yanmuyuan
24645c7fc9
refactor: optimize cloud training process with improved stop handling and file path updates
2025-06-04 13:14:08 +08:00
wyx-hhhh
112acf2275
feat: The document embedding part is restored to its original state
2025-06-04 11:00:06 +08:00
yanmuyuan
2879b176b9
Add is_trained field modification in the cloud
2025-06-03 19:15:09 +08:00
yanmuyuan
96236ff51a
bug fix
2025-06-03 16:59:50 +08:00
yanmuyuan
348f54bf3d
translate into chinese
2025-06-03 10:23:12 +08:00
yanmuyuan
5f358d0fa5
translate Chinese comments to English in cloud service modules
2025-05-30 17:50:01 +08:00
wyx-hhhh
ff39d8b6f7
feat:Cleaned up code comment
2025-05-30 17:24:46 +08:00
wyx-hhhh
fc4039169b
Enhance cloud and local service management with status tracking and improved progress reporting
...
- Implemented service status file management in cloud and local services to track active status and model information.
- Added endpoints to start and stop cloud services, including validation for existing services.
- Enhanced local service management with status checks and progress updates during document processing and chunk embedding.
- Introduced real-time progress tracking for document embedding and chunk processing, allowing for incremental updates.
- Improved error handling and logging throughout the service management processes.
- Refactored chat request handling to intelligently route between local and cloud services based on current status.
2025-05-30 15:53:37 +08:00
yanmuyuan
6d8886cb0b
Change chat reply format
2025-05-30 14:55:50 +08:00
yanmuyuan
8a0a315bbe
fix stop and reset
2025-05-29 17:21:03 +08:00
yanmuyuan
f1844bb337
fix error: reset training
2025-05-29 14:07:28 +08:00
yanmuyuan
5f56028bc0
Stop system modification
2025-05-29 10:30:26 +08:00
yanmuyuan
ee9de8b6b3
Repair data redundancy
2025-05-28 17:06:20 +08:00
yanmuyuan
b219475e04
Resume training at breakpoint
2025-05-28 15:32:27 +08:00
wyx-hhhh
5a1620dee2
feat: Enhance cloud training and inference capabilities
...
- Updated TrainingProgress component to handle cloud training progress data and job ID.
- Modified trainExposureModel to allow nullable path and added optional stageName.
- Enhanced useSSE hook to support cloud model inference with new parameters.
- Introduced CloudProgressData type to align cloud training progress with local training structure.
- Implemented cloud inference request handling with local knowledge retrieval in cloudService.
- Added utility functions for managing active cloud model state in cloudModelUtils.
- Updated cloud inference endpoint to support local knowledge retrieval before cloud inference.
- Refactored advanced chat service to utilize new message structure for cloud inference.
- Enhanced prompt strategies to incorporate knowledge retrieval based on user messages.
2025-05-28 11:44:21 +08:00
yanmuyuan
5644635f3f
Stream response change
2025-05-27 19:10:00 +08:00
yanmuyuan
04c2a9eb16
Stream Output
2025-05-27 17:03:58 +08:00
yanmuyuan
df91ba701c
Progress bar modification
2025-05-27 11:42:39 +08:00
yanmuyuan
590c9439f6
feat: implement async cloud training process with job tracking and API key management
2025-05-23 13:55:42 +08:00
yanmuyuan
c5b609786d
full cloud service
2025-05-23 10:23:48 +08:00
yanmuyuan
7e53db7965
Merge branch 'feature/CloudService'
2025-05-21 15:56:53 +08:00
yanmuyuan
72c40c91de
Service Change
2025-05-21 15:37:19 +08:00
wyx-hhhh
65ce8d4309
Update the model service startup logic, add integrity check for the model path, and support obtaining the model path from different fields
2025-05-21 15:32:59 +08:00
yanmuyuan
cb5d0cb4da
Add gguf path to json file
2025-05-20 19:42:17 +08:00
wyx-hhhh
2c8cd6cc0e
Change the data type of the is_trained field to boolean and update the related logic to reflect this change
2025-05-20 19:06:35 +08:00
wyx-hhhh
33952c1ef6
Change the data type of the is_trained field to boolean and update the related logic to reflect this change
2025-05-20 17:41:30 +08:00
yanmuyuan
bcb928dccf
cloud service
2025-05-20 17:15:02 +08:00
yanmuyuan
a80d18b8a8
fix
2025-05-20 15:26:44 +08:00
yanmuyuan
8bcbeb591c
Check if is_trained exists
2025-05-19 15:12:07 +08:00
doubleBlack2
eaeac58c18
Fix progress bar display abnormality ( #358 )
2025-05-19 11:32:14 +08:00
CangWu
c89bae94b2
Feature/0509/add download current file ( #368 )
...
* feat:add current file to model download progress
* git ignore yarn
* feat: show current downloading
---------
Co-authored-by: Ye Xiangle <yexiangle@mail.mindverse.ai>
Co-authored-by: kevinaimonster <kevinaimonster@gmail.com>
2025-05-16 14:02:56 +08:00
doubleBlack2
899e2cb752
Provide a selection of Chinese mirror websites for Huggingface ( #360 )
...
* Provide a selection of Chinese mirror websites for Huggingface
* Remove default values
2025-05-16 11:55:27 +08:00
wuyuxiangX
1f257184bd
Feature/fix duplicate files ( #363 )
...
* feat: file display and deletion related
* fix: file saving logic
2025-05-15 15:30:34 +08:00
Xiang Ying
4f6dffc64d
Update utils.py for progress ( #365 )
2025-05-15 15:27:29 +08:00
KKKKKKKevin
5ceed311bf
Feature/add hint ( #361 )
...
* optimize doc
* better code
---------
Co-authored-by: kevinaimonster <kevinaimonster@gmail.com>
2025-05-14 20:26:45 +08:00
KKKKKKKevin
b4766a9d9d
UI Improvements and Thinking Model Configuration Enhancements ( #353 )
...
* Join AI Network -> Export your Second Me
* Default Synthesis Mode -> high
Default Epoch -> 3
* Set Thinking-Mode Default Value
* Better Display Of ReadMe
* default value of thinking mode
* Set Default value of enableL0Retrival to false
2025-05-13 19:42:34 +08:00
Crabboss
166db04c22
feature: add support for multi deepseek api format ( #352 )
2025-05-13 16:12:42 +08:00
KKKKKKKevin
601f371f46
change log ( #346 )
2025-05-12 11:59:38 +08:00
Xiang Ying
a65f4a58fe
hotfix for strage problem which leads to the error during graphrag. ( #347 )
2025-05-12 11:59:35 +08:00
yanmuyuan
94e960e1c8
Enhance GGUF model handling with timestamps, metadata and memory training status
2025-05-12 10:24:18 +08:00
yingapple
da2b704ed4
fix(model tokenizer): just use the model tokenizer without anythink else.
2025-05-09 16:09:20 +08:00
ryangyuan
c3855f37ad
Fix/0429/fix all log ( #318 )
...
* fix:fix return all log problem
* fix:delete no use code
* fix: add sse offset
* fix: change offset to string
* fix: fix more localStore
* fix: change log only
* fix: cancel offset
* fix: remove offset
* fix:delete no use code
* fix:add hertbeat
* fix: delete useless code
---------
Co-authored-by: Ye Xiangle <yexiangle@mail.mindverse.ai>
2025-05-07 15:53:25 +08:00
yexiangle
ff9a9b9970
delete useless code in route_l2.py ( #332 )
2025-05-07 13:40:10 +08:00
yexiangle
82422a5f76
Merge pull request #313 from mindverse/feat/0427/meta_exposure
...
Feat/0427/meta exposure
2025-05-06 16:04:38 +08:00
ryangyuan
b7f0cc7feb
Feat/0422/train l1 exposure ( #319 )
...
* feat:add get steps content(EXTRACT_DIMENSIONAL_TOPICS,MAP_ENTITY_NETWORK,DECODE_PREFERENCE_PATTERNS,AUGMENT_CONTENT_RETENTION)
* feat:add file_type
* feat: exponse train L1
* feat:jsonfy return data
* fix: jsonfy
* feat:add log
* fix: fix step change error
* feat:delete useless log
* fix:fix not import problem
* fix:fix old trainprocess init problem
* feat: Train Step Show Table
* feat:add L1_exposure_manager optimize code structure
* fix: fix bio return format & map_your_entity_network
* feat: show tip when resource empty
* add have_output & path
* fix: fix log problem
* feat: adjustment output ui
* fix: L1 exposure add loading
---------
Co-authored-by: Ye Xiangle <yexiangle@mail.mindverse.ai>
2025-05-06 16:02:22 +08:00
KKKKKKKevin
245bb1e27b
fix:hotfix use_previous_params problem ( #320 )
...
Co-authored-by: Ye Xiangle <yexiangle@mail.mindverse.ai>
2025-04-30 16:13:18 +08:00
KKKKKKKevin
78bb0e3c8a
Merge pull request #316 from mindverse/fix/0430/hotfix_use_previous_params
...
fix:hotfix use_previous_params problem
2025-04-30 16:08:06 +08:00
Ye Xiangle
1bf8ba5ce7
fix:hotfix use_previous_params problem
2025-04-30 14:49:07 +08:00
yexiangle
b3dcdd8ed5
fix:fix monitor model download log problem ( #305 )
2025-04-28 17:12:41 +08:00
yingapple
53dfdafc9b
feat: up max seq length
2025-04-27 11:59:16 +08:00
