a189d293f8
make logging not use f-str, change others to f-str ( #22882 )
2025-07-25 10:32:48 +08:00
27390adca6
Added a check to ensure the input text is a string before proceeding with parsing ( #22809 )
...
Co-authored-by: -LAN- <laipz8200@outlook.com >
2025-07-23 13:53:27 +08:00
60c37fe492
Added a check to ensure the input text is a string before proceeding with parsing ( #22809 )
...
Co-authored-by: -LAN- <laipz8200@outlook.com >
2025-07-23 13:53:27 +08:00
585f3635b9
feat: add support for dark icons in provider and tool entities ( #22081 )
2025-07-10 14:43:31 +08:00
94a13d7d62
feat: add support for dark icons in provider and tool entities ( #22081 )
2025-07-10 14:43:31 +08:00
8e6afbd87f
fix: The statistics page cannot display the tokens consumed by agent node ( #21861 )
2025-07-03 14:40:47 +08:00
f3c8625fe2
fix: The statistics page cannot display the tokens consumed by agent node ( #21861 )
2025-07-03 14:40:47 +08:00
160e70da34
refactor: move structured output support outside LLM Node ( #21565 )
...
Co-authored-by: Novice <novice12185727@gmail.com >
2025-06-27 14:55:31 +08:00
0cb00d5fd2
refactor: move structured output support outside LLM Node ( #21565 )
...
Co-authored-by: Novice <novice12185727@gmail.com >
2025-06-27 14:55:31 +08:00
e0944e9326
refactor: Improve model status handling and structured output ( #20586 )
...
Signed-off-by: -LAN- <laipz8200@outlook.com >
2025-06-04 19:56:54 +08:00
5ccfb1f4ba
refactor: Improve model status handling and structured output ( #20586 )
...
Signed-off-by: -LAN- <laipz8200@outlook.com >
2025-06-04 19:56:54 +08:00
f2d4916ad6
refactor: Removes unused LLMMode value_of method ( #20575 )
...
Signed-off-by: -LAN- <laipz8200@outlook.com >
2025-06-03 16:36:10 +08:00
257bf13fef
refactor: Removes unused LLMMode value_of method ( #20575 )
...
Signed-off-by: -LAN- <laipz8200@outlook.com >
2025-06-03 16:36:10 +08:00
879986dcba
fix: drop some type fixme ( #20344 )
2025-05-30 14:10:09 +08:00
5a991295e0
fix: drop some type fixme ( #20344 )
2025-05-30 14:10:09 +08:00
a1ffe78fc7
feat(api): Add image multimodal support for LLMNode ( #17372 )
...
Enhance `LLMNode` with multimodal capability, introducing support for
image outputs.
This implementation extracts base64-encoded images from LLM responses,
saves them to the storage service, and records the file metadata in the
`ToolFile` table. In conversations, these images are rendered as
markdown-based inline images.
Additionally, the images are included in the LLMNode's output as
file variables, enabling subsequent nodes in the workflow to utilize them.
To integrate file outputs into workflows, adjustments to the frontend code
are necessary.
For multimodal output functionality, updates to related model configurations
are required. Currently, this capability has been applied exclusively to
Google's Gemini models.
Close #15814 .
Signed-off-by: -LAN- <laipz8200@outlook.com >
Co-authored-by: -LAN- <laipz8200@outlook.com >
2025-04-30 17:28:02 +08:00
349c3cf7b8
feat(api): Add image multimodal support for LLMNode ( #17372 )
...
Enhance `LLMNode` with multimodal capability, introducing support for
image outputs.
This implementation extracts base64-encoded images from LLM responses,
saves them to the storage service, and records the file metadata in the
`ToolFile` table. In conversations, these images are rendered as
markdown-based inline images.
Additionally, the images are included in the LLMNode's output as
file variables, enabling subsequent nodes in the workflow to utilize them.
To integrate file outputs into workflows, adjustments to the frontend code
are necessary.
For multimodal output functionality, updates to related model configurations
are required. Currently, this capability has been applied exclusively to
Google's Gemini models.
Close #15814 .
Signed-off-by: -LAN- <laipz8200@outlook.com >
Co-authored-by: -LAN- <laipz8200@outlook.com >
2025-04-30 17:28:02 +08:00
af7a907960
immediately return initialed tiktokenizer instance and remove dead code in usage of tiktokenizer ( #17957 )
2025-04-30 16:07:20 +08:00
12c96b93d9
immediately return initialed tiktokenizer instance and remove dead code in usage of tiktokenizer ( #17957 )
2025-04-30 16:07:20 +08:00
487b107e6f
Enhance Code Consistency Across Repository with .editorconfig ( #19023 )
2025-04-29 18:04:33 +08:00
bd1bbfee4b
Enhance Code Consistency Across Repository with .editorconfig ( #19023 )
2025-04-29 18:04:33 +08:00
63802d8104
refactor: rename plugin manager to plugin client and rename path from manager to impl ( #18876 )
2025-04-27 14:22:25 +08:00
abafa68647
refactor: rename plugin manager to plugin client and rename path from manager to impl ( #18876 )
2025-04-27 14:22:25 +08:00
84b076bf93
fix: LLMResultChunk cause concatenate str and list exception ( #18852 )
2025-04-27 11:32:14 +08:00
c1559a7c8e
fix: LLMResultChunk cause concatenate str and list exception ( #18852 )
2025-04-27 11:32:14 +08:00
cabcaf7439
fix : #18744 The model order defined in position.yaml in the Model Plugin is not taking effect. ( #18756 )
2025-04-25 16:45:48 +08:00
9bcc8041e9
fix : #18744 The model order defined in position.yaml in the Model Plugin is not taking effect. ( #18756 )
2025-04-25 16:45:48 +08:00
8ebdd4649c
fix: Update prompt message content types to use Literal and add union type for content ( #17136 )
...
Co-authored-by: 朱庆超 <zhuqingchao@xiaomi.com >
Co-authored-by: crazywoola <427733928@qq.com >
2025-04-22 16:17:55 +08:00
a1158cc946
fix: Update prompt message content types to use Literal and add union type for content ( #17136 )
...
Co-authored-by: 朱庆超 <zhuqingchao@xiaomi.com >
Co-authored-by: crazywoola <427733928@qq.com >
2025-04-22 16:17:55 +08:00
e31c98eea3
fix(promptMessage): correct field_serializer implementation for content serialization ( #18458 )
2025-04-21 15:09:49 +08:00
f191d372f0
fix(promptMessage): correct field_serializer implementation for content serialization ( #18458 )
2025-04-21 15:09:49 +08:00
2eb79ef233
feat: structured output ( #17877 )
2025-04-18 16:33:53 +08:00
da9269ca97
feat: structured output ( #17877 )
2025-04-18 16:33:53 +08:00
491a1beed3
fix: invalid new tool call creation logic during response handling in OAI-Compat model ( #17781 )
2025-04-17 16:52:49 +08:00
defd5520ea
fix: invalid new tool call creation logic during response handling in OAI-Compat model ( #17781 )
2025-04-17 16:52:49 +08:00
93eef1625f
feat: re-add prompt messages to result and chunks in llm ( #17883 )
...
Signed-off-by: -LAN- <laipz8200@outlook.com >
2025-04-11 17:04:49 +08:00
8e6f6d64a4
feat: re-add prompt messages to result and chunks in llm ( #17883 )
...
Signed-off-by: -LAN- <laipz8200@outlook.com >
2025-04-11 17:04:49 +08:00
27edcb6e7c
fix: autocorrect everything in api ( #17859 )
...
Signed-off-by: yihong0618 <zouzou0208@gmail.com >
2025-04-11 15:24:39 +08:00
f04d52c044
fix: autocorrect everything in api ( #17859 )
...
Signed-off-by: yihong0618 <zouzou0208@gmail.com >
2025-04-11 15:24:39 +08:00
bf11af4e04
feat(large_language_model): Adds plugin-based token counting configuration option ( #17706 )
...
Signed-off-by: -LAN- <laipz8200@outlook.com >
Co-authored-by: Yeuoly <admin@srmxy.cn >
2025-04-09 20:52:58 +08:00
d3157b46ee
feat(large_language_model): Adds plugin-based token counting configuration option ( #17706 )
...
Signed-off-by: -LAN- <laipz8200@outlook.com >
Co-authored-by: Yeuoly <admin@srmxy.cn >
2025-04-09 20:52:58 +08:00
73e81323fc
合并dify1.2.0版本代码
...
# Conflicts:
# api/controllers/service_api/app/workflow.py
# api/controllers/service_api/wraps.py
# web/.env.example
# web/app/components/share/utils.ts
# web/app/signin/page.module.css
# web/context/debug-configuration.ts
2025-04-09 19:57:08 +08:00
44f911a0a8
chore: docstring not match the function parameter ( #17162 )
2025-03-31 13:19:15 +08:00
81dbfd6748
feat: 合并dify1.1.3版本
...
# Conflicts:
# README.md
# api/.env.example
# api/controllers/console/__init__.py
# api/controllers/console/apikey.py
# api/controllers/console/explore/completion.py
# api/controllers/console/explore/workflow.py
# api/controllers/service_api/app/workflow.py
# api/controllers/service_api/wraps.py
# api/controllers/web/workflow.py
# api/core/model_runtime/model_providers/bedrock/get_bedrock_client.py
# api/core/model_runtime/model_providers/bedrock/llm/llm.py
# api/core/model_runtime/model_providers/openai_api_compatible/openai_api_compatible.yaml
# api/core/model_runtime/model_providers/openai_api_compatible/text_embedding/text_embedding.py
# api/models/model.py
# api/poetry.lock
# api/pyproject.toml
# web/.env.example
# web/Dockerfile
# web/app/(commonLayout)/app/(appDetailLayout)/[appId]/layout.tsx
# web/app/components/app/overview/appCard.tsx
# web/app/components/base/chat/chat-with-history/chat-wrapper.tsx
# web/app/components/base/chat/embedded-chatbot/index.tsx
# web/app/components/base/mermaid/index.tsx
# web/app/components/develop/index.tsx
# web/app/components/develop/secret-key/secret-key-modal.tsx
# web/app/components/explore/app-list/index.tsx
# web/app/components/explore/item-operation/index.tsx
# web/app/components/explore/sidebar/app-nav-item/index.tsx
# web/app/components/explore/sidebar/index.tsx
# web/app/components/header/account-setting/index.tsx
# web/app/components/header/index.tsx
# web/app/components/share/text-generation/index.tsx
# web/app/components/tools/provider/detail.tsx
# web/app/layout.tsx
# web/package.json
# web/service/base.ts
# web/yarn.lock
2025-03-28 16:35:13 +08:00
b5aa970766
feat: 新增sandbox-full支持
2025-03-28 15:18:33 +08:00
8047d08b3b
chore: remove third party models ( #13885 )
2025-03-27 10:22:32 +08:00
a30945312a
fix: typos ( #16385 )
2025-03-21 11:14:40 +08:00
963b6f628a
Chore: PromptMessage is not an abstract base class ( #15965 )
2025-03-18 10:57:52 +08:00
037f200527
fix: invoke_error is not callable ( #15555 )
...
Co-authored-by: 刘江波 <jiangbo721@163.com >
2025-03-12 10:58:44 +08:00
4668c4996a
feat: Add caching mechanism for plugin model schemas ( #14898 )
2025-03-04 18:02:06 +08:00
Asuka Minato