langgenius/dify 0.5.7

v0.5.7

on GitHub

New Features

• Added Mistral AI model provider. #2594
• Added Vector Database migrate tool, see below. #2562
• Added response format(JSON/XML) for google, anthropic, openai, wenxin, chatglm, tongyi LLMs. #2563
• Refactor RAG(knowledge) module, remove dependency on langchain to increase scalability and flexibility. #2528
• Agent App utilizing an LLM with ReACT mode (not support function calling), supports streaming output. #2498
• Added DuckDuckGo Search Tool for Enhanced Privacy-Focused Search Functionality by @Yash-1511 #2499

Vector Database Migrate Tool

When you want to switch to another vector database, you can deactivate or delete the original vector database after switching.

How to use

Step:

1. If you are starting from local source code, modify the environment variable in the .env file to the vector database you want to migrate to.
   For example:

VECTOR_STORE=qdrant

1. If you are starting from docker compose, modify the environment variable in the docker-compose.yaml file to the vector database you want to migrate to, both api and worker are all needed.

For example:

# The type of vector store to use. Supported values are `weaviate`, `qdrant`, `milvus`.
VECTOR_STORE: qdrant

1. run the below command in your terminal or docker container

flask vdb-migrarte

Update Guide

Deploying with Docker Compose:

1. Get the latest code from the main branch:

   git checkout main
   git pull origin main

2. Go to the next step and update to the latest image:

   cd docker
   docker-compose up -d

Deploying from Source Code:

1. Stop API server, Worker and Web frontend Server.

2. Get the latest code from the main branch:

   git checkout main
   git pull origin main

3. 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.

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

What's Changed

• Windows local deployment switch "tool“ interface failed by @kukuze in #2483
• fix: chat restart by @zxhlyh in #2488
• fix: code-based extension by @zxhlyh in #2490
• fix: incorrect tool name by @Yeuoly in #2489
• fix: audio to text by @zxhlyh in #2493
• del doc support by @JohnJyong in #2494
• Add default values for optional parameters in API tool and parser by @Yeuoly in #2491
• doc: typo in chat by @crazywoola in #2492
• feat: increase max tools by @Yeuoly in #2497
• Refactor agent history organization and initialization of agent scrat… by @Yeuoly in #2495
• Chore/delete chunk decode error alert by @guchenhe in #2500
• FEAT: Add DuckDuckGo Search Tool for Enhanced Privacy-Focused Search Functionality by @Yash-1511 in #2499
• Feat/stream react by @Yeuoly in #2498
• fix: api doc example error by @iamjoel in #2505
• update issue template by @crazywoola in #2507
• fix: config not exists by @crazywoola in #2513
• Fix #2512 by @crazywoola in #2515
• fix: bing search response filter by @Yeuoly in #2519
• Voice audition by @charli117 in #2504
• Fix/upload limit by @JohnJyong in #2521
• Feat/dify rag by @JohnJyong in #2528
• fix: update current tenant id of account when switching tenant by @bowenliang123 in #2530
• Fix/tool default value by @Yeuoly in #2536
• fix: tolerate exceptions in cleaning up index when vector db service unavailable by @bowenliang123 in #2533
• chore: add api key and value placeholder by @iamjoel in #2538
• Fix/langchain document schema by @JohnJyong in #2539
• Feat/i18n restructure by @crazywoola in #2529
• fix dev/reformat by @JohnJyong in #2542
• fix: webapp name by @zxhlyh in #2543
• Feat/openai llm trial paid config by @GarfieldDai in #2545
• feat: openai llm get trial or paid models from config. by @GarfieldDai in #2546
• Fix/new RAG bugs by @JohnJyong in #2547
• Update README_CN.md by @takatost in #2550
• feat: change max_question_num to 5 by @wststone in #2520
• Feat/use searchparams as state by @wststone in #2554
• Feat/vdb migrate command by @JohnJyong in #2562
• Feat/json mode by @Yeuoly in #2563
• fix typo in error message of supported keyword store by @bowenliang123 in #2560
• chore: remove redundant casting flask app config into dict by @bowenliang123 in #2564
• Add Dify Meetup Event on Mar 9 by @crazywoola in #2566
• fix weaviate delete_by_ids by @bowenliang123 in #2565
• Fix some RAG bugs by @JohnJyong in #2570
• fix: notion binding by @zxhlyh in #2572
• fix mivlus delete by ids error by @JohnJyong in #2573
• enhancement: improve client-side code by @wststone in #2568
• fix: parameter type handling in API tool and parser by @Yeuoly in #2574
• Fix/hit test tsne issue by @JohnJyong in #2581
• fix: correct the parent class of CacheEmbedding by @bowenliang123 in #2578
• fix: convert tool messages into user messages in react mode and fill … by @Yeuoly in #2584
• enhancement: skip fetching to improve user experience when switching … by @wststone in #2580
• Fix 500 error when creating from the template and the provider is None by @crazywoola in #2591
• feat:add mistral ai by @joshua20231026 in #2594
• fix: parameter user exceeded max length when invoking moonshot llm by @takatost in #2596
• Feat/provider mistralai by @joshua20231026 in #2598
• doc: props.appDetail.api_base_url by @crazywoola in #2597
• fix props.appDetail.api_base_url /v1 repeat error by @xiangpingjiang in #2601
• Fix/2559 upload powered by brand image not showing up by @crazywoola in #2602
• Fix: explore apps is not shown by @crazywoola in #2604
• fix: missing default user for APP service api by @takatost in #2606
• fix: AppParameterApi.get() got an unexpected keyword argument 'end_user' by @takatost in #2607
• fix: notion extractor raise 'NoneType' object has no attribute 'curre… by @takatost in #2608
• Fix: default button behavior by @crazywoola in #2609
• version to 0.5.7 by @takatost in #2610

New Contributors

• @kukuze made their first contribution in #2483
• @wststone made their first contribution in #2520
• @xiangpingjiang made their first contribution in #2601

Full Changelog: 0.5.6...0.5.7