opensource
/
dify
mirror of https://github.com/langgenius/dify.git
2
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
4,404 Commits 315 Branches 162 Tags 666 MiB
Commit Graph

1904 Commits

Author SHA1 Message Date
Jiang 0d04cdc323
Lindorm vdb (#11574) 
Co-authored-by: jiangzhijie <jiangzhijie.jzj@alibaba-inc.com>
 2024-12-12 09:43:27 +08:00
非法操作 926f604f09
feat: add gemini-2.0-flash-exp (#11570) 2024-12-12 09:33:39 +08:00
liuzhenghua d05f189049
Fix: RateLimit requests were not released when a streaming generation exception occurred (#11540) 2024-12-11 19:16:35 +08:00
Novice 1765fe2a29
fix: iteration node in parallel mode token count error (#11539) 
Co-authored-by: Novice Lee <novicelee@NoviPro.local>
 2024-12-11 14:23:01 +08:00
Novice 79a710ce98
Feat: continue on error (#11458) 
Co-authored-by: Novice Lee <novicelee@NovicedeMacBook-Pro.local>
Co-authored-by: Novice Lee <novicelee@NoviPro.local>
 2024-12-11 14:22:42 +08:00
Tommy 42d986b96d
[Pixtral] Add new model ; add vision (#11231) 2024-12-11 10:14:16 +08:00
zkyTech fbc4ca980c
fix: Remove duplicate 'response_format' parameter from model YAML files (#11531) 
Co-authored-by: zhangkunyuan <zhangkunyuan@cmhi.chinamobile.com>
 2024-12-11 10:10:53 +08:00
Paul van Oorschot 80c52e0ea4
feat: Add llama-3.3 models for Groq (#11533) 2024-12-11 09:59:46 +08:00
yihong 225fcd5e41
Revert "fix: total tokens is wrong which is zero in inter way, close … (#11536) 2024-12-11 09:54:46 +08:00
yihong 716576043d
fix: issue 11247 that Completion mode content maybe list or str (#11504) 
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
 2024-12-10 23:22:14 +08:00
Wei Mingzhi 28231d39a4
Remove the processing of single quote when testing API tools. (#11390) 2024-12-10 19:53:38 +08:00
非法操作 9e23c3d625
chore: LOCAL_FILE also try to use remote_url as Prompt message (#11443) 2024-12-10 10:56:49 +08:00
-LAN- fd354d999d
fix(app_generator_service): overload type hints (#11507) 
Signed-off-by: -LAN- <laipz8200@outlook.com>
 2024-12-10 09:06:34 +08:00
orangeclk ec00b25793
feat: add siliconflow qwq and llama3.3 model (#11492) 2024-12-10 08:49:45 +08:00
Yingchun Lai 32f8439143
fix: add the missing abab6.5t-chat model of Minimax (#11484) 2024-12-09 17:59:20 +08:00
-LAN- 537068cfde
refactor(iteration_node): use Sequence and Mapping in parameters (#11483) 
Signed-off-by: -LAN- <laipz8200@outlook.com>
 2024-12-09 15:41:20 +08:00
suzuki.sh c3c6a48059
Fix the token count at the iteration node (#11235) 
Co-authored-by: -LAN- <laipz8200@outlook.com>
 2024-12-09 15:02:04 +08:00
Kazuki Takamatsu 4d7cfd0de5
Fix model provider of vertex ai (#11437) 2024-12-08 08:44:49 +08:00
非法操作 7e1184c071
feat: support json_schema for ollama models (#11449) 2024-12-08 08:36:12 +08:00
非法操作 1ce51e57ab
feat: add gemini exp 1206 (#11444) 2024-12-07 22:28:10 +08:00
非法操作 142b4fd699
feat: add zhipu glm_4v_flash (#11440) 2024-12-07 22:27:57 +08:00
yihong d9d5d35a77
fix: issue #10596 by making the iteration node outputs right (#11394) 
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
Signed-off-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: -LAN- <laipz8200@outlook.com>
 2024-12-07 16:28:15 +08:00
Huỳnh Gia Bôi 9277156b6c
fix(document_extractor): pptx file type and missing metadata_filename UnstructuredIO (#11364) 
Co-authored-by: Julian Huynh <julian.huynh@immersio.io>
 2024-12-06 18:55:59 +08:00
Jyong 9b7adcd4d9
update tidb batch get endpoint to basic mode (#11426) 2024-12-06 17:06:46 +08:00
Jyong a8d32f9964
fix external retrieval without segment id (#11423) 2024-12-06 14:45:15 +08:00
shirochan 5093337de1
FEAT: cohere rerank 3.5 model added (#11289) 2024-12-06 09:58:55 +08:00
Matsuda f54225568c
fix(model_runtime): add vision to Amazon Nova Lite and Pro (#11398) 2024-12-06 09:15:32 +08:00
Warren Chen 631cbcd781
[fix] rename yaml files to fit windows (#11379) 2024-12-05 14:38:12 +08:00
yihong 5669cac16d
fix: some typos using typos (#11374) 
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
 2024-12-05 13:24:06 +08:00
Warren Chen 376726cf90
[feat] Add AWS Bedrock rerank (#11349) 
Co-authored-by: crazywoola <427733928@qq.com>
 2024-12-05 11:31:43 +08:00
Akira Noda eca466bdaa
chore: fix typo (#11359) 2024-12-05 09:04:30 +08:00
crazywoola d56abec195
Revert "Fix: iteration not in main thread pool" (#11358) 2024-12-04 21:22:22 +08:00
yihong 961e25f608
fix: better bedrock message handler close #10976 (#11317) 
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
 2024-12-04 19:46:40 +08:00
ybalbert001 1bae9b8ff7
update pricing for bedrock nova LLM models (#11336) 
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
 2024-12-04 16:16:41 +08:00
Jyong d7c1f43b49
fix tidb full-text-search vector missed (#11337) 2024-12-04 16:13:23 +08:00
非法操作 91e1ff5e30
chore: improve zhipu LLM (#11321) 2024-12-04 15:14:30 +08:00
ybalbert001 5908e10549
integrate amazon nove llms to dify (#11324) 
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
 2024-12-04 15:13:08 +08:00
-LAN- 464e6354c5
feat: correct the prompt grammar. (#11328) 
Signed-off-by: -LAN- <laipz8200@outlook.com>
 2024-12-04 15:12:47 +08:00
非法操作 d470e55f8c
fix: http node download file always image type (#11319) 2024-12-04 12:15:26 +08:00
Jyong c58d2fce89
roll back rerank topn setting (#11297) 2024-12-03 17:34:56 +08:00
yihong e39e776d03
fix: better wenxin rerank handler, close #11252 (#11283) 
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
 2024-12-03 13:57:16 +08:00
Yi Xiao e135ffc2c1
Feat: upgrade variable assigner (#11285) 
Signed-off-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: -LAN- <laipz8200@outlook.com>
 2024-12-03 13:56:40 +08:00
Bowen Liang e79eac688a
chore(lint): sort __all__ definitions (#11243) 2024-12-03 13:26:33 +08:00
-LAN- 643a90c48d
fix: use `removeprefix()` instead of `lstrip()` to remove the `data:` prefix (#11272) 
Signed-off-by: -LAN- <laipz8200@outlook.com>
 2024-12-03 09:16:25 +08:00
Novice 2a448a899d
Fix: iteration not in main thread pool (#11271) 
Co-authored-by: Novice Lee <novicelee@NovicedeMacBook-Pro.local>
 2024-12-03 09:16:03 +08:00
yihong e686f12317
fix: better handle error (#11265) 
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
 2024-12-03 09:15:38 +08:00
Hash Brown c4fad66f2a
fix: `dialogue_count` incorrect in chatflow when there's... (#11175) 2024-12-02 16:09:26 +08:00
yihong 02572e8cca
fix: claude can not handle empty string (#11238) 
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
 2024-12-02 16:00:40 +08:00
-LAN- f8c966c39c
fix(workflow_tool): Rename `stream` to `streaming` (#11258) 
Signed-off-by: -LAN- <laipz8200@outlook.com>
 2024-12-02 15:00:26 +08:00
-LAN- 3c8efe7c0a
fix(workflow_cycle_manage): Handle special values in the process_data. (#11253) 
Signed-off-by: -LAN- <laipz8200@outlook.com>
 2024-12-02 13:53:43 +08:00
yihong 239bf97b47
fix: nvidia special embedding model payload close #11193 (#11239) 
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
 2024-12-02 10:25:15 +08:00
-LAN- c34bdb74e6
Fix/type-error (#11240) 
Signed-off-by: -LAN- <laipz8200@outlook.com>
 2024-12-02 10:24:21 +08:00
-LAN- 9601102885
fix(word_extractor): Fix type error and remove stream in ssrf_proxy (#11241) 
Signed-off-by: -LAN- <laipz8200@outlook.com>
 2024-12-02 10:24:03 +08:00
yihong fd4be36991
fix: total tokens is wrong which is zero in inter way, close #11221 (#11224) 
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
 2024-11-30 23:18:24 +08:00
Shota Totsuka 594666eb61
fix: use Gemini response metadata for token counting (#11226) 2024-11-30 17:30:55 +08:00
朱晓兵 e80f41a701
fix: support setting variables in url (#10676) 2024-11-30 11:15:17 +08:00
Cling_o3 f9c2aa7689
feat: add retireval_top_n to config in env (#11132) 2024-11-30 11:14:45 +08:00
yihong 5a9b785773
fix: excel in node only read one sheet, close #9661 (#11215) 
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
 2024-11-30 11:11:08 +08:00
catusax d96a28487a
fix: 'validation error for ToolInvokeMessage' when blob_message meta is None (#11212) 2024-11-29 17:35:13 +08:00
liujiamingtiny 6f9ce6a199
fix: fix azure open-4o-08-06 when enable json schema cant process content = "" (#11204) 
Co-authored-by: jiaming.liu <jiaming.liu@zkh.com>
 2024-11-29 17:26:07 +08:00
ybalbert001 cc0b92bc75
Update aws tools (#11174) 
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
 2024-11-29 09:28:28 +08:00
kazuya-awano 2d6865d421
Ensure consistent float type for cached embedding return values (#10185) 2024-11-29 09:18:41 +08:00
yihong d7160ee563
fix: typo in upstashVector if id is always true, also fix some type hint (#11183) 
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
 2024-11-28 14:05:25 +08:00
yihong 40fc6f529e
fix: gitee ai wrong default model, and better para (#11168) 
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
 2024-11-27 17:27:11 +08:00
Hiroshi Fujita a918cea2fe
feat: add VTT file support to Document Extractor (#11148) 2024-11-27 11:42:42 +08:00
-LAN- 9789905a1f
chore(*): Removes debugging print statements (#11145) 
Signed-off-by: -LAN- <laipz8200@outlook.com>
 2024-11-26 22:03:19 +08:00
Charlie.Wei f458580dee
fix parameter extractor function call Expected str (#11142) 2024-11-26 21:46:56 +08:00
-LAN- 223a30401c
fix: LLM invoke error should not be raised (#11141) 
Signed-off-by: -LAN- <laipz8200@outlook.com>
 2024-11-26 20:56:48 +08:00
Tao Wang aa135a3780
Add TTS to OpenAI_API_Compatible (#11071) 2024-11-26 15:14:02 +08:00
-LAN- 044e7b63c2
fix(llm_node): Ignore file if not supported. (#11114) 2024-11-26 14:14:14 +08:00
-LAN- 5b7b328193
feat: Allow to contains files in the system prompt even model not support. (#11111) 2024-11-26 13:45:49 +08:00
-LAN- 8d5a1be227
fix: Cannot use files in the user inputs. (#11112) 2024-11-26 13:43:38 +08:00
-LAN- 1db14793fa
fix(anthropic_llm): Ignore non-text parts in the system prompt. (#11107) 2024-11-26 13:31:40 +08:00
-LAN- cbb4e95928
fix(llm_node): Ignore user query when memory is disabled. (#11106) 2024-11-26 13:07:32 +08:00
-LAN- 20c091a5e7
fix: user query be ignored if query_prompt_template is an empty string (#11103) 2024-11-26 12:47:59 +08:00
horochx 9f75970347
fix: ops_trace_manager `from_end_user_id` (#11077) 2024-11-26 10:29:00 +08:00
SebastjanPrachovskij 17ee731546
SearchApi - Return error message instead of raising a ValueError (#11083) 2024-11-26 09:34:51 +08:00
Tao Wang af2461cccc
Add query_prefix + Return TED Transcript URL for Downstream Scraping Tasks (#11090) 2024-11-26 09:32:37 +08:00
fengjiajie ab6dcf7032
fix: update the max tokens configuration for Azure GPT-4o (2024-08-06) to 16384 (#11074) 2024-11-25 21:13:02 +08:00
yihong 8aae235a71
fix: int None will cause error for context size (#11055) 
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
 2024-11-25 21:04:16 +08:00
Tao Wang 1065917872
Add grok-vision-beta to xAI + Update grok-beta Features (#11004) 2024-11-25 20:53:03 +08:00
非法操作 56e361ac44
fix: chart tool chinese font display and raise error (#11058) 2024-11-25 19:50:33 +08:00
yihong 2e00829b1e
fix: drop useless and wrong code for zhipu embedding (#11069) 
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
 2024-11-25 19:50:23 +08:00
-LAN- 98d85e6b74
fix: WorkflowNodeExecution.created_at may be earlier than WorkflowRun.created_at (#11070) 2024-11-25 18:16:55 +08:00
Pedro Gomes 319d49084b
fix: ignore empty outputs in Tool node (#10988) 2024-11-25 18:00:42 +08:00
-LAN- 3eb51d85da
fix(workflow_entry): Support receive File and FileList in single step run. (#10947) 
Signed-off-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: JzoNg <jzongcode@gmail.com>
 2024-11-25 12:46:50 +08:00
Kalo Chin 684f6b2299
fix: slidespeak text output is not the download link (#10997) 2024-11-25 11:28:52 +08:00
SiliconFlow, Inc a4fc057a1c
ISSUE=11042: add tts model in siliconflow (#11043) 2024-11-25 11:04:13 +08:00
Tao Wang aae29e72ae
Fix Deepseek Function/Tool Calling (#11023) 2024-11-25 11:03:53 +08:00
cyflhn 87c831e5dd
make tool parameters parsing compatible with the response of glm4 model in xinference provider when function tool call integerated (#11049) 2024-11-25 11:02:58 +08:00
-LAN- 60b5dac3ab
fix: query will be None if the query_prompt_template not exists (#11031) 
Signed-off-by: -LAN- <laipz8200@outlook.com>
 2024-11-24 21:06:51 +08:00
cyflhn 03ba4bc760
fix error with xinference tool calling with qwen2-instruct and add timeout retry setttings for xinference (#11012) 
Co-authored-by: crazywoola <427733928@qq.com>
 2024-11-24 15:29:30 +08:00
litterGuy ae3a2cb272
fix: json parse err when http node send request (#11001) 2024-11-24 14:19:48 +08:00
Bowen Liang 6c8e208ef3
chore: bump minimum supported Python version to 3.11 (#10386) 2024-11-24 13:28:46 +08:00
yihong 0181f1c08c
fix: wrong convert in PromptTemplateConfigManager (#11016) 
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
 2024-11-24 12:18:19 +08:00
yihong 7f00c5a02e
fix: uuid not import bug (#11014) 
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
 2024-11-24 11:17:55 +08:00
kenwoodjw 096c0ad564
feat: Add support for TEI API key authentication (#11006) 
Signed-off-by: kenwoodjw <blackxin55+@gmail.com>
Co-authored-by: crazywoola <427733928@qq.com>
 2024-11-23 23:55:35 +08:00
Kazuhisa Wada 16c41585e1
Fixing #11005: Incorrect max_tokens in yaml file for AWS Bedrock US Cross Region Inference version of 3.5 Sonnet v2 and 3.5 Haiku (#11013) 2024-11-23 23:46:25 +08:00
AkisAya 566ab9261d
fix: gitlab file url not correctly encoded (#10996) 2024-11-23 23:44:17 +08:00
yihong 448a19bf54
fix: fish audio wrong validate credentials interface (#11019) 
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
 2024-11-23 23:39:41 +08:00