1577 Commits

Author	SHA1	Message	Date
-LAN-	dee5d0911e	Merge branch 'feat/enhance-multi-modal-support' into deploy/dev	2024-10-17 16:40:49 +08:00
-LAN-	39d029d1b5	fix(podcast_audio_generator): specify audio format for file loading	2024-10-17 16:40:28 +08:00
-LAN-	5f8199b3a5	Merge branch 'feat/enhance-multi-modal-support' into deploy/dev	2024-10-17 16:05:07 +08:00
-LAN-	9156cfd384	fix(podcast_audio_generator): remove explicit format specification for audio file loading	2024-10-17 16:04:49 +08:00
StyleZhang	1397c782d4	merge feat/attachment	2024-10-17 15:31:32 +08:00
-LAN-	7d88218a8b	Merge branch 'feat/enhance-multi-modal-support' into deploy/dev	2024-10-17 13:24:24 +08:00
-LAN-	b10a599cc8	feat(podcast_audio_generator): improve audio generation workflow ... - Replace custom silent MP3 generation with pydub library for silent WAV data. - Adjust silence duration between audio segments for a more seamless playback. - Export combined audio as WAV format in memory for better audio quality. - Update dependencies to include pydub for enhanced audio manipulation.	2024-10-17 13:23:55 +08:00
ybalbert001	fdcf87c70c	fix https://github.com/langgenius/dify/issues/9409 (#9433) ... Co-authored-by: Yuanbo Li <ybalbert@amazon.com>	2024-10-17 10:47:56 +08:00
-LAN-	a28e2341da	Merge branch 'feat/enhance-multi-modal-support' into deploy/dev	2024-10-16 19:28:21 +08:00
-LAN-	8d424c8222	refactor(tool_node): simplify tool_file_id assignment ... - Remove redundant condition by directly assigning tool_file_id. - Assume URL structure provides necessary file identifier.	2024-10-16 19:28:04 +08:00
-LAN-	739919556d	Merge branch 'feat/enhance-multi-modal-support' into deploy/dev	2024-10-16 18:39:17 +08:00
-LAN-	1529fe3b01	refactor(api): enhance file streaming response handling ... - Split returned variables in `get_file_generator_by_tool_file_id` for improved clarity. - Revised response construction to directly use file stream and include headers for content length. - Removed unnecessary type hint that restricted flexibility.	2024-10-16 18:39:02 +08:00
-LAN-	912e4ca686	Merge branch 'feat/enhance-multi-modal-support' into deploy/dev	2024-10-16 18:29:30 +08:00
-LAN-	8cfdaf8325	refactor(workflow/nodes): unify filtering and ordering under a single node ... - Rename ListFilterNode to ListOperatorNode for broader functionality. - Introduce 'FilterBy' class to consolidate filter conditions. - Update node mapping and enums to reflect the new naming. - Revise unit tests to accommodate combined operations in ListOperatorNode.	2024-10-16 17:51:50 +08:00
-LAN-	f647715a28	refactor(workflow): rename and restructure list filter components ... - Renamed `FilterBy` to `FilterCondition` for clarity. - Moved `models.py` to `entities.py` to better reflect the purpose of the contained classes. - Updated imports and references across the codebase to align with the renaming and file restructuring.	2024-10-16 17:31:14 +08:00
-LAN-	cdcc0c1a15	refactor(workflow): improve handling of outputs and inputs ... - Use empty dictionaries instead of None for default outputs and inputs. - Replace manual json loads with dedicated getter methods for inputs and outputs. - Ensure type hints for converted input and output dictionaries. - Improve code readability and reduce potential null errors.	2024-10-16 17:28:02 +08:00
Yi	03d704ea5a	Merge branch 'fix/rerank-validation-in-run' into deploy/dev	2024-10-16 16:47:49 +08:00
zhuhao	86594851cb	refactor: update the default values of top-k parameter in vdb to be consistent (#9367)	2024-10-16 16:00:21 +08:00
Jyong	50635e9c15	Fix/economical knowledge retrieval (#9396)	2024-10-16 15:13:45 +08:00
-LAN-	f91a80b489	Merge branch 'feat/enhance-multi-modal-support' into deploy/dev	2024-10-16 14:35:21 +08:00
-LAN-	fd35e32265	refactor(http_executor): improve HTTP request logging format ... - Utilize `urlparse` to separate URL components for a cleaner format. - Ensure query parameters in URLs are accurately appended. - Add `Host` header and consistent CRLF line endings for HTTP compliance. - Simplify body content generation and calculate `Content-Length` for logs.	2024-10-16 14:34:47 +08:00
zhuhao	7d3dad3d1d	feat: add timezone conversion for time tool (#9393)	2024-10-16 11:17:40 +08:00
ice yao	dd22e78515	fix: Deprecated gemma2-9b model in Fireworks AI Provider (#9373)	2024-10-16 10:44:54 +08:00
crazywoola	423df67042	fix: use gpt-4o-mini for validating credentials (#9387)	2024-10-16 10:18:06 +08:00
非法操作	da25b91980	fix: remove the stream option of zhipu and gemini (#9319)	2024-10-15 19:13:43 +08:00
Jason Tan	9b8aa9b75d	feat: add minimax abab6.5t support (#9365)	2024-10-15 19:00:05 +08:00
非法操作	4ffaabcc04	feat: add glm-4-flashx, deprecated chatglm_turbo (#9357)	2024-10-15 17:33:34 +08:00
Warren Wong	b597a0d31c	fix: Azure OpenAI o1 max_completion_token and get_num_token_from_messages error (#9326) ... Co-authored-by: wwwc <wwwc@outlook.com>	2024-10-15 16:26:44 +08:00
Wei-shun Bao	fb32e5ca9a	fix: In the output, the order of 'ta' is sometimes reversed as 'at'. #8015 (#8791)	2024-10-15 16:24:29 +08:00
-LAN-	3483a21772	Merge branch 'feat/enhance-multi-modal-support' into deploy/dev	2024-10-15 15:35:03 +08:00
-LAN-	a36ef8430e	refactor(core): improve type annotations and file handling consistency ... - Use more precise type annotations with Sequence and Mapping for task entities. - Ensure raw_prompt is assigned properly after replacement in advanced prompt transform. - Remove unused generator return type from _fetch_context method. - Refactor tool node file handling to retrieve more comprehensive file attributes, ensuring file existence validation in the database.	2024-10-15 15:34:14 +08:00
zhuhao	cd7ab6231f	refactor: Add an enumeration type and use the factory pattern to obtain the corresponding class (#9356)	2024-10-15 12:51:13 +08:00
-LAN-	dba67cd87a	fix(memory): filter non-image file types in prompt message content ... - Skip non-image files when converting file objects to prompt message content. - Ensures only image files are processed, improving the accuracy and relevance of prompt messages.	2024-10-15 12:01:00 +08:00
-LAN-	8e023d60e8	Merge branch 'feat/enhance-multi-modal-support' into deploy/dev	2024-10-15 11:05:12 +08:00
-LAN-	b3fdd618a1	refactor(core): simplify role handling and improve usability ... - Replaced explicit string usage with `CreatedByRole` enum for better maintainability. - Removed duplicate `CreatedByRole` class definition, improving codebase consistency. - Increased file number limits from 6 to 10 to allow more file uploads. - Transitioned `AppMode` to a string enum for consistent type usage. - Refactored `extract_thread_messages` function argument for flexibility. - Removed file extension limitation in file service to support custom extensions. - Improved enum import statements across multiple modules for clarity and consistency.	2024-10-15 11:04:28 +08:00
ice yao	5908fd6552	Adapt input type parameter with MiniMax embedding model (#9342)	2024-10-15 09:01:00 +08:00
ice yao	3f9d6759d4	feat: Add qwen2.5 72B Instruct model in Fireworks AI (#9340)	2024-10-14 23:15:34 +08:00
ice yao	aba70207ab	feat: Add fireworks custom llm intergration (#9333)	2024-10-14 22:50:31 +08:00
Hash Brown	fa47f0c707	chore: disable chat service API passing parent_message_id (#8984)	2024-10-14 19:13:16 +08:00
-LAN-	353ed8652c	Merge branch 'feat/enhance-multi-modal-support' into deploy/dev	2024-10-14 16:53:38 +08:00
-LAN-	0d310b503b	refactor(prompt): improve handling of variable templates in advanced prompt transform	2024-10-14 16:47:03 +08:00
-LAN-	03018823d8	fix(workflow): handle special values for process data consistently ... - Apply `handle_special_values` to `process_data` in workflow cycle management. - Improve template processing in `AdvancedPromptTransform` with `VariablePool`. - Make `system_variables` and `user_inputs` optional in `VariablePool` initialization.	2024-10-14 16:47:03 +08:00
-LAN-	885192db38	feat(podcast_generator): add new podcast generation tools ... - Introduced podcast generator with text-to-speech functionality using OpenAI's API. - Implemented credential validation for TTS services and API keys. - Added support for generating podcast audio with alternating host voices. - Included user-friendly setup with internationalized YAML configuration. - Added SVG icon to enhance visual identification.	2024-10-14 16:47:03 +08:00
-LAN-	ea18dd1571	feat(api): Enhance multi modal support.	2024-10-14 16:47:03 +08:00
twwu	84819ff220	Merge branch 'fix/refresh-token' into deploy/dev	2024-10-14 11:44:39 +08:00
非法操作	ffc3f33670	chore: remove the copied zhipu_ai sdk (#9270)	2024-10-14 10:53:45 +08:00
kurokobo	857055b797	fix: remove the latest message from the user that does not have any answer yet (#9297)	2024-10-13 23:25:50 +08:00
ice yao	d15ba3939d	Add Volcengine VikingDB as new vector provider (#9287)	2024-10-13 21:26:05 +08:00
zhuhao	d97d3ff5fc	chore: add abstract decorator and output log when query embedding fails (#9264)	2024-10-12 23:58:41 +08:00
Shili Cao	2ec6ffe478	feat:support baidu vector db (#9185)	2024-10-12 23:24:17 +08:00