supplychain.suppliers -> suppliers to avoid get_code.dspy SQL error
2026-07-10 10:55:00 +08:00
f0d3550b63
fix: use get_sor_context(rbac) to query suppliers in sage db
2026-07-10 09:26:21 +08:00
3ae70d2c92
fix: providerid 下拉从 suppliers 表而非 organization 获取
2026-07-10 09:21:32 +08:00
6186d15fee
refactor: providerid codes → supplychain.suppliers
2026-07-09 13:39:09 +08:00
802ab896d8
fix: correct tab/space indentation — tabs for sync/async/llmclient, spaces for product_interface
2026-07-09 11:43:53 +08:00
064df40b4a
fix: tab/space indentation in tenantid lines
2026-07-09 11:42:22 +08:00
fd65b5a59e
feat: write tenantid to llmusage from API request params
...
Populate llmusage.tenantid from params_kw.tenantid in all 6 inference paths:
syncinference, product_interface, llmclient, asyncinference
2026-07-09 11:38:43 +08:00
8f63d20f57
docs: 删除冗余status模型，标注异步状态通过/v1/tasks查询
2026-07-08 15:22:11 +08:00
a61e60deff
cleanup: 删除冗余status端点(realesrgan/synth)，统一走query_apiname
2026-07-08 15:20:39 +08:00
6c030b0a01
cleanup: 移除media端点中的空if transno块
2026-07-08 13:49:36 +08:00
b8de8db76f
fix: 14个media端点移除冗余uuid生成，统一走inference+getID()
2026-07-08 13:42:38 +08:00
fe82251e2e
feat: /v1/media/{apiname} 14端点(KTV GPU服务)
2026-07-07 21:28:05 +08:00
