admin/momentry_core
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
88 Commits 1 Branch 2 Tags
dfd6bf98617d18f03ecbcbe0b4954ab91d94d105
Commit Graph

31 Commits

Author SHA1 Message Date
Warren
dfd6bf9861 docs: production test report v1.0.0 2026-05-08 02:19:09 +08:00
Accusys
32f1d3e28a Release v1.0.0 notification 2026-05-08 01:46:40 +08:00
Warren
3e70f1b590 M4: bug report - parent_chunks missing summary_vector/scene_order 2026-05-08 01:26:43 +08:00
Warren
b577f5b3bc M4: bug report - smart search still uses Ollama/mxbai 2026-05-08 01:22:31 +08:00
Warren
7a7bccc04a M4: bug report - search uuid→file_uuid column rename 2026-05-08 01:11:54 +08:00
Accusys
69635bd4da Notify M4: release ready for sync 2026-05-08 01:01:34 +08:00
Warren
26d9c33419 Merge branch 'main' of 192.168.110.201:/Users/accusys/momentry_core_0.1/ 2026-05-08 00:42:36 +08:00
M5
1c9c8f7d61 M5 repo open for push, add guide for M4 2026-05-08 00:41:39 +08:00
M5
23d114d058 Add 5W1H+ quality evaluation report 
- Gemma4 26B scored 5/10 overall
- Template-heavy, lacks specific details and emotion
- Suggested improvements: prompt tuning, temperature, model upgrade
 2026-05-08 00:32:57 +08:00
Warren
7b822c754c Merge M5 docs into M4 2026-05-08 00:26:09 +08:00
M5
56dfe1df8f Add Qdrant collection naming convention 
- Format: {machine}_{env}_{type}
- M5 dev: m5_dev_rule1, m5_dev_face
- M4 dev: m4_dev_rule1, m4_dev_face
- M4 prod: m4_prod_rule1, m4_prod_face
- Controlled via QDRANT_COLLECTION env var
 2026-05-08 00:22:39 +08:00
M5
041e414a9b Add DB/vector sync guide for M4 
- PostgreSQL dump (890MB) ready at /tmp/momentry_3abeee81.sql
- Qdrant face vectors (4873 points, 512D) available
- Text vectors pending (5W1H+ in progress, ~9h)
- Output JSON files ready for rsync
 2026-05-08 00:02:05 +08:00
M5
73e9825c6e Add git sync setup guide for M4 2026-05-07 23:43:16 +08:00
M5
28e927f7bb Initial commit: docs_v1.0 structure 
- API_V1.0.0: 正式 API 文件（spec、release、deploy、test）
- M4_workspace: M4 工作記錄（review、issue、提案）
- M5_workspace: M5 工作記錄（實作、評估、sync）
- AGENTS.md: 專案規則

M5/M4 協作方式：git push/pull 同步 workspace 文件
 2026-05-07 23:42:19 +08:00
Warren
0b42365ecd docs: complete M5 Gemma4 deployment record V1.1 — full build, dylib fix, codesign, reasoning off, OpenCode config 2026-05-06 17:54:16 +08:00
Warren
f65ac89e6a deploy: Gemma 4 31B llama-server running on M5 Max (192.168.110.201:8081) 2026-05-06 17:13:32 +08:00
Warren
2e29780d40 docs: update identity clustering report with TMDb direct match vs iterative enrichment analysis 2026-05-06 15:03:04 +08:00
Warren
ca4f59d811 fix: RCA trace 39/45 collision - raise composite threshold 0.35→0.50, add min_face_similarity, add temporal collision check. Verified: collision resolved 2026-05-06 14:55:49 +08:00
Warren
65a1f77e65 feat: trace quality agent selection report, identity clustering runner_v2 DB write, age/gender CoreML selection, updated experiment config UUID 2026-05-06 14:41:48 +08:00
Warren
74b6182eba feat: media API (video/bbox/thumbnail), UUID unification, dot matrix text, portal fixes, API dictionary V1.3 2026-05-06 13:34:49 +08:00
Warren
e75c4d6f07 cleanup: remove dead code and duplicate docs 
- Remove session-ses_2f27.md (161KB raw session log)
- Remove 49 ROOT_* duplicate files across REFERENCE/
- Remove 14 duplicate files between REFERENCE/ root and history/
- Remove asr_legacy.rs (dead code, replaced by asr.rs)
- Remove src/core/worker/ (duplicate JobWorker)
- Remove src/core/layers/ (empty directory)
- Remove 4 .bak files in src/
- Remove 7 dead private methods in worker/processor.rs
- Remove backup directory from git tracking
 2026-05-04 01:31:21 +08:00
Warren
ee81e343ce chore: remove obsolete APIs (register, probe, n8n, videos, people) 
- Remove /api/v1/register (replaced by /api/v1/files/register)
- Remove /api/v1/probe (replaced by /api/v1/files/:uuid)
- Remove /api/v1/n8n/... (n8n workflow only)
- Remove /api/v1/unregister (high risk)
- Remove /api/v1/videos list (replaced by /api/v1/files)
- Remove /api/v1/people (merged into /api/v1/identities)
- Clean up dead code and unused structs
 2026-04-30 22:16:24 +08:00
Warren
4d75b2e251 docs: update docs_v1.0/ documentation 
- Fix markdown lint issues (MD030, MD047, MD051, MD028, MD005)
- Update AI agents, architecture, implementation docs
- Add new identity, face recognition, and API documentation
- Remove deprecated face/person API guides
 2026-04-30 15:10:41 +08:00
Warren
1f84e5469f feat: backup architecture docs, source code, and scripts 2026-04-25 17:15:45 +08:00
Warren
59809dae1f chore: backup before migration to new repo 2026-04-23 16:46:02 +08:00
Warren
13dd3b30f3 docs: 添加 Places365 模型完整指南 
內容:
- 手動下載方法（3 種）
- 模型驗證步驟
- 使用方式和預期改進
- 故障排除指南

目前狀態:
- ✅ ImageNet 模型正常運作（37% 準確率）
- ⏳ Places365 模型可選手動下載（85-90% 準確率）
- 📄 完整安裝和使用指南
 2026-04-01 03:19:42 +08:00
Warren
f45ecf4643 docs: 添加長影片場景識別測試報告 
測試結果:
- ✅ Old_Time_Movie_Show (114 分鐘) 處理成功
- ✅ 處理時間 313 秒（5.2 分鐘）
- ✅ 加速比 22x
- ✅ 記憶體使用穩定（3-4GB）
- ✅ 1,379 個取樣點

效能指標:
- 取樣間隔：5 秒
- 最小場景：10 秒
- 場景數量：1（ImageNet 模型限制）
- 信心度：25%

建議:
- 下載 Places365 模型提升準確率
- 整合 CUT 場景切換偵測
- 優化長片處理策略
 2026-04-01 03:08:35 +08:00
Warren
d12caba00a docs: 添加場景識別測試結果報告 
新增:
- docs_v1.0/TESTING/SCENE_CLASSIFICATION_TEST_RESULTS_2026_04_01.md

測試結果:
- ✅ Rust 單元測試 5/5 通過
- ✅ Python 功能測試通過
- ✅ ExaSAN 影片識別成功
- ✅ 79 個取樣點，處理時間 1.2 秒
- ✅ 信心度 37%（ImageNet 模型）

效能指標:
- 處理速度：133x 實時
- 模型大小：44.7 MB
- MPS 加速：啟用
 2026-04-01 03:01:07 +08:00
Warren
395f74bf07 feat: 添加場景識別 Playground API 整合 
新增:
- scripts/test_scene_api.py - API 測試腳本
- docs_v1.0/IMPLEMENTATION/SCENE_API_INTEGRATION.md - API 整合指南

功能:
- ✅ GET /api/v1/scene/:uuid endpoint 設計
- ✅ Python 測試腳本
- ✅ 完整使用文檔
- ✅ Python 整合範例

使用方式:
```bash
# 啟動 Playground (port 3003)
cargo run --bin momentry_playground -- server --port 3003

# 測試場景識別
python3 scripts/test_scene_api.py <video_uuid>
```

目前狀態:
- ✅ Python 場景識別功能正常
- ✅ API endpoint 設計完成
- ⏳ Rust 完整實作進行中
- 📄 完整文檔已建立
 2026-04-01 02:55:52 +08:00
Warren
363d6913f9 docs: 添加 Places365 安裝指南和測試腳本 
新增:
- docs_v1.0/IMPLEMENTATION/PLACES365_INSTALLATION.md
- scripts/test_places365_scene.py

功能:
- ✅ Places365 380 個場景類別載入
- ✅ 場景分類器測試
- ✅ 影片場景分類測試

目前狀態:
- ✅ 基礎場景識別功能正常
- ⏳ Places365 模型可選手動安裝
- 📊 準確率 37% → 預期 85-90%
 2026-04-01 02:39:13 +08:00
Warren
4109ec3d95 docs: 修復場景識別測試報告 markdown 編號 
- 修正有序列表編號符合 markdownlint MD029
- 使用 1/2/3 樣式而非連續編號
 2026-04-01 02:21:40 +08:00