v0.3.31-fix2

New Features

• add anthropic claude-2.1 support

Major Fixes

• fix: white page problem in Safari.

Important Notice

Before upgrading to 0.3.31, please ensure that all steps outlined in the Important Upgrade Notice for the 0.3.31 release are completed: https://github.com/langgenius/dify/releases/tag/0.3.31

What's Changed

• fix: safari can not in by @iamjoel in #1590
• feat: add anthropic claude-2.1 support by @takatost in #1591
• feat: bump version to 0.3.31-fix2 by @takatost in #1592

Full Changelog: 0.3.31-fix1...0.3.31-fix2

v0.3.31-fix1

Releasing a new version due to some issues that made the previous one unavailable.

Important Notice

Before upgrading to 0.3.31, please ensure that all steps outlined in the Important Upgrade Notice for the 0.3.31 release are completed: https://github.com/langgenius/dify/releases/tag/0.3.31

What's Changed

• fix: retrieval test page hide rerank model also hide retrieval config by @iamjoel in #1585
• fix: chat on start bug by @iamjoel in #1588
• Update docker-compose.yaml by @JohnJyong in #1587
• feat: bump version to 0.3.31-fix1 by @takatost in #1589

Full Changelog: 0.3.31...0.3.31-fix1

v0.3.31

New Features

• Added support for multi-datasets retrieval, hybrid search, and result re-ranking.
  Learn more: Dify.AI v0.3.31: Surpassing the Assistants API – Dify's RAG Demonstrates an Impressive 20% Improvement

Important Upgrade Notice

Current version adds full-text search and hybrid search functions for datasets, significantly improving search results. If you want to use this feature, you need to make the following configurations:

• If the vector database you are using is Weaviate
  Please update your version to v1.19.0 or later in /dify/docker/docker-compose.yaml.
  For more details, please refer to the Weaviate release list.

 weaviate:
    image: semitechnologies/weaviate:1.19.0
    restart: always
    volumes:
      # Mount the Weaviate data directory to the container.
      - ./volumes/weaviate:/var/lib/weaviate
    environment:
      # The Weaviate configurations
      # You can refer to the [Weaviate](https://weaviate.io/developers/weaviate/config-refs/env-vars) documentation for more information.
      QUERY_DEFAULTS_LIMIT: 25
      AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED: 'false'
      PERSISTENCE_DATA_PATH: '/var/lib/weaviate'
      DEFAULT_VECTORIZER_MODULE: 'none'
      CLUSTER_HOSTNAME: 'node1'
      AUTHENTICATION_APIKEY_ENABLED: 'true'
      AUTHENTICATION_APIKEY_ALLOWED_KEYS: 'WVF5YThaHlkYwhGUSmCRgsX3tD5ngdN8pkih'
      AUTHENTICATION_APIKEY_USERS: '[email protected]'
      AUTHORIZATION_ADMINLIST_ENABLED: 'true'
      AUTHORIZATION_ADMINLIST_USERS: '[email protected]'

• If the vector database you are using is Qdrant
  1. Since Dify's full-text index relies on the multilingual tokenizer in Qdrant's full-text index, by default, Qdrant does not support Chinese, Japanese, and Korean language tokenization.
  2. Therefore, we provide a full-language tokenizer mirror for Qdrant: langgenius/qdrant:latest, which can be deployed and used directly. You can also build your own Qdrant image using the following command:

  docker buildx build .  --build-arg  FEATURES="multiling-chinese,multiling-japanese,multiling-korean" --tag=langgenius/qdrant
  

  3. Due to the lack of full-text index in previous Qdrant data, you need to execute the following commands in the api container to complete the process:
     1. Start a bash shell inside the running Docker container:

      docker exec -it docker-api-1 bash
     

     2. Execute the command to create the full-text-index index:

       flask add-qdrant-full-text-index
     

• Milvus/Zilliz temporarily does not support Hybrid search

What's Changed

• Update README.md by @goocarlos in #1525
• fix: conversation rename always auto generate by @takatost in #1530
• new readme by @crazywoola in #1528
• doc: update readme by @crazywoola in #1536
• feat: optimize timezone of server by @takatost in #1537
• Doc/update readme patch 1 by @crazywoola in #1538
• feat: add code of conduct by @crazywoola in #1541
• fix: upload image by @zxhlyh in #1522
• feat: remove plugin page by @zxhlyh in #1544
• update images by @crazywoola in #1548
• update images by @crazywoola in #1549
• fix: upload file not clickable in firefox by @crazywoola in #1552
• feat: supports for new version of openllm by @takatost in #1554
• Add some interesting badges :) by @crazywoola in #1558
• Feat/add retriever rerank by @JohnJyong in #1560
• Feat/jp and es by @crazywoola in #1562
• feat: add retriever rank fe by @iamjoel in #1557
• fix hybrid search reranking check by @JohnJyong in #1563
• fix the error message by @JohnJyong in #1564
• chore: retrieval docs links and enchance help doc translation by @iamjoel in #1570
• feat: fetch stream compatibility enhance by @rickythink in #1551
• fix(web): Sidebar create new chat context by @JunIce in #1569
• Feat/sdk vision support by @GarfieldDai in #1531
• fix(api): patch Windows timezone set by @JunIce in #1575
• feat: configurable invite expiry time by @MatriQ in #1573
• Fix/check rerank model selected by @zxhlyh in #1577
• fix: some text by @zxhlyh in #1579
• fix multi retrieval with resource score issue by @JohnJyong in #1578
• feat: add supported_model_types field and filter in provider list by @takatost in #1581
• Compatible model saving error by @JohnJyong in #1582
• feat: bump version to 0.3.31 by @takatost in #1584

New Contributors

• @rickythink made their first contribution in #1551

Full Changelog: 0.3.30...0.3.31

v0.3.30

New Features

• App supports image uploading and calls the OpenAI GPT-4V or gpt-4-vision-preview which allows the model to take in images and answer questions about them.

What's Changed

• fix: universal chat external_data_tools NPE by @takatost in #1467
• fix: external data tool parse error by @takatost in #1469
• feat: hidden api key enhancement. by @GarfieldDai in #1468
• fix: external data tool batch retrieve bug by @takatost in #1472
• fix: openai model name by @zxhlyh in #1474
• fix: code-based extension by @zxhlyh in #1477
• feat: support basic feature of OpenAI new models by @takatost in #1476
• fix: api extension selector by @zxhlyh in #1486
• fix: rename api based extension by @zxhlyh in #1485
• application embedded add chrome && ChatBot Chrome plugin update v1.5 by @charli117 in #1480
• feat: update the docs in forking applications by @crazywoola in #1491
• Fixed missing i18n app-debug.zh.ts items. by @BenjaminX in #1503
• Change Embedded chrome plugin Url by @charli117 in #1498
• feat: update free plan rules of spark by @takatost in #1515
• feat: add spark 3.0 tip by @zxhlyh in #1516
• 1506 remove duplicated code by @crazywoola in #1511
• feat: [backend] vision support by @takatost in #1510
• feat: [frontend] support vision by @zxhlyh in #1518
• feat: bump version to 0.3.30 by @takatost in #1519

Full Changelog: 0.3.29...0.3.30

v0.3.29

New Features

• App Moderation Support [DOCS WIP]
• App External Data Retrieve Support [DOCS WIP]
• the above functions support API-based / Code-based Extension [DOCS WIP]
• Support ZhipuAI chatglm_turbo, spark v3.0, weixin ernie-bot-4 model

What's Changed

• feat: logo by @zxhlyh in #1356
• Fix milvus configuration error by @JackLCL in #1362
• feat: optimize completion model agent by @takatost in #1364
• fix: app model config detached in completion thread by @takatost in #1366
• feat: support wenxin ernie-bot-4 and chat mode by @takatost in #1375
• fix: i18n runtime error by @zxhlyh in #1376
• fix: app config zhipu chatglm_std model, but it still use chatglm_lit… by @sbwkl in #1377
• refactor advanced prompt core. by @GarfieldDai in #1350
• feat: enchance prompt mode copywriting by @iamjoel in #1379
• fix: npm run start by @zxhlyh in #1380
• fix: not load dataset config by @iamjoel in #1381
• feat: add context missing warning by @iamjoel in #1384
• feat: add advanced prompt doc link by @iamjoel in #1363
• Chrome Dify Chatbot Plug-in by @charli117 in #1378
• feat: adjust anthropic by @takatost in #1387
• fix: return wrong when init 0 quota in trial provider by @takatost in #1394
• Update README.md by @Panmuse in #1389
• Update README_CN.md by @Panmuse in #1390
• Added diagram picture file for docker-compose yaml file visualization. by @yangboz in #1374
• fix: hex problem by @takatost in #1395
• feat: upgrade xinference-client to 0.5.4 by @takatost in #1402
• fix: workspace app avatar is abnormal by @Hickays in #1411
• mermaid front-end rendering initialization exception handling logic o… by @charli117 in #1407
• fix: provider delete api key modal z-index by @zxhlyh in #1416
• fix: Add icons for apps in "Related apps list" by @Hickays in #1425
• fix: delete app and setting modal is not wokring in firefox by @crazywoola in #1427
• fix: metadata not saved by @crazywoola in #1429
• feat: add spark v3.0 llm support by @takatost in #1434
• chore(deps): bump semver from 5.7.1 to 5.7.2 in /web by @dependabot in #1436
• chore(deps): bump crypto-js from 4.1.1 to 4.2.0 in /web by @dependabot in #1437
• chore(deps-dev): bump postcss from 8.4.24 to 8.4.31 in /web by @dependabot in #1439
• chore(deps): bump word-wrap from 1.2.3 to 1.2.5 in /web by @dependabot in #1440
• fix: service suggested api by @crazywoola in #1452
• feat: support chatglm_turbo model #1443 by @takatost in #1460
• fix: Use correct typehint for return values by @lethe3000 in #1454
• feat: add api-based extension & external data tool & moderation backend by @GarfieldDai in #1403
• feat: add api-based extension & external data tool & moderation by @zxhlyh in #1459
• fix: chat style by @zxhlyh in #1463
• fix: refresh api-based-extension by @zxhlyh in #1464
• fix: prompt variables validate when using external data tools by @takatost in #1465
• feat: bump version to 0.3.29 by @takatost in #1462

New Contributors

• @JackLCL made their first contribution in #1362
• @sbwkl made their first contribution in #1377
• @yangboz made their first contribution in #1374
• @dependabot made their first contribution in #1436
• @lethe3000 made their first contribution in #1454

Full Changelog: 0.3.28...0.3.29

v0.3.28

What's Changed

• fix: new app with template display by @kztao in #1322
• fix: value.join is not a function in log list by @crazywoola in #1332
• fix: raise error in minimax stream generate by @takatost in #1336
• Add Message Suggested Api by @charli117 in #1326
• fix: modal z-index by @crazywoola in #1337
• fix: max tokens of OpenAI gpt-3.5-turbo-instruct to 4097 by @takatost in #1338
• feat: use xinference client instead of xinference by @takatost in #1339
• Feat/advanced prompt enhancement by @GarfieldDai in #1340
• feat: switch to generation model set default stop word by @iamjoel in #1341
• fix: modal z-index by @Hickays in #1343
• remove the suggested api for completion app by @crazywoola in #1347
• feat: bump version to 0.3.28 by @takatost in #1349

New Contributors

• @kztao made their first contribution in #1322
• @Hickays made their first contribution in #1343

Full Changelog: 0.3.27...0.3.28

v0.3.27

What's Changed

• feat: using random sampling to check if it violates the review mechan… by @takatost in #1308
• fix: compatibility issues with the tongyi model. by @takatost in #1310
• feat: optimize minimax llm call by @takatost in #1312
• fix: grpc gevent compatible by @JohnJyong in #1314
• fix: minimax tests by @takatost in #1313
• feat: add document of authorization by @JzoNgKVO in #1311
• feat: remove llm client use by @takatost in #1316
• fix: retriever_resource missing by @takatost in #1317
• feat: adjust to only build the latest image when pushing a tag. by @takatost in #1324
• feat: improve document delete logic by @JohnJyong in #1325
• fix: dataset segment not exist return agent response by @takatost in #1329
• feat: advanced prompt backend by @GarfieldDai in #1301
• feat: advanced prompt by @zxhlyh in #1330
• feat: bump version to 0.3.27 by @takatost in #1331

Full Changelog: 0.3.26...0.3.27

v0.3.26

What's Changed

• document segmentApi Add get&update&delete operate by @charli117 in #1285
• fix: openllm completion start with prompt, remove it by @takatost in #1303
• Feat/add milvus vector db by @JohnJyong in #1302
• milvus secure check fix by @JohnJyong in #1305
• milvus docker compose env by @JohnJyong in #1306
• bump version to 0.3.26 by @JohnJyong in #1307

Full Changelog: 0.3.25...0.3.26

v0.3.25

What's Changed

• fix: request timeout when openai completion by @takatost in #1265
• fix: db not commit when streaming output by @takatost in #1266
• fix: count down thread in completion db not commit by @takatost in #1267
• fix: detached model in completion thread by @takatost in #1269
• fix devcontainer issue by @guangtouwangba in #1273
• chore(web): strong type by @JunIce in #1259
• Application share qrcode by @charli117 in #1277
• feat: move login_required wrapper outside by @takatost in #1281
• feat: qdrant support in docker compose by @takatost in #1286
• feat: upgrade xinference client to 0.5.2 by @takatost in #1292
• feat: add baichuan llm support by @takatost in #1294
• feat: support openllm embedding by @takatost in #1293
• feat: provider add baichuan by @zxhlyh in #1298
• fix: prompt for baichuan text generation models by @takatost in #1299
• feat: bump version to 0.3.25 by @takatost in #1300

Full Changelog: 0.3.24...0.3.25

v0.3.24

What's Changed

• add help wanted issue template by @crazywoola in #1199
• fix: provider spark free quota text by @zxhlyh in #1201
• Complete type defined. by @JunIce in #1200
• fix: transaction hangs due to message commit block during long LLM calls by @takatost in #1206
• fix: transaction not commit during long LLM calls by @takatost in #1213
• Feat/huggingface embedding support by @GarfieldDai in #1211
• Fix/qdrant data issue by @JohnJyong in #1203
• fix: dataset eslint error by @iamjoel in #1221
• Fix: add loading for dataset creation by @JzoNgKVO in #1214
• feat: batch run support retry errors and decrease rate limit times by @iamjoel in #1215
• Feat/api jwt by @zxhlyh in #1212
• fix: FATAL: role "root" does not exist. by @crazywoola in #1233
• Fix App logs page modal show different model icon. by @JunIce in #1224
• Fix: debounce of dataset creation by @JzoNgKVO in #1237
• Fix: dataset list refresh by @JzoNgKVO in #1216
• feat: support binding context var by @GarfieldDai in #1227
• fix: dataset query error. by @GarfieldDai in #1244
• Feat/dataset service api by @JohnJyong in #1245
• Feat/dataset support api service by @zxhlyh in #1240
• fix: wenxin model name invalid when llm call by @takatost in #1248
• fix: db session not commit before long llm call running by @takatost in #1251
• fix: dataset footer styles by @crazywoola in #1254
• Fix/dataset api key delete by @JohnJyong in #1255
• fix: doc by @zxhlyh in #1256
• Fix/notion sync by @zxhlyh in #1258
• feat: bump version to 0.3.24 by @takatost in #1262

Full Changelog: 0.3.23...0.3.24