zhangzhanwei
|
4786970689
|
feat: Support iFLYTEK large model for Chinese-English speech recognition
|
2025-08-28 10:57:52 +08:00 |
|
wxg0103
|
93e5c9db38
|
feat: enhance model provider with additional LLM and embedding models
|
2025-08-27 11:14:05 +08:00 |
|
wxg0103
|
8cdb085734
|
feat: add support for v2 API version in embedding models and update validation logic
|
2025-08-26 13:20:31 +08:00 |
|
zhangzhanwei
|
20cf018c81
|
fix: Models rerank stt
|
2025-08-26 11:58:51 +08:00 |
|
wxg0103
|
fbfeb67db6
|
chore: update file hashes for community and xpack
fix: correct parameter name in KimiChatModel instantiation
|
2025-08-25 10:51:37 +08:00 |
|
zhangzhanwei
|
f5fada9b9e
|
feat: Vllm reranker model bge reranker v2 m3
|
2025-08-21 18:02:47 +08:00 |
|
zhangzhanwei
|
c8ec7c5558
|
feat: Vllm whisper model
|
2025-08-20 18:25:21 +08:00 |
|
wxg0103
|
c83462ef74
|
fix: make API URL and keys required fields in llm.py
|
2025-08-20 10:33:47 +08:00 |
|
zhangzhanwei
|
354f85ddb6
|
feat: Qwen asr speech recognition
|
2025-08-19 15:44:22 +08:00 |
|
wxg0103
|
044465fcc6
|
feat: enhance model credential validation and support for multiple API versions
|
2025-08-18 16:46:27 +08:00 |
|
zhangzhanwei
|
b32b06391f
|
feat: Qwen2.5-omni-7b full modal speech recognition
|
2025-08-18 11:05:34 +08:00 |
|
zhangzhanwei
|
15ec70c4a8
|
feat: Interface with Qwen Omni speech to text model
|
2025-08-15 17:52:43 +08:00 |
|
CaptainB
|
581143cba2
|
fix: improve error logging format for TencentCloudSDKException
|
2025-08-14 14:31:03 +08:00 |
|
zhangzhanwei
|
f9f475a5a0
|
feat: Integrate with Tencent SentienceRecognition model
|
2025-08-14 11:23:16 +08:00 |
|
shaohuzhang1
|
bd589e50e2
|
fix: Calling the model using non stream cannot obtain the token (#3826)
|
2025-08-06 11:00:43 +08:00 |
|
wxg0103
|
0e684f2946
|
chore: update SVG icons in local_icon_svg and modify community file hash
--bug=1059658 --user=王孝刚 【模型】icon 替换 https://www.tapd.cn/62980211/s/1747959
|
2025-08-04 11:09:50 +08:00 |
|
CaptainB
|
2ec98d9c3b
|
fix: update request data handling to use request.data instead of request.query_params
|
2025-07-21 12:25:17 +08:00 |
|
shaohuzhang1
|
a67b39c87e
|
fix: reranker prefix (#3605)
|
2025-07-15 16:00:22 +08:00 |
|
wxg0103
|
cef7075382
|
fix: update image size format and expand available options in tti.py
|
2025-07-15 09:23:50 +08:00 |
|
wxg0103
|
99d94abe85
|
refactor: improve image URL handling and clean up unused code in base_image_generate_node.py and tti.py
|
2025-07-11 14:44:04 +08:00 |
|
wxg0103
|
fe78de5d3c
|
feat: add email templates for verification codes in English, Chinese, and Traditional Chinese
|
2025-07-10 15:02:10 +08:00 |
|
wxg0103
|
16088975fa
|
refactor: enhance text-to-speech processing by splitting content into chunks and merging audio segments
|
2025-07-09 18:08:41 +08:00 |
|
wxg0103
|
eceb8f8375
|
refactor: simplify optional parameters and update image generation base URL
|
2025-07-09 15:45:49 +08:00 |
|
wxg0103
|
573ec2b706
|
refactor: remove unused ModelInfo entry for dall-e-2 in openai_model_provider.py
|
2025-07-08 19:05:53 +08:00 |
|
wxg0103
|
521fff2818
|
refactor: add is_cache_model method to various model classes to standardize cache behavior
|
2025-07-08 17:11:31 +08:00 |
|
wxg0103
|
1d35700d2a
|
refactor: enhance model retrieval logic and update optional parameters
|
2025-07-03 17:28:19 +08:00 |
|
CaptainB
|
8c0361bbc2
|
refactor: update API endpoint paths to include admin prefix
|
2025-07-01 18:08:12 +08:00 |
|
wxg0103
|
7e80b951ac
|
refactor: model params
|
2025-06-30 17:47:31 +08:00 |
|
wxg0103
|
da3c945b56
|
refactor: model
|
2025-06-30 17:42:48 +08:00 |
|
wxg0103
|
a7cbba161c
|
refactor: xfembedding model
|
2025-06-27 16:34:22 +08:00 |
|
wxg0103
|
d0e447774f
|
refactor: model
sync2gitee / repo-sync (push) Waiting to run
|
2025-06-27 11:54:27 +08:00 |
|
wxg0103
|
594ca6cd89
|
refactor: model
|
2025-06-27 11:18:02 +08:00 |
|
wxg0103
|
20010ee227
|
refactor: model
|
2025-06-26 20:06:26 +08:00 |
|
wxg0103
|
0886459bad
|
refactor: Add log records for image understanding
--bug=1057568 --user=王孝刚 【模型管理】阿里云百炼视觉模型输入错误的基础模型可正常创建 https://www.tapd.cn/62980211/s/1719185
|
2025-06-26 16:58:18 +08:00 |
|
CaptainB
|
a73e0b10f9
|
refactor: replace logging with maxkb_logger for consistent logging across modules
|
2025-06-25 17:00:18 +08:00 |
|
CaptainB
|
fe8f87834d
|
refactor: replace logging with maxkb_logger for consistent logging across modules
|
2025-06-25 16:46:50 +08:00 |
|
wxg0103
|
2f9052279a
|
fix: VolcanicEngine tts error
|
2025-06-25 14:47:08 +08:00 |
|
wxg0103
|
9f684dadd2
|
refactor: add aliyun llm example
--bug=1057451 --user=王孝刚 【模型】-阿里百炼的基础模型中增加千问3的模型,保持和v1相同 https://www.tapd.cn/62980211/s/1718320
|
2025-06-25 14:34:29 +08:00 |
|
wxg0103
|
44c318e8c8
|
fix: VolcanicEngine stt error
--bug=1057449 --user=王孝刚 【模型】添加火山语音识别模型失败 https://www.tapd.cn/62980211/s/1718297
|
2025-06-25 14:28:31 +08:00 |
|
wxg0103
|
c253e8b696
|
refactor: remove print
|
2025-06-24 15:30:42 +08:00 |
|
CaptainB
|
3e9c3c0602
|
feat: update UUID generation to use uuid7 for improved uniqueness across models
|
2025-06-23 11:19:20 +08:00 |
|
wxg0103
|
74ce98c39b
|
refactor: gemini
|
2025-06-05 09:12:38 +08:00 |
|
wxg0103
|
3e9069aac1
|
refactor: bailian
|
2025-05-06 15:03:31 +08:00 |
|
CaptainB
|
870fabe187
|
chore: add init file for every folder
|
2025-04-29 10:31:49 +08:00 |
|
wxg0103
|
83ace97ecc
|
refactor: model
|
2025-04-25 18:12:55 +08:00 |
|
wxg0103
|
7f492b4d92
|
refactor: openai
|
2025-04-25 17:53:22 +08:00 |
|
wxg0103
|
ff41b1ff6e
|
refactor: tokens
|
2025-04-25 10:17:50 +08:00 |
|
CaptainB
|
fbb4e7d449
|
feat: add __init__.py file to initialize the package
|
2025-04-24 11:10:58 +08:00 |
|
wxg0103
|
cc0e431605
|
refactor: remove image params
sync2gitee / repo-sync (push) Waiting to run
|
2025-04-22 18:22:50 +08:00 |
|
wxg0103
|
55705593a9
|
feat: remove qwen
|
2025-04-22 14:35:09 +08:00 |
|