185 Commits

Author	SHA1	Message	Date
wxg0103	222ca030d6	fix: remove unnecessary error logging in base_chat_open_ai.py	2025-12-11 13:01:02 +08:00
zhangzhanwei	faa6323822	fix: XF tts model	2025-12-10 16:15:01 +08:00
qijingyu0727	532eee571f	feat: enhance TTS model parameters and API version handling (#4480) ... Co-authored-by: xiaoc <648844981@qq.com>	2025-12-10 12:25:43 +08:00
zhangzhanwei	4c0132a3aa	fix: Error thrown when adding voice model	2025-12-09 18:04:21 +08:00
zhangzhanwei	6e87ceffce	feat: Support tag in knowledge_workflow	2025-12-09 12:05:00 +08:00
wxg0103	2a32193c26	fix: update imports to use langchain_aws for Bedrock embeddings and chat models	2025-12-08 14:38:50 +08:00
zhangzhanwei	6c1451f0e1	refactor: Support different types of aliyun stt model	2025-12-05 17:38:24 +08:00
wxg0103	33da607302	feat: implement AWS Bedrock Vision-Language and Reranker models with credential validation	2025-12-02 14:27:38 +08:00
wxg0103	becfd1f4a9	feat: add Docker AI icon SVG asset	2025-11-28 17:41:00 +08:00
wxg0103	590a7a38f3	feat: implement Docker AI model provider with various model credentials and parameters	2025-11-28 16:49:08 +08:00
wxg0103	3670ec27de	feat: enhance image generation by supporting multiple model types	2025-11-24 10:33:17 +08:00
liqiang-fit2cloud	8c0836627a	refactor: remove print.	2025-11-19 17:16:22 +08:00
wxg0103	18b40f3664	fix: remove unnecessary print statement from model invocation	2025-11-19 16:24:49 +08:00
wxg0103	05b59a4d35	fix: remove unnecessary print statement from model invocation	2025-11-19 15:40:59 +08:00
wxg0103	27dd90c7df	feat: enhance token management and normalize content handling in chat model	2025-11-19 15:14:54 +08:00
wxg0103	0555632095	feat: add token usage and top questions statistics endpoints	2025-11-13 14:56:56 +08:00
zhangzhanwei	a568cfe893	fix: Whisper stt model	2025-11-12 11:31:53 +08:00
wxg0103	371e4e6a09	fix: remove streaming parameter from GeminiImage initialization	2025-11-11 14:47:56 +08:00
shaohuzhang1	f457588cd5	feat: Local model validation using local_madel (#4330)	2025-11-07 14:43:40 +08:00
shaohuzhang1	3f6453eb3a	feat: Using the HuggingFace tokenizer (#4329)	2025-11-07 13:29:17 +08:00
shaohuzhang1	1b464c4d8f	fix: Rearrange model dependency (#4324)	2025-11-06 14:24:48 +08:00
shaohuzhang1	a8d0729e65	perf: Memory optimization (#4318)	2025-11-05 19:05:26 +08:00
zhangzhanwei	2a15017523	fix: XF stt model	2025-10-31 13:49:24 +08:00
CaptainB	d0cd6d657a	refactor: replace get_embedding_model_default_params with get_model_default_params	2025-10-30 17:12:30 +08:00
wxg0103	ab434b0a9e	fix: add retry mechanism for file uploads and response handling in image.py	2025-10-30 15:34:41 +08:00
CaptainB	543f83a822	refactor: update ZhipuChatModel to use BaseChatOpenAI and improve token counting ... --bug=1061305 --user=刘瑞斌 【应用】ai对话启用工具后部分模型（智谱）不统计tokens https://www.tapd.cn/62980211/s/1791683	2025-10-30 11:12:43 +08:00
wxg0103	28d403f237	fix: update message handling in image.py to support multiple message types	2025-10-28 16:24:21 +08:00
wxg0103	79fce87e93	fix: add video format detection for uploaded files in image.py	2025-10-28 15:54:56 +08:00
wxg0103	e17d7c4d10	feat: add file upload method with base64 encoding in image.py	2025-10-28 10:15:22 +08:00
shaohuzhang1	03e4bda814	fix: Alibaba Cloud Bailian Stream Response (#4266)	2025-10-27 17:02:53 +08:00
wxg0103	267bdae924	feat: enhance video processing by adding video model parameter and implement file upload to OSS	2025-10-27 16:43:27 +08:00
CaptainB	18543a0703	feat: add OpenAI embedding model parameters form ... --bug=1062976 --user=刘瑞斌 【模型】openai的向量模型，设置dimensions参数后，向量化失败 https://www.tapd.cn/62980211/s/1790130	2025-10-27 12:46:49 +08:00
zhangzhanwei	8fda8196f2	fix: Xinference add ... --bug=1062934 --user=张展玮 【github#4242】添加xinference平台的语音识别模型失败 https://www.tapd.cn/62980211/s/1789683	2025-10-24 14:42:11 +08:00
CaptainB	887de56877	feat: enhance model handling with default parameters and cache model check	2025-10-22 12:30:47 +08:00
zhangzhanwei	89749a3006	feat: Folder authorization backend	2025-10-14 16:33:13 +08:00
CaptainB	e4ac7783e3	feat: add optional parameters to OpenAIEmbeddingModel for enhanced embedding functionality	2025-10-11 15:16:21 +08:00
wxg0103	e8a52c824a	feat: implement authentication check in image processing model	2025-10-09 18:29:28 +08:00
wxg0103	0c0f30c58e	chore: update AliyunBaiLianReranker to use BaseDocumentCompressor and enhance document compression logic	2025-09-28 12:07:38 +08:00
zhangzhanwei	684b86f197	pref: Generate prompt	2025-09-28 09:37:23 +08:00
zhangzhanwei	e8c36a6223	feat: STT model params	2025-09-25 15:47:33 +08:00
wxg0103	15af6c97f8	chore: update negative prompt handling and fix tooltip field labels	2025-09-23 11:13:24 +08:00
wxg0103	180c115f17	fix: update default voice selection for TTS to MOSS-TTSD-v0.5:alex	2025-09-22 14:02:41 +08:00
wxg0103	2e69698e6b	chore: update watermark attributes and cache timeout settings	2025-09-19 18:22:54 +08:00
wxg0103	60ce4bf70d	fix: improve error handling for video generation process	2025-09-19 15:31:48 +08:00
wxg0103	47d4bce84f	fix: improve error handling and logging in video generation process	2025-09-19 14:51:17 +08:00
zhangzhanwei	71cec2fca4	feat: Support stt model params setting	2025-09-19 10:15:02 +08:00
wxg0103	a0118ca397	feat: add TTS model credential and general parameters form	2025-09-18 16:23:03 +08:00
wxg0103	faf238109b	feat: add password authentication option and update related translations	2025-09-18 15:47:38 +08:00
zhangzhanwei	6c2b2f6c17	feat: STT model params	2025-09-16 16:15:21 +08:00
wxg0103	f1cd675caa	feat: add translation for video generation error messages and implement TTV model parameters	2025-09-15 11:08:54 +08:00