Releases · langgenius/dify

26 Jan 07:02

takatost

0.5.2

4ab6629

v0.5.2

Add OpenAI gpt-4-turbo-preview, gpt-4-0125-preview, text-embedding-3-large, text-embedding-3-small Models
Chunk overlap supported in Knowledge
Fix some problems

Update Guide

Deploying with Docker Compose:

Get the latest code from the main branch:
```
git checkout main
git pull origin main
```
Go to the next step and update to the latest image:
```
cd docker
docker-compose up -d
```

Deploying from Source Code:

Stop API server, Worker and Web frontend Server.
Get the latest code from the main branch:
```
git checkout main
git pull origin main
```
Then, let's run the migration script:
```
cd api
flask db upgrade
```
Note: To use TTS, ffmpeg installation is required on servers running Dify API from source. More details can be found in our FAQ.
Finally, run API server, Worker and Web frontend Server again.

What's Changed

Add new OpenAI embedding models by @guchenhe in #2217
fix: remove and create app not reload plan by @iamjoel in #2220
fix: tts model tip by @ashening in #2221
fix: multiple rows were found correctly by @crazywoola in #2219
chore: no custom tool placeholder ui by @iamjoel in #2222
Update EditCustomCollectionModal button styling for Chinese by @BenjaminX in #2225
Maintenance notice href by @charli117 in #2227
Feat: chunk overlap supported by @JzoNgKVO in #2209
add openai gpt-4-0125-preview by @Yeuoly in #2226
version to 0.5.2 by @takatost in #2230

New Contributors

@ashening made their first contribution in #2221

Full Changelog: 0.5.1...0.5.2

Contributors

BenjaminX, iamjoel, and 7 other contributors

Assets 2

25 Jan 19:16

takatost

0.5.1

c038040

v0.5.1

add multiple LLM debug mode ⚔️
let citation show on webapp
add tongyi tts
minimax abab6-chat LLM supported
support Annotations output
openai_api_compatible support config stream_mode_delimiter
fix some problems

Update Guide

Deploying with Docker Compose:

Get the latest code from the main branch:
```
git checkout main
git pull origin main
```
Go to the next step and update to the latest image:
```
cd docker
docker-compose up -d
```

Deploying from Source Code:

Stop API server, Worker and Web frontend Server.
Get the latest code from the main branch:
```
git checkout main
git pull origin main
```
Then, let's run the migration script:
```
cd api
flask db upgrade
```
Note: To use TTS, ffmpeg installation is required on servers running Dify API from source. More details can be found in our FAQ.
Finally, run API server, Worker and Web frontend Server again.

What's Changed

fix: transcript asr params wrong by @takatost in #2162
let citation show on webapp by @guchenhe in #2161
fix: empty usage by @Yeuoly in #2168
bump alpine from 3.18 to 3.19 in web image by @bowenliang123 in #2126
fix: credentials validate compatible problem by @takatost in #2170
fix: knowledge api doc by @zxhlyh in #2174
fix: filename cause windows import error by @crazywoola in #2176
feat: utm supports. by @GarfieldDai in #2181
chore: utm by @zxhlyh in #2180
feat: add tool labels by @Yeuoly in #2178
refine: faster rsa implement by @Yeuoly in #2182
Add tongyi tts&tts function optimization by @charli117 in #2177
fix: credentials validation of ababa by @Yeuoly in #2183
feat: abab6-chat supported by @takatost in #2184
fix: minimax request timeout by @takatost in #2185
Doc/update readme by @crazywoola in #2186
Add tts document&fix bug by @charli117 in #2156
fix: utm by @zxhlyh in #2191
chore: remove universal chat code by @iamjoel in #2194
Support JSONL output by @JzoNgKVO in #2171
feat: multiple model configuration by @zxhlyh in #2196
improve api docker file and lock Debian version in base image tag by @bowenliang123 in #2195
fix: split chunks return empty strings by @takatost in #2197
skip installing python3-dev package on base stage in api docker image by @bowenliang123 in #2193
fix: chatbot support agent by @iamjoel in #2201
fix: typing delay by @zxhlyh in #2200
chore: test register ga by @iamjoel in #2202
Feat/zhipuai function calling by @Yeuoly in #2199
chore: enchance some use experience by @iamjoel in #2204
feat: create app show agent type tip by @iamjoel in #2207
fix: model parameter modal input by @zxhlyh in #2206
fix: sometimes app main content not fill the window by @iamjoel in #2208
fix:determine multiple result exceptions caused by admin by @IAMZn1018 in #2211
Update version to 0.5.1 by @takatost in #2213
feat: openai_api_compatible support config stream_mode_delimiter by @geosmart in #2190
Add gmpy2 dependencies packages by @takatost in #2216

New Contributors

@IAMZn1018 made their first contribution in #2211
@geosmart made their first contribution in #2190

Full Changelog: 0.5.0...0.5.1

Contributors

bowenliang123, iamjoel, and 10 other contributors

Assets 2

24 Jan 05:07

takatost

0.5.0

e0f72d2

v0.5.0

🎉🎉 Dify Version 0.5 Release Notes

We're excited to announce the release of Dify Version 0.5. This update introduces several major enhancements, including the integration of Agent mode, the implementation of text-to-speech (TTS) capabilities, and the introduction of the AWS Bedrock model provider. Additionally, we have incorporated GLM3/GLM4 models and Portuguese language support. Read on for more details 👇

What's New

Agent Mode Integration

The Assistant App (previously known as the Chat App) now features an Agent mode, providing access to 12 built-in tools including DALL-E, Stable Diffusion, WebScraper, WolframAlpha, Dify Knowledge, and more.

The integration of Agent reasoning and tool outputs with the Assistant's replies offers a fluid, intuitive user experience.

logo.design.final.mp4

Our expansion into text-to-image capabilities marks a significant step in our multimodal journey. This includes a shared file variable pool, facilitating image-to-image and image-to-text functionality across all tools.

Custom tool integration is now more accessible through:

APIs: OpenAI/Swagger and ChatGPT Plugin spec files are supported, with a UI form for API specification in development.
Extensions: A guide is provided for users to contribute their own tool business logic.

Additional Updates:

The "Build App" has been renamed "Studio", and the "Chat App" is now the "Assistant". Choose between "Basic Assistant" or "Agent Assistant" in the Assistant den.
"API Based Extension", previously under the Assistant, is now in the "Variables" module.
For ease of use, "Tools" has been relocated to the main product menu, centralizing customization, authorization, and management.
With the release of the Agent Assistant, the experimental feature 'Universal Chat in Explorer' has completed its mission! Now, you can directly create an Agent Assistant to achieve the same functions.

TTS Capabilities

Thanks to @charli117, new TTS models are now supported. Our model provider includes an interface for the OpenAI TTS model, and we welcome contributions to our TTS scheme here.

TTS features are available in-app under "Add Feature".

Easily convert text to speech playback.

Note: To use TTS, ffmpeg installation is required on servers running Dify API from source. More details can be found in our FAQ.

Additional Enhancements

We've introduced the AWS Bedrock model provider and expanded GLM3/GLM4 model support. Plus, Dify now supports Portuguese, broadening our language capabilities.

Update Guide

Deploying with Docker Compose:

Get the latest code from the main branch:
```
git checkout main
git pull origin main
```
Go to the next step and update to the latest image:
```
cd docker
docker-compose up -d
```

Deploying from Source Code:

Stop API server, Worker and Web frontend Server.
Get the latest code from the main branch:
```
git checkout main
git pull origin main
```
Then, let's run the migration script:
```
cd api
flask db upgrade
```

Note: To use TTS, ffmpeg installation is required on servers running Dify API from source. More details can be found in our FAQ.

Finally, run API server, Worker and Web frontend Server again.

Change Log

fix: arg missing when call method on_message_replace_func in output… by @takatost in #2106
fix: empty keywords moderation. by @GarfieldDai in #2108
chore: enchance view billing text by @iamjoel in #2109
feat: support legacy doc by @crazywoola in #2100
feat: support re-invite email. by @GarfieldDai in #2107
Init azure openai show quota by @charli117 in #2096
fix: invite email template languages constant var by @BenjaminX in #2111
Fix/2102 long dify app description throws backend exception by @crazywoola in #2112
Feat/2070 glm 4 and glm 3 turbo by @crazywoola in #2114
feat: add cohere llm and embedding by @takatost in #2115
Add bedrock by @guchenhe in #2119
feat: support GLM-4V by @Yeuoly in #2124
feat: bedrock reorder in provider list by @takatost in #2121
fix: recipt info by @zxhlyh in #2123
fix: bump lamejs from 1.2.0 to 1.2.1 by @bowenliang123 in #2122
fix annotation reply by @JohnJyong in #2127
fix: model-parameter-modal slider by @zxhlyh in #2135
feat: support assistant frontend by @iamjoel in #2139
Feat/assistant app by @Yeuoly in #2086
feat: remove universal chat app by @takatost in #2140
fix: agent strategy by @Yeuoly in #2141
Feat/portuguese support by @crazywoola in #2075
fix: None type in cot assistant app by @Yeuoly in #2142
Fix/assistant none type by @Yeuoly in #2143
Fix/assistant none type by @Yeuoly in #2145
tts models support by @charli117 in #2033
feat: add ffmpeg faq link in missing ffmpeg error by @takatost in #2146
Fix/language support by @crazywoola in #2154
refractor: assistant runner rename by @rickythink in #2150
fix: Fix typo in credentials field name by @Yeuoly in #2155
fix: add tool index by @Yeuoly in #2152
Refactor: CoT runner by @Yeuoly in #2157
fix: embeded chat app input by @zxhlyh in #2159
fix: explore app add to workspace by @zxhlyh in #2160
version to 0.5.0. by @takatost in #2147

Full Changelog: 0.4.9...0.5.0

Contributors

BenjaminX, bowenliang123, and 10 other contributors

Assets 2

19 Jan 14:35

takatost

0.4.9

c7783db

v0.4.9

Fix some bugs

Notice

As per the planned schedule, these deprecated envs are being removed:

CONSOLE_URL: Replace with CONSOLE_API_URL and CONSOLE_WEB_URL.
APP_URL: Replace with APP_API_URL and APP_WEB_URL.
API_URL : Replace with SERVICE_API_URL.

More details: https://docs.dify.ai/getting-started/install-self-hosted/environments#console_api_url

Update Guide

Deploying with Docker Compose:

Get the latest code from the main branch:
```
git checkout main
git pull origin main
```
Go to the next step and update to the latest image:
```
cd docker
docker-compose up -d
```

Deploying from Source Code:

Stop API server, Worker and Web frontend Server.
Get the latest code from the main branch:
```
git checkout main
git pull origin main
```
Then, let's run the migration script:
```
cd api
flask db upgrade
```
Finally, run API server, Worker and Web frontend Server again.

What's Changed

feat: remove deprecated envs by @takatost in #2078
fix: version by @takatost in #2083
bump default NodeJS version to 20 LTS by @bowenliang123 in #2061
use redis to cache embeddings by @JohnJyong in #2085
fix notion estimate by @JohnJyong in #2090
fix: bypass admin users to use dataset api with API key by @bowenliang123 in #2072
add feature request copilot by @guchenhe in #2095
fix: yarn install command in web Dockerfile by @bowenliang123 in #2084
Add jina-embeddings-v2-base-de model configuration by @joshua20231026 in #2094
fix: saving error in empty dataset by @crazywoola in #2098
support setting timezone in docker images by @bowenliang123 in #2091
fix: skip linking /etc/localtime file first in api docker image by @bowenliang123 in #2099
delete document cache embedding by @JohnJyong in #2101
bump version to 0.4.9 by @takatost in #2103

Full Changelog: 0.4.8...0.4.9

Contributors

bowenliang123, takatost, and 4 other contributors

Assets 2

17 Jan 15:01

takatost

0.4.8

8654415

v0.4.8

Jina AI jina-embeddings-v2-base-zh model supported.
Minimax abab5.5s-chat model supported.
App OpenAPI add LLM usage return
Fix some problems.

Update Guide

Deploying with Docker Compose:

Get the latest code from the main branch:
```
git checkout main
git pull origin main
```
Go to the next step and update to the latest image:
```
cd docker
docker-compose up -d
```

Deploying from Source Code:

Stop API server, Worker and Web frontend Server.
Get the latest code from the main branch:
```
git checkout main
git pull origin main
```
Then, let's run the migration script:
```
cd api
flask db upgrade
```
Finally, run API server, Worker and Web frontend Server again.

What's Changed

fix qdrant tag in docker-compose.yaml by @takatost in #2047
fix: dataset sidebar by @zxhlyh in #2048
Add jina-embeddings-v2-base-zh model configuration by @rickythink in #2049
fix multi-dataset retrieve score limit by @JohnJyong in #2050
timeout parameter error by @JohnJyong in #2052
Update contribution guide by @guchenhe in #2053
fix indentation & move contact into community section by @guchenhe in #2055
Update README.md by @crazywoola in #2058
fix: add sharp package to fix sharp-missing-in-production warning by @bowenliang123 in #2060
Fix aspect ratio of buttons in readme by @guchenhe in #2062
feat: add abab5.5s-chat by @crazywoola in #2063
fix: free quota type apply button missing by @takatost in #2069
fix: azure customize model name duplicate by @takatost in #2073
feat: service api add llm usage by @takatost in #2051
bump version to 0.4.8 by @takatost in #2074

Full Changelog: 0.4.7...0.4.8

Contributors

bowenliang123, rickythink, and 5 other contributors

Assets 2

15 Jan 17:19

takatost

0.4.7

c51e179

v0.4.7

Fix some problems.

Update Guide

Deploying with Docker Compose:

Get the latest code from the main branch:
```
git checkout main
git pull origin main
```
Go to the next step and update to the latest image:
```
cd docker
docker-compose up -d
```

Deploying from Source Code:

Stop API server, Worker and Web frontend Server.
Get the latest code from the main branch:
```
git checkout main
git pull origin main
```
Then, let's run the migration script:
```
cd api
flask db upgrade
```
Finally, run API server, Worker and Web frontend Server again.

What's Changed

fix: chat log wont show up by @rickythink in #2007
fix: model provider credentials null value validate failed by @takatost in #2009
text spliter length method use default embedding model tokenizer by @JohnJyong in #2011
Update CONTRIBUTING.md by @WeepsDanky in #2010
fixup /stop api by @killpanda in #2012
fix: tongyi stream generate not incremental and add qwen max models by @takatost in #2013
feat: huggingface llm add new params. by @GarfieldDai in #2014
fix: datasets indexing-status api document by @vikeychen in #2019
fix: openai tool tokens by @Yeuoly in #2026
doc: replace readme images by @crazywoola in #2030
ascii filter Unicode U+FFFE by @JohnJyong in #2038
doc: replace readme images by @crazywoola in #2039
fix: dependencies security problems by @takatost in #2040
feat: fix debug rerank params error by @iamjoel in #2041
fix: dataset and moderation. by @GarfieldDai in #2042
fix SQL slow query by @JohnJyong in #2043
fix: qwen top_p min/max wrong by @takatost in #2044
bump version to 0.4.7 by @takatost in #2045

New Contributors

@WeepsDanky made their first contribution in #2010
@vikeychen made their first contribution in #2019

Full Changelog: 0.4.6...0.4.7

Contributors

killpanda, iamjoel, and 8 other contributors

Assets 2

12 Jan 04:51

takatost

0.4.6

9245f0a

v0.4.6

Support for Models Integration Provided by the Ollama, details: https://docs.dify.ai/advanced/model-configuration/ollama
Fix some problems.

What's Changed

chore: remove unused code by @crazywoola in #1989
feat: app sidebar support collapse by @zxhlyh in #1997
feat: make default slider behavior better by @crazywoola in #1988
optimize baichuan invalid key error by @Yeuoly in #1996
fix: azure openai stream response usage missing by @takatost in #1998
fix data_source_detail_dict parameter error by @JohnJyong in #2000
feat: ollama support by @takatost in #2003
improve: introduce isort for linting Python imports by @bowenliang123 in #1983
fix: model parameter default value by @zxhlyh in #2005
bump version to 0.4.6 by @takatost in #2006

Full Changelog: 0.4.5...0.4.6

Contributors

bowenliang123, takatost, and 4 other contributors

Assets 2

11 Jan 02:57

takatost

0.4.5

f7939c7

v0.4.5

Fix some BUGs.

What's Changed

correct xorbits spelling by @guchenhe in #1965
fix: cover missed source paths for eslint by @bowenliang123 in #1956
fix: update model list by @zxhlyh in #1967
improvement: introduce Super-Linter actions to check style for shell script, dockerfile and yaml files by @bowenliang123 in #1966
web: bump Next.js to 14.0 for faster local server startup by @bowenliang123 in #1925
enforce utf-8 encoding for provider response by @guchenhe in #1973
web: requires NodeJs 18.17 at minimum for NextJs 14 by @bowenliang123 in #1974
fix: indentation violations in YAML files by @bowenliang123 in #1972
Azure openai init by @charli117 in #1929
zhipu embedding token method by @JohnJyong in #1976
Fix hosting cloud version limit by @charli117 in #1975
fix: httpx socks package missing by @takatost in #1977
fix rerank issue when doing economy search by @JohnJyong in #1978
Update Resend SDK and resend api url in configuration. by @BenjaminX in #1963
Update Qdrant version by @JohnJyong in #1979
Escape capturing prices with dollar sign as math expressions by @guchenhe in #1985
fix get embedding model provider in empty dataset by @JohnJyong in #1986
fix: resend url optional by @takatost in #1987
fix: baichuan max chunks by @Yeuoly in #1990
fix: azure openai model parameters wrong when using hosting credentials by @takatost in #1993
feat: bump version 0.4.5 by @takatost in #1994

Full Changelog: 0.4.4...0.4.5

Contributors

BenjaminX, bowenliang123, and 6 other contributors

Assets 2

05 Jan 19:10

takatost

0.4.4

9f58912

v0.4.4

Add Together.ai model provider and fix some bugs.

What's Changed

feat: optimize memory & invoke error output by @takatost in #1931
fix: vision fail in complete app by @takatost in #1933
Feat/optimize entity construct by @takatost in #1935
feat: reuse decoding_rsa_key & decoding_cipher_rsa & optimize construct by @takatost in #1937
fix: llm result usage none by @takatost in #1940
fix: gpt-4-32k model name empty in OpenAI response by @takatost in #1941
fix: arg user required and must not be null in service generate api by @takatost in #1943
fix: text completion app cannot get data. by @GarfieldDai in #1942
fix: text-generation run batch by @zxhlyh in #1945
fix streaming by @guchenhe in #1944
Add Together.ai's OpenAI API-compatible inference endpoints by @guchenhe in #1947
feat: reorder togetherai by @takatost in #1951
change API key field to 'required' by @guchenhe in #1953
optimize qa prompt by @JohnJyong in #1957
prohibit enable and disable function when segment is not completed by @JohnJyong in #1954
delete remnant 'required': false by @guchenhe in #1955
fix: check result should be string. by @GarfieldDai in #1959
fix: generate not stop when pressing stop link by @takatost in #1961
bump version to 0.4.4 by @takatost in #1962

Full Changelog: 0.4.3...0.4.4

Contributors

takatost, guchenhe, and 3 other contributors

Assets 2

04 Jan 13:17

takatost

0.4.3

97c972f

v0.4.3

Optimize performance & fix few bugs.

What's Changed

fix: zhipuai chatglm turbo prompts must user, assistant in sequence by @takatost in #1899
fix: customize model schema fetch failed raise error by @takatost in #1900
Fix/add qdrant timeout default value by @JohnJyong in #1901
fix: remove useless code by @zxhlyh in #1903
fix: read file encoding error by @newsouther in #1902
fix: tongyi generate error by @takatost in #1904
fix: array oob in azure openai embeddings by @crazywoola in #1905
fix: spark credentials validate by @takatost in #1906
fix: notion_indexing_estimate embedding_model_instance NPE by @takatost in #1907
fix: window size changed causes result regeneration by @iamjoel in #1908
fix: model quota format by @zxhlyh in #1909
fix: remove useless code. by @GarfieldDai in #1913
ci: Properly cache pip packages by @bowenliang123 in #1912
web: Add style CI workflow to enforce eslint checks on web module by @bowenliang123 in #1910
fix customer spliter character by @JohnJyong in #1915
feat: model parameter prefefined by @zxhlyh in #1917
fix: email template style by @takatost in #1914
Fix comparison bug in ApplicationQueueManager by @waltcow in #1919
fix: app create raise error when no available model providers by @takatost in #1921
feat: optimize invoke errors by @takatost in #1922
alter schedule timedelta by @JohnJyong in #1923
fix a typo in file agent_app_runner.py by @liupeng0913 in #1927
fix: xinference cache by @Yeuoly in #1926
feat: optimize performance by @takatost in #1928
feat: bump version 0.4.3 by @takatost in #1930

New Contributors

@newsouther made their first contribution in #1902
@liupeng0913 made their first contribution in #1927

Full Changelog: 0.4.2...0.4.3

Contributors

bowenliang123, iamjoel, and 9 other contributors

Assets 2

Releases: langgenius/dify

v0.5.2

Update Guide

Deploying with Docker Compose:

Deploying from Source Code:

What's Changed

New Contributors

Contributors

v0.5.1

Update Guide

Deploying with Docker Compose:

Deploying from Source Code:

What's Changed

New Contributors

Contributors

v0.5.0

What's New

Agent Mode Integration

TTS Capabilities

Additional Enhancements

Update Guide

Deploying with Docker Compose:

Deploying from Source Code:

Change Log

Contributors

v0.4.9

Notice

Update Guide

Deploying with Docker Compose:

Deploying from Source Code:

What's Changed

Contributors

v0.4.8

Update Guide

Deploying with Docker Compose:

Deploying from Source Code:

What's Changed

Contributors

v0.4.7

Update Guide

Deploying with Docker Compose:

Deploying from Source Code:

What's Changed

New Contributors

Contributors

v0.4.6

What's Changed

Contributors

v0.4.5

What's Changed

Contributors

v0.4.4

What's Changed

Contributors

v0.4.3

What's Changed

New Contributors

Contributors