Releases: langgenius/dify
v0.5.4
- GPT-3.5-Turbo-0125 Integration
- Moonshot LLM Integration
- Add Bing Search Tool
- Add Built-in Maths Tool, a tool for evaluating an math expression, calculated locally with NumExpr.
- Enhanced Custom Tool Response Visibility, which allows users to view detailed custom API responses during testing, facilitating better debugging and integration.
- 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
- feat:add gpt-3.5-turbo-0125 by @leslie2046 in #2347
- Refactor error handling in GenerateTaskPipeline class by @limboinf in #2345
- fix [baichuan] Error: argument of type 'NoneType' is not iterable by @baiyansong in #2351
- Feat/move tenant id into db by @crazywoola in #2341
- fix: frontend security risk by @iamjoel in #2355
- add gpt-3.5-turbo-0125 to trail llm list by @takatost in #2354
- fix: unsafe external link by @iamjoel in #2356
- fix: input not set min or max null value blur would set null by @iamjoel in #2361
- fix: switch tenant by @crazywoola in #2363
- chore: replace chat in web app by @zxhlyh in #2373
- fix: webapp stop chat & citation by @zxhlyh in #2376
- fix variable invalid when key only one character by @takatost in #2377
- fix: webapp language by @zxhlyh in #2378
- feat: bing search by @Yeuoly in #2375
- fix: bad xinference error by @Yeuoly in #2384
- Feat/add bing search by @Yeuoly in #2379
- feat: tool credentials cache and introduce _position.yaml by @Yeuoly in #2386
- chore: enchange pic uploading tip by @zxhlyh in #2388
- fix: knowledge doc by @zxhlyh in #2389
- feat: add openai paid llm model. by @GarfieldDai in #2392
- fix: error stop response api url in text generation and uniform url by @iamjoel in #2394
- chore: show credit help link by @iamjoel in #2393
- fix: missing variables in agent prompt by @Yeuoly in #2395
- fix:add translation for dataset knowledge and update document title by @BenjaminX in #2396
- add built-in maths tool for local expression evaluation on NumExpr by @bowenliang123 in #2390
- Feat/show detailed custom api response when testing by @Yeuoly in #2400
- feat: add moonshot support by @jialeicui in #2398
- fix:update document title in Apps component by @BenjaminX in #2404
- fix: error type get wrong by @takatost in #2403
- enhancement: introduce Ruff for Python linter for reordering and removing unused imports with automated pre-commit and sytle check by @bowenliang123 in #2366
- fix: webapp variable input & app unavailable status by @zxhlyh in #2405
- fix: moonshot context size error by @takatost in #2406
- version to 0.5.4 by @takatost in #2407
New Contributors
- @limboinf made their first contribution in #2345
- @baiyansong made their first contribution in #2351
- @jialeicui made their first contribution in #2398
Full Changelog: 0.5.3...0.5.4
v0.5.3
- Support function calling for more models (Azure OpenAI, xinference, ZhipuAI, Minimax)
- 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: occasional multiple responses displayed in frontend due to unexpected message_id from onData by @rickythink in #2231
- feat: prompt IDE support change height by @iamjoel in #2232
- Fix/update broken doc links by @guchenhe in #2187
- Maintenance notice href by @charli117 in #2228
- fix:Bedrock llm issue #2214 by @glayyiyi in #2215
- chore: move register ga to signin page by @iamjoel in #2233
- fix: register ga id error by @iamjoel in #2237
- fix: vision config by @zxhlyh in #2235
- feat: team admin can pay billing by @iamjoel in #2240
- Feat/billing enhancement by @GarfieldDai in #2239
- Maintenance notice href by @charli117 in #2234
- fix: Resolved the issue of duplicate display of supported file types during text file upload by @huangbaichao in #2241
- fix typo by @guchenhe in #2248
- fix: remove invalid parameter return_type by @crazywoola in #2253
- fix: user handling in stop api by @takatost in #2254
- Bugfix/invitemailmultilangs by @BenjaminX in #2257
- update qdrant migrate command by @JohnJyong in #2260
- fix: initial paragraph can not input more than 48 chars by @crazywoola in #2258
- fix: stop generate api doc error by @iamjoel in #2262
- chore: change expert mode the same line height as automatic by @iamjoel in #2263
- feat: Nodejs sdk support auto rename conversation api by @iamjoel in #2265
- chore: update price page by @iamjoel in #2272
- Feat/utm update by @GarfieldDai in #2269
- fix: missing keys language in parser by @crazywoola in #2271
- use pm2 to guard and monitor the web service in docker file by @bowenliang123 in #2238
- fix: remove finish_reason condition logic when deltaContent is empty by @geosmart in #2270
- fix: typo of builtin tools by @bowenliang123 in #2275
- Add custom tools by @charli117 in #2259
- Feat/add azure dalle tool by @leslie2046 in #2276
- fix: setting default model to gpt-3.5-turbo-1106 and remove default m… by @Yeuoly in #2274
- bump flask from 2.3 to 3.0 by @bowenliang123 in #2279
- feat: some unused command-line tasks were removed. by @takatost in #2281
- chore: handle app name and options too long by @iamjoel in #2283
- feat: optimize tool name by @takatost in #2284
- Feat/blocking function call by @Yeuoly in #2247
- feat: file icon support doc and docx by @iamjoel in #2289
- fix: multiple model configuration clear conversation by rerender by @zxhlyh in #2286
- fix: missing files by @iamjoel in #2291
- Add custom tools by @charli117 in #2292
- remove repositories tool by @Yeuoly in #2293
- fix: missing prompt by @Yeuoly in #2294
- fix: keep original tool credentials by @Yeuoly in #2288
- Add custom tools by @charli117 in #2299
- Feat: Add Top bar while routing different different pages by @Yash-1511 in #2298
- fix: api tool encoding by @Yeuoly in #2296
- chore:azure dalle tool support pt-BR text by @leslie2046 in #2301
- feat: recommended apps list support sort by position by @iamjoel in #2303
- feat: ui improvements for Portuguese by @crazywoola in #2304
- Fix/typos by @rickythink in #2308
- fix: next public edition default value by @zxhlyh in #2310
- fix: invalid server tool url caused crash by @iamjoel in #2311
- chore: detect is function calling from model config by @iamjoel in #2312
- remove unused session store codes by @takatost in #2313
- Feat/add spark3.5 llm by @leslie2046 in #2314
- Change ZHIPU_MAX_LIMITS to 5. Fix issue 2323 by @orangeclk in #2324
- Fix/api tool by @Yeuoly in #2317
- Optimization stable diffusion verify by @charli117 in #2322
- revert: remove unused session store codes by @takatost in #2329
- fix: typo by @Yeuoly in #2318
- fix: empty model features by @Yeuoly in #2330
- feat: add sd model parameter by @Yeuoly in #2331
- fix: check empty tool provider credentials by @Yeuoly in #2332
- add option to prompt for a validation password when initializing admin user by @guchenhe in #2302
- fix: first agent latency by @Yeuoly in #2334
- Feat/current time tool zone by @Yeuoly in #2337
- feat: add xinference llm context size by @Yeuoly in #2336
- fix: ignore spark provider credential validate by @takatost in #2344
- chore(web): strong typing by @JunIce in #2339
- bump version to 0.5.3 by @takatost in #2306
New Contributors
- @glayyiyi made their first contribution in #2215
- @huangbaichao made their first contribution in #2241
- @leslie2046 made their first contribution in #2276
- @Yash-1511 made their first contribution in #2298
- @orangeclk made their first contribution in #2324
Full Changelog: 0.5.2...0.5.3
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
Full Changelog: 0.5.1...0.5.2
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
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
v0.4.9
- Fix some bugs
Notice
As per the planned schedule, these deprecated envs are being removed:
CONSOLE_URL
: Replace withCONSOLE_API_URL
andCONSOLE_WEB_URL
.APP_URL
: Replace withAPP_API_URL
andAPP_WEB_URL
.API_URL
: Replace withSERVICE_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
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
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
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
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