149 Commits

Author	SHA1	Message	Date
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
wxg0103	7dc132e35c	feat: implement text-to-video and image-to-video generation nodes with serializers and workflow integration	2025-09-12 14:27:48 +08:00
zhangzhanwei	d2463abaac	feat: Vllm url support v1	2025-09-09 13:49:46 +08:00
shaohuzhang1	d53b4dcd00	fix: Return the link to the connection pool after the node execution is completed (#3957)	2025-08-28 16:08:05 +08:00
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	ee494a5bc0	chore: update file hashes for consistency and remove unnecessary ordering in model queries	2025-08-20 14:20:47 +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
wxg0103	3d1ebad70b	chore: update commit hashes for community and xpack; modify SQL queries to cast meta as JSON	2025-07-31 15:12:33 +08:00
zhangzhanwei	ca070d7466	fix: Model swagger	2025-07-25 18:35:58 +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
CaptainB	ea56fd6212	feat: add db_index to various fields for improved query performance	2025-07-14 11:54:19 +08:00
wxg0103	92fba08185	fix: handle potential None values for user in model serialization	2025-07-14 11:07:10 +08:00
CaptainB	1ac7fc4669	refactor: Update user foreign key constraints and add new fields across multiple models	2025-07-14 10:52:08 +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
zhangzhanwei	c78c2b39fe	fix: Model params permission	2025-07-10 13:49:31 +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
zhangzhanwei	14eea7df42	fix: common user use of shared model params	2025-07-09 16:22:45 +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