dify

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.

OTHER License

Downloads
2.8K
Stars
47.4K
Committers
431
View Code on GitHub Visit Website
Ecosystems: Next, Llama, Python

Bot releases are hidden (Show)

dify - v0.5.6

Published by takatost 8 months ago

  • Added voice choose for TTS in App. Thanks @charli117!
  • Fix some problems.

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

New Contributors

Full Changelog: https://github.com/langgenius/dify/compare/0.5.5...0.5.6

dify - v0.5.5

Published by takatost 8 months ago

  • Adding SMTP method for sending emails. Thanks @jonahcui!
  • Fix some problems.

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

New Contributors

Full Changelog: https://github.com/langgenius/dify/compare/0.5.4...0.5.5

dify - v0.5.4

Published by takatost 9 months ago

  • GPT-3.5-Turbo-0215 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:

  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

New Contributors

Full Changelog: https://github.com/langgenius/dify/compare/0.5.3...0.5.4

dify - v0.5.3

Published by takatost 9 months ago

  • Support function calling for more models (Azure OpenAI, xinference, ZhipuAI, Minimax)
  • Fix some problems

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

New Contributors

Full Changelog: https://github.com/langgenius/dify/compare/0.5.2...0.5.3

dify - v0.5.2

Published by takatost 9 months ago

  • 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:

  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

New Contributors

Full Changelog: https://github.com/langgenius/dify/compare/0.5.1...0.5.2

dify - v0.5.1

Published by takatost 9 months ago

  • add multiple LLM debug mode โš”๏ธ

    image
    image

  • 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:

  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

New Contributors

Full Changelog: https://github.com/langgenius/dify/compare/0.5.0...0.5.1

dify - v0.5.0

Published by takatost 9 months ago

๐ŸŽ‰๐ŸŽ‰ 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 ๐Ÿ‘‡

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.

https://github.com/langgenius/dify/assets/138381132/c0682fb9-33ee-4521-a149-b6c6fb1dc5b4

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:

  1. 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.

  2. "API Based Extension", previously under the Assistant, is now in the "Variables" module.

  3. For ease of use, "Tools" has been relocated to the main product menu, centralizing customization, authorization, and management.

  4. 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".

TTS Feature

Easily convert text to speech playback.

TTS 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:

  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.

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

Change Log

Full Changelog: https://github.com/langgenius/dify/compare/0.4.9...0.5.0

dify - v0.4.9

Published by takatost 9 months ago

  • 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:

  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

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

What's Changed

Full Changelog: https://github.com/langgenius/dify/compare/0.4.8...0.4.9

dify - v0.4.8

Published by takatost 9 months ago

  • 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:

  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

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

What's Changed

Full Changelog: https://github.com/langgenius/dify/compare/0.4.7...0.4.8

dify - v0.4.7

Published by takatost 9 months ago

Fix some problems.

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

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

What's Changed

New Contributors

Full Changelog: https://github.com/langgenius/dify/compare/0.4.6...0.4.7

dify - v0.4.6

Published by takatost 9 months ago

What's Changed

Full Changelog: https://github.com/langgenius/dify/compare/0.4.5...0.4.6

dify - v0.4.5

Published by takatost 9 months ago

Fix some BUGs.

What's Changed

Full Changelog: https://github.com/langgenius/dify/compare/0.4.4...0.4.5

dify - v0.4.4

Published by takatost 10 months ago

Add Together.ai model provider and fix some bugs.

What's Changed

Full Changelog: https://github.com/langgenius/dify/compare/0.4.3...0.4.4

dify - v0.4.3

Published by takatost 10 months ago

Optimize performance & fix few bugs.

What's Changed

New Contributors

Full Changelog: https://github.com/langgenius/dify/compare/0.4.2...0.4.3

dify - v0.4.2

Published by takatost 10 months ago

What's Changed

New Contributors

Full Changelog: https://github.com/langgenius/dify/compare/0.4.1...0.4.2

dify - v0.4.1

Published by takatost 10 months ago

What's Changed

Full Changelog: https://github.com/langgenius/dify/compare/0.4.0...0.4.1

dify - v0.4.0

Published by takatost 10 months ago

๐ŸŽ‰๐ŸŽ‰ Dify's Version 0.4 is out now.

We've made some serious under-the-hood changes to how the Model Runtime works, making it more straightforward for our specific needs, and paving the way for smoother model expansions and more robust production use.

What's Changed

  • Model Runtime Rework: We've moved away from LangChain, simplifying the model layer. Now, expanding models is as easy as setting up the model provider in the backend with a bit of YAML.

    For more details, see: https://github.com/langgenius/dify/blob/main/api/core/model_runtime/README.md

  • App Generation Update: Replacing the old Redis Pubsub queue with threading.Queue for a more reliable, performant, and straightforward workflow.

  • Model Providers Upgraded: Support for both preset and custom models, ideal for adding OpenAI fine-tuned models or fitting into various MaaS platforms. Plus, you can now check out supported models without any initial configuration.

  • Context Size Definition: Introduced distinct context size settings, separate from Max Tokens, to handle the different limits and sizes in models like OpenAI's GPT-4 Turbo.

  • Flexible Model Parameters: Customize your model's behavior with easily adjustable parameters through YAML.

  • GPT-2 Tokenizer Files: Now cached within Dify's codebase, making builds quicker and solving issues related to acquiring tokenizer files in offline source deployments.

  • Model List Display: The App now displays all supported preset models, including details on any that aren't available and how to configure them.

  • New Model Additions: Including Google's Gemini Pro and Gemini Pro Vision models (Vision requires an image input), Azure OpenAI's GPT-4V, and support for OpenAI-API-compatible providers.

  • Expanded Inference Support: Xorbit Inference now includes chat mode models, and there's a wider range of models supporting Agent inference.

  • Updates & Fixes: We've updated other model providers to be in sync with the latest version APIs and features, and squashed a series of minor bugs for a smoother experience.

Catch you in the code,

The Dify Team ๐Ÿ› ๏ธ

Change Log

New Contributors

Full Changelog: https://github.com/langgenius/dify/compare/0.3.34...0.4.0

dify - v0.3.34

Published by takatost 10 months ago

Features

  • Annotation Reply, see details: Link
  • Dify Knowledge supports unstructured.io as the file extraction solution.
  • Azure OpenAI add gpt-4-1106-previewใ€gpt-4-vision-preview models support.
  • SaaS services now support replacing the logo of WebApp after subscribing.

Important Upgrade Notice

  • Annotation Reply

    The annotation function can support direct replies to related questions, so we need to assign values to previously unstored questions for the table message_annotations.

    we need doing below command in your api docker container

    docker exec -it docker-api-1 bash
flask add-annotation-question-field-value

    or direct run below command when you launch from source codes.

    cd api
flask add-annotation-question-field-value

  • Unstructured.io Support

    Due to the support of this feature, we have added four new formats of text parsing( msg , eml, ppt, pptx ) and optimized two text parsing formats (text, markdown) in our SAAS erviroment.

    For localhost you need to do below actions to support unstructured.io

    Unstructured Document

    1. docker pull from unstructured's image repository.
    docker pull downloads.unstructured.io/unstructured-io/unstructured-api:latest
    1. Once pulled, you can launch the container
    docker run  -d --rm --name unstructured-api downloads.unstructured.io/unstructured-io/unstructured-api:latest --port 8000 --host 0.0.0.0
    1. In our docker-compose.yaml, add two new environment variables for the api and worker services.
    ETL_TYPE=Unstructured
UNSTRUCTURED_API_URL=http://unstructured:8000/general/v0/general
    1. Restart the Difyโ€˜s services
    docker-compose up -d

What's Changed

New Contributors

Full Changelog: https://github.com/langgenius/dify/compare/0.3.33...0.3.34

dify - v0.3.33

Published by takatost 11 months ago

What's Changed

New Contributors

Full Changelog: https://github.com/langgenius/dify/compare/0.3.32...0.3.33

dify - v0.3.32

Published by takatost 11 months ago

New Features

  • Supported the rerank model of xinference for local deployment, such as: bge-reranker-large, bge-reranker-base.
  • ChatGLM2/3 support

โš ๏ธ Breaking Change

We've recently switched provider ChatGLM to the OpenAI API protocol, so from now on, we'll only be supporting ChatGLM3 and ChatGLM2. Unfortunately, support for ChatGLM1 has been deprecated.

What's Changed

New Contributors

Full Changelog: https://github.com/langgenius/dify/compare/0.3.31...0.3.32

Package Rankings
Top 13.56% on Pypi.org
Top 31.86% on Npmjs.org
Top 24.98% on Rubygems.org
Badges
Extracted from project README
Star History Chart
Related Projects
agentkit

Starter-kit to build constrained agents with Nextjs, FastAPI and Langchain

25 Jan 2024 1,555
llm.report

๐Ÿ“Š llm.report is an open-source logging and analytics platform for OpenAI: Log your ChatGPT API re...

25 Apr 2023 893