Skip to content

Commit

Permalink
Feat/modelhub (#1)
Browse files Browse the repository at this point in the history
* feat: translations (langgenius#3176)

* fix: prompt editor variable picker (langgenius#3177)

* Fix: features of agent-chat (langgenius#3178)

* version to 0.6.0-fix1 (langgenius#3179)

* fix keyword index error when storage source is S3 (langgenius#3182)

* Update README.md to include workflows (langgenius#3180)

* Compatible with unique index conflicts (langgenius#3183)

* fix: sometimes chosed old selected knowledge may overwirte the new knowledge (langgenius#3199)

* Fix: remove unavailable return_preamble parameter in cohere (langgenius#3201)

Signed-off-by: Jat <jat@sinosky.org>

* Fix/code transform result (langgenius#3203)

* fix(code_executor): surrogates not allowed error in jinja2 template (langgenius#3191)

* fix: node connect self (langgenius#3194)

* Update README.md (langgenius#3206)

* fix economy index search in workflow (langgenius#3205)

* fix: index number in api/README (langgenius#3214)

* Update README.md (langgenius#3212)

* fix detached instance error in keyword index create thread and fix question classifier node out of index error (langgenius#3219)

* fix: incomplete response (langgenius#3215)

* fix: latest image tag not push in GitHub action (langgenius#3213)

* fix: vision config doesn't enabled in llm (langgenius#3225)

* fixed the issue of missing cleanup function in the AudioBtn component (langgenius#3133)

* fix: image text when retrieve chat histories (langgenius#3220)

* feat: moonshot function call (langgenius#3227)

* feat: support setting database used in Milvus (langgenius#3003)

* fix milvus database name parameter missed (langgenius#3229)

* fix: file not uploaded caused api error (langgenius#3228)

* update link (langgenius#3226)

* fix: skip Celery warning by setting broker_connection_retry_on_startup config (langgenius#3188)

* fix: workflow run edge status (langgenius#3236)

* fix: empty conversation list of explore chatbot (langgenius#3235)

* Fix: picture of workflow (langgenius#3241)

* feat: prompt-editor support undo (langgenius#3242)

* fix: number type in app would render as select type in webapp (langgenius#3244)

* fix: token is not logging of question classifier node (langgenius#3249)

* chore: remove langchain in tools (langgenius#3247)

* make sure validation flow works for all model providers in bedrock (langgenius#3250)

* feat: remove unregistered-llm-in-debug (langgenius#3251)

* version to 0.6.1 (langgenius#3253)

* fix: agent chat multiple model debug (langgenius#3258)

* feat: gpt-4-turbo (langgenius#3263)

* fix: image was sent to an unsupported LLM when sending second message (langgenius#3268)

* feat: vision parameter support of OpenAI Compatible API (langgenius#3272)

* fix: var assigner input node can not find caused error (langgenius#3274)

* fix: variable-assigner node connect (langgenius#3288)

* Feat/Agent-Image-Processing (langgenius#3293)

Co-authored-by: Joel <iamjoel007@gmail.com>

* chore: address security alerts on braces escape and KaTeX (langgenius#3301)

* chore(deps): bump katex from 0.16.8 to 0.16.10 in /web (langgenius#3307)

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

* Update README.md (langgenius#3281)

* Remove langchain dataset retrival agent logic (langgenius#3311)

* add german translations (langgenius#3322)

* feat: add missing workflow i18n keys (langgenius#3309)

Co-authored-by: lbm21 <313338264@qq.com>

* feat:add 'name' field return (langgenius#3152)

* improvement: speed up dependency installation in docker image rebuilds by mounting cache layer (langgenius#3218)

* feat: support gpt-4-turbo-2024-04-09 model (langgenius#3300)

* feat: Add Cohere Command R / R+ model support (langgenius#3333)

* fix dataset retrival in dataset mode (langgenius#3334)

* chore:bump pypdfium2 from 4.16.0 to 4.17.0 (langgenius#3310)

* feat(llm/models): add gemini-1.5-pro (langgenius#2925)

* feat: make input size bigger in start (langgenius#3340)

* Doc/update readme (langgenius#3344)

* fix: leave  progress page still call indexing-status api (langgenius#3345)

* feat: update aws bedrock (langgenius#3326)

Co-authored-by: chenhe <guchenhe@gmail.com>

* fix/moonshot-function-call (langgenius#3339)

* fix issue: user’s keywords do not affect when add segment (langgenius#3349)

* add segment with keyword issue (langgenius#3351)

Co-authored-by: StyleZhang <jasonapring2015@outlook.com>

* Fix issue : don't delete DatasetProcessRule, DatasetQuery and AppDatasetJoin when delete dataset with no document (langgenius#3354)

* fix: remove middle editor may cause render placement error (langgenius#3356)

* Added a note on the front-end docker build: use taobao source to accelerate the installation of front-end dependency packages to achieve the purpose of quickly building containers (langgenius#3358)

Co-authored-by: lbm21 <313338264@qq.com>
Co-authored-by: akou <beiming1201@gmail.com>

* fix: var name too long would break ui in var assigner and end nodes (langgenius#3361)

* Refactor/react agent (langgenius#3355)

* Fix/Bing Search url endpoint cannot be customized (langgenius#3366)

* fix: image token calc of OpenAI Compatible API (langgenius#3368)

* Update README.md (langgenius#3371)

* update workflow intro mp4 codec (langgenius#3372)

* fix: cohere tool call does not support single tool (langgenius#3373)

* version to 0.6.2 (langgenius#3375)

* fix: variable pool mapping variable mixed up (langgenius#3378)

* version to 0.6.2-fix1 (langgenius#3380)

* fix: yarn install extract package err when using GitHub Cache in amd6… (langgenius#3383)

* feat: Add support for embed file with AWS Bedrock Titan Model (langgenius#3377)

Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>

* fix: remove - in dataset retriever tool name (langgenius#3381)

* feat:api Add support for extracting EPUB files in ExtractProcessor (langgenius#3254)

Co-authored-by: crazywoola <427733928@qq.com>

* feat: show citation info in run history (langgenius#3399)

* Feat: Invitation link automatically completes domain name (langgenius#3393)

Co-authored-by: huangbaichao <hbc@moonlit.art>

* Integrated SearXNG search as built-in tool (langgenius#3363)

Co-authored-by: crazywoola <427733928@qq.com>

* fix: [azure_openai] Error: 'NoneType' object has no attribute 'content' (langgenius#3389)

* Update providers preview (langgenius#3403)

* add xls file suport (langgenius#3321)

* Update README.md (langgenius#3405)

* Fix/workflow tool incorrect parameter configurations (langgenius#3402)

Co-authored-by: Joel <iamjoel007@gmail.com>

* chore: replace all set interval (langgenius#3411)

* feat: Deprecate datetime.utcnow() in favor of datetime.now(timezone.utc).replace(tzinfo=None) for better timezone handling (langgenius#3408) (langgenius#3416)

* chore: remove Langchain tools import (langgenius#3407)

* feat: gemini pro function call (langgenius#3406)

* fix: shared text-generation stream (langgenius#3419)

* fix/dataset-retriever-tool-parameter-redundancy (langgenius#3418)

* Feat/api tool custom timeout (langgenius#3420)

* fix: test env key missing or wrong (langgenius#3430)

* Doc/update readme (langgenius#3433)

* Update README_CN.md (langgenius#3434)

* Update README_CN.md (langgenius#3435)

* feat: add workflow editor shortcuts (langgenius#3382) (langgenius#3390)

* FEAT: cohere rerank 3 model added (langgenius#3431)

* chore: remove the COPY instruction in .devcontainer/Dockerfile (langgenius#3409)

* fix typo: Changlog -> Changelog (langgenius#3442)

* fix: node shortcuts active in input fields (langgenius#3438)

* Add nvidia codegemma 7b (langgenius#3437)

* Update yaml and py file in Tavily Tool (langgenius#3450)

* feat: Added the mirror of Aliyun's Linux apk installation package and updated the deprecated taobao npm mirror address to npmmirror (langgenius#3459)

* Revert "Update yaml and py file in Tavily Tool" (langgenius#3464)

* feat: jina reader (langgenius#3468)

* feat: support configurate openai compatible stream tool call (langgenius#3467)

* feat: optimize the efficiency of generating chatbot conversation name (langgenius#3472)

* feat: remove langchain from output parsers (langgenius#3473)

* chore: separate Python dependencies for development (langgenius#3198)

* chore: add sandbox permission tooltip (langgenius#3477)

* fix: prompt template issue (langgenius#3449)

* feat: support relyt vector database  (langgenius#3367)

Co-authored-by: jingsi <jingsi@leadincloud.com>

* Update README.md (langgenius#3478)

* nvidia-label-update (langgenius#3482)

* fix: in conversation log click op button would cause close drawer (langgenius#3483)

* fix: workflow auto layout nodes offset & delete node shortcuts (langgenius#3484)

* fix: workflow edge curvature (langgenius#3488)

* fix: stringify object while exporting batch result to csv (langgenius#3481)

* question classifier prompt optimization (langgenius#3479)

* feat: refactor tongyi models (langgenius#3496)

* fix: bump twilio to 9.0.4 skipping yanked versions (langgenius#3500)

* test: install ffmpeg for pytests (langgenius#3499)

* feat: support var auto rename in prompt editor (langgenius#3510)

* fix: add message caused problem after simple chat convert to workflow (langgenius#3511)

* fix: the object field is empty string in some openAI api compatible model (langgenius#3506)

* Add suuport for AWS  Bedrock Cohere embedding (langgenius#3444)

* fix: add completion mode object check (langgenius#3515)

* get config default for sandbox (langgenius#3508)

Co-authored-by: miendinh <miendinh@users.noreply.github.com>

* chore: improve reference variable picker user experience (langgenius#3517)

* fix: array[string] context in llm node invalid (langgenius#3518)

* version to 0.6.3 (langgenius#3519)

* fix the return with wrong datatype of segment (langgenius#3525)

* fix: the hover style of the card-item operation button container (langgenius#3520)

* chore: lint .env file templates (langgenius#3507)

* add support for swagger object type (langgenius#3426)

Co-authored-by: lipeikui <lipeikui@3vjia.com>

* /fix register

* /add modelhub

* localhost

* /fix req bugs

* modelhub add rerank

---------

Signed-off-by: Jat <jat@sinosky.org>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
Co-authored-by: zxhlyh <jasonapring2015@outlook.com>
Co-authored-by: KVOJJJin <jzongcode@gmail.com>
Co-authored-by: takatost <takatost@users.noreply.github.com>
Co-authored-by: Jyong <76649700+JohnJyong@users.noreply.github.com>
Co-authored-by: Chenhe Gu <guchenhe@gmail.com>
Co-authored-by: Joel <iamjoel007@gmail.com>
Co-authored-by: Jat <jat@sinosky.org>
Co-authored-by: Yeuoly <45712896+Yeuoly@users.noreply.github.com>
Co-authored-by: Eric Wang <wrqatw@gmail.com>
Co-authored-by: Bowen Liang <liangbowen@gf.com.cn>
Co-authored-by: legao <837937787@qq.com>
Co-authored-by: Leo Q <LeoQuote@users.noreply.github.com>
Co-authored-by: minakokojima <lychees67@gmail.com>
Co-authored-by: Nite Knite <nkCoding@gmail.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Lao <khazzz1c@gmail.com>
Co-authored-by: lbm21 <313338264@qq.com>
Co-authored-by: 呆萌闷油瓶 <253605712@qq.com>
Co-authored-by: Kenny <kt.tian@gmail.com>
Co-authored-by: akou <beiming1201@gmail.com>
Co-authored-by: longzhihun <38651850@qq.com>
Co-authored-by: LiuVaayne <10231735+vaayne@users.noreply.github.com>
Co-authored-by: crazywoola <427733928@qq.com>
Co-authored-by: Moonlit <bc.h@foxmail.com>
Co-authored-by: huangbaichao <hbc@moonlit.art>
Co-authored-by: junytang <junytang@gmail.com>
Co-authored-by: saga.rey <saga.rey@outlook.com>
Co-authored-by: chenxu9741 <1309095142@qq.com>
Co-authored-by: LIU HONGWEI <1327374483@qq.com>
Co-authored-by: Pascal M <11357019+perzeuss@users.noreply.github.com>
Co-authored-by: Yash Parmar <82636823+Yash-1511@users.noreply.github.com>
Co-authored-by: Bodhi <3882561+BodhiHu@users.noreply.github.com>
Co-authored-by: Selene29 <funmailfach@web.de>
Co-authored-by: Josh Feng <noisywolf@gmail.com>
Co-authored-by: Richards Tu <142148415+richards199999@users.noreply.github.com>
Co-authored-by: YidaHu <huyidada@gmail.com>
Co-authored-by: Jingpan Xiong <71321890+klaus-xiong@users.noreply.github.com>
Co-authored-by: jingsi <jingsi@leadincloud.com>
Co-authored-by: Joshua <138381132+joshua20231026@users.noreply.github.com>
Co-authored-by: sino <sino2322@gmail.com>
Co-authored-by: liuzhenghua <1090179900@qq.com>
Co-authored-by: kerlion <40377268+kerlion@users.noreply.github.com>
Co-authored-by: miendinh <22139872+miendinh@users.noreply.github.com>
Co-authored-by: miendinh <miendinh@users.noreply.github.com>
Co-authored-by: buu <bushuai@yahoo.com>
Co-authored-by: LeePui <444561897@qq.com>
Co-authored-by: lipeikui <lipeikui@3vjia.com>
  • Loading branch information
Show file tree
Hide file tree
Showing 384 changed files with 15,369 additions and 4,571 deletions.
3 changes: 0 additions & 3 deletions .devcontainer/Dockerfile
Original file line number Diff line number Diff line change
@@ -1,8 +1,5 @@
FROM mcr.microsoft.com/devcontainers/python:3.10

COPY . .


# [Optional] Uncomment this section to install additional OS packages.
# RUN apt-get update && export DEBIAN_FRONTEND=noninteractive \
# && apt-get -y install --no-install-recommends <your-package-list-here>
11 changes: 9 additions & 2 deletions .github/workflows/api-tests.yml
Original file line number Diff line number Diff line change
Expand Up @@ -32,15 +32,22 @@ jobs:
- name: Checkout code
uses: actions/checkout@v4

- name: Install APT packages
uses: awalsh128/cache-apt-pkgs-action@v1
with:
packages: ffmpeg

- name: Set up Python
uses: actions/setup-python@v5
with:
python-version: '3.10'
cache: 'pip'
cache-dependency-path: ./api/requirements.txt
cache-dependency-path: |
./api/requirements.txt
./api/requirements-dev.txt
- name: Install dependencies
run: pip install -r ./api/requirements.txt
run: pip install -r ./api/requirements.txt -r ./api/requirements-dev.txt

- name: Run ModelRuntime
run: pytest api/tests/integration_tests/model_runtime/anthropic api/tests/integration_tests/model_runtime/azure_openai api/tests/integration_tests/model_runtime/openai api/tests/integration_tests/model_runtime/chatglm api/tests/integration_tests/model_runtime/google api/tests/integration_tests/model_runtime/xinference api/tests/integration_tests/model_runtime/huggingface_hub/test_llm.py
Expand Down
2 changes: 1 addition & 1 deletion .github/workflows/build-push.yml
Original file line number Diff line number Diff line change
Expand Up @@ -46,7 +46,7 @@ jobs:
with:
images: ${{ env[matrix.image_name_env] }}
tags: |
type=raw,value=latest,enable=${{ github.ref == 'refs/heads/main' && startsWith(github.ref, 'refs/tags/') }}
type=raw,value=latest,enable=${{ startsWith(github.ref, 'refs/tags/') }}
type=ref,event=branch
type=sha,enable=true,priority=100,prefix=,suffix=,format=long
type=raw,value=${{ github.ref_name }},enable=${{ startsWith(github.ref, 'refs/tags/') }}
Expand Down
5 changes: 4 additions & 1 deletion .github/workflows/style.yml
Original file line number Diff line number Diff line change
Expand Up @@ -24,11 +24,14 @@ jobs:
python-version: '3.10'

- name: Python dependencies
run: pip install ruff
run: pip install ruff dotenv-linter

- name: Ruff check
run: ruff check ./api

- name: Dotenv check
run: dotenv-linter ./api/.env.example ./web/.env.example

- name: Lint hints
if: failure()
run: echo "Please run 'dev/reformat' to fix the fixable linting errors."
Expand Down
2 changes: 1 addition & 1 deletion CONTRIBUTING.md
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,7 @@ In terms of licensing, please take a minute to read our short [License and Contr
| Feature Type | Priority |
| ------------------------------------------------------------ | --------------- |
| High-Priority Features as being labeled by a team member | High Priority |
| Popular feature requests from our [community feedback board](https://feedback.dify.ai/) | Medium Priority |
| Popular feature requests from our [community feedback board](https://github.com/langgenius/dify/discussions/categories/feedbacks) | Medium Priority |
| Non-core features and minor enhancements | Low Priority |
| Valuable but not immediate | Future-Feature |

Expand Down
2 changes: 1 addition & 1 deletion CONTRIBUTING_CN.md
Original file line number Diff line number Diff line change
Expand Up @@ -34,7 +34,7 @@
| Feature Type | Priority |
| ------------------------------------------------------------ | --------------- |
| High-Priority Features as being labeled by a team member | High Priority |
| Popular feature requests from our [community feedback board](https://feedback.dify.ai/) | Medium Priority |
| Popular feature requests from our [community feedback board](https://github.com/langgenius/dify/discussions/categories/feedbacks) | Medium Priority |
| Non-core features and minor enhancements | Low Priority |
| Valuable but not immediate | Future-Feature |

Expand Down
295 changes: 189 additions & 106 deletions README.md

Large diffs are not rendered by default.

232 changes: 167 additions & 65 deletions README_CN.md
Original file line number Diff line number Diff line change
@@ -1,78 +1,167 @@
[![](./images/describe.png)](https://dify.ai)
<p align="center">
<a href="./README.md">English</a> |
<a href="./README_CN.md">简体中文</a> |
<a href="./README_JA.md">日本語</a> |
<a href="./README_ES.md">Español</a> |
<a href="./README_KL.md">Klingon</a> |
<a href="./README_FR.md">Français</a>
</p>
![cover-v5-optimized](https://github.com/langgenius/dify/assets/13230914/f9e19af5-61ba-4119-b926-d10c4c06ebab)

<div align="center">
<a href="https://cloud.dify.ai">Dify 云服务</a> ·
<a href="https://docs.dify.ai/getting-started/install-self-hosted">自托管</a> ·
<a href="https://docs.dify.ai">文档</a> ·
<a href="https://cal.com/guchenhe/dify-demo">预约演示</a>
</div>

<p align="center">
<a href="https://dify.ai" target="_blank">
<img alt="Static Badge" src="https://img.shields.io/badge/AI-Dify?logo=AI&logoColor=%20%23f5f5f5&label=Dify&labelColor=%20%23155EEF&color=%23EAECF0"></a>
<img alt="Static Badge" src="https://img.shields.io/badge/Product-F04438"></a>
<a href="https://dify.ai/pricing" target="_blank">
<img alt="Static Badge" src="https://img.shields.io/badge/free-pricing?logo=free&color=%20%23155EEF&label=pricing&labelColor=%20%23528bff"></a>
<a href="https://discord.gg/FngNHpbcY7" target="_blank">
<img src="https://img.shields.io/discord/1082486657678311454?logo=discord"
<img src="https://img.shields.io/discord/1082486657678311454?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb"
alt="chat on Discord"></a>
<a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
<img src="https://img.shields.io/twitter/follow/dify_ai?style=social&logo=X"
<img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
alt="follow on Twitter"></a>
<a href="https://hub.docker.com/u/langgenius" target="_blank">
<img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web"></a>
</p>

<p align="center">
<a href="https://mp.weixin.qq.com/s/TnyfIuH-tPi9o1KNjwVArw" target="_blank">
Dify 发布 AI Agent 能力:基于不同的大型语言模型构建 GPTs 和 Assistants
</a>
<img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
<a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
<img alt="Commits last month" src="https://img.shields.io/github/commit-activity/m/langgenius/dify?labelColor=%20%2332b583&color=%20%2312b76a"></a>
<a href="https://github.com/langgenius/dify/" target="_blank">
<img alt="Issues closed" src="https://img.shields.io/github/issues-search?query=repo%3Alanggenius%2Fdify%20is%3Aclosed&label=issues%20closed&labelColor=%20%237d89b0&color=%20%235d6b98"></a>
<a href="https://github.com/langgenius/dify/discussions/" target="_blank">
<img alt="Discussion posts" src="https://img.shields.io/github/discussions/langgenius/dify?labelColor=%20%239b8afb&color=%20%237a5af8"></a>
</p>

Dify 是一个 LLM 应用开发平台,已经有超过 10 万个应用基于 Dify.AI 构建。它融合了 Backend as Service 和 LLMOps 的理念,涵盖了构建生成式 AI 原生应用所需的核心技术栈,包括一个内置 RAG 引擎。使用 Dify,你可以基于任何模型自部署类似 Assistants API 和 GPTs 的能力。

![](./images/demo.png)

## 使用云端服务

使用 [Dify.AI Cloud](https://dify.ai) 提供开源版本的所有功能,并包含 200 次 GPT 试用额度。

## 为什么选择 Dify

Dify 具有模型中立性,相较 LangChain 等硬编码开发库 Dify 是一个完整的、工程化的技术栈,而相较于 OpenAI 的 Assistants API 你可以完全将服务部署在本地。

| 功能 | Dify.AI | Assistants API | LangChain |
| --- | --- | --- | --- |
| 编程方式 | 面向 API | 面向 API | 面向 Python 代码 |
| 生态策略 | 开源 | 封闭且商用 | 开源 |
| RAG 引擎 | 支持 | 支持 | 不支持 |
| Prompt IDE | 包含 | 包含 | 没有 |
| 支持的 LLMs | 丰富 | 仅 GPT | 丰富 |
| 本地部署 | 支持 | 不支持 | 不适用 |


## 特点

![](./images/models.png)

**1. LLM支持**:与 OpenAI 的 GPT 系列模型集成,或者与开源的 Llama2 系列模型集成。事实上,Dify支持主流的商业模型和开源模型(本地部署或基于 MaaS)。

**2. Prompt IDE**:和团队一起在 Dify 协作,通过可视化的 Prompt 和应用编排工具开发 AI 应用。 支持无缝切换多种大型语言模型。

**3. RAG引擎**:包括各种基于全文索引或向量数据库嵌入的 RAG 能力,允许直接上传 PDF、TXT 等各种文本格式。

**4. AI Agent**:基于 Function Calling 和 ReAct 的 Agent 推理框架,允许用户自定义工具,所见即所得。Dify 提供了十多种内置工具调用能力,如谷歌搜索、DELL·E、Stable Diffusion、WolframAlpha 等。

**5. 持续运营**:监控和分析应用日志和性能,使用生产数据持续改进 Prompt、数据集或模型。

## 在开始之前

**关注我们,您将立即收到 GitHub 上所有新发布版本的通知!**

![star-us](https://github.com/langgenius/dify/assets/100913391/95f37259-7370-4456-a9f0-0bc01ef8642f)

- [网站](https://dify.ai)
- [文档](https://docs.dify.ai)
- [部署文档](https://docs.dify.ai/getting-started/install-self-hosted)
- [常见问题](https://docs.dify.ai/getting-started/faq)
<div align="center">
<a href="./README.md"><img alt="上个月的提交次数" src="https://img.shields.io/badge/英文-d9d9d9"></a>
<a href="./README_CN.md"><img alt="上个月的提交次数" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
<a href="./README_JA.md"><img alt="上个月的提交次数" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
<a href="./README_ES.md"><img alt="上个月的提交次数" src="https://img.shields.io/badge/西班牙语-d9d9d9"></a>
<a href="./README_KL.md"><img alt="上个月的提交次数" src="https://img.shields.io/badge/法语-d9d9d9"></a>
<a href="./README_FR.md"><img alt="上个月的提交次数" src="https://img.shields.io/badge/克林贡语-d9d9d9"></a>
</div>


#

<div align="center">
<a href="https://trendshift.io/repositories/2152" target="_blank"><img src="https://trendshift.io/api/badge/repositories/2152" alt="langgenius%2Fdify | 趋势转变" style="width: 250px; height: 55px;" width="250" height="55"/></a>
</div>

Dify 是一个开源的LLM应用开发平台。其直观的界面结合了AI工作流程、RAG管道、代理功能、模型管理、可观察性功能等,让您可以快速从原型到生产。以下是其核心功能列表:
</br> </br>

**1. 工作流**:
在视觉画布上构建和测试功能强大的AI工作流程,利用以下所有功能以及更多功能。


https://github.com/langgenius/dify/assets/13230914/356df23e-1604-483d-80a6-9517ece318aa



**2. 全面的模型支持**:
与数百种专有/开源LLMs以及数十种推理提供商和自托管解决方案无缝集成,涵盖GPT、Mistral、Llama2以及任何与OpenAI API兼容的模型。完整的支持模型提供商列表可在[此处](https://docs.dify.ai/getting-started/readme/model-providers)找到。

![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3)


**3. Prompt IDE**:
用于制作提示、比较模型性能以及向基于聊天的应用程序添加其他功能(如文本转语音)的直观界面。

**4. RAG Pipeline**:
广泛的RAG功能,涵盖从文档摄入到检索的所有内容,支持从PDF、PPT和其他常见文档格式中提取文本的开箱即用的支持。

**5. Agent 智能体**:
您可以基于LLM函数调用或ReAct定义代理,并为代理添加预构建或自定义工具。Dify为AI代理提供了50多种内置工具,如谷歌搜索、DELL·E、稳定扩散和WolframAlpha等。

**6. LLMOps**:
随时间监视和分析应用程序日志和性能。您可以根据生产数据和注释持续改进提示、数据集和模型。

**7. 后端即服务**:
所有Dify的功能都带有相应的API,因此您可以轻松地将Dify集成到自己的业务逻辑中。


## 功能比较
<table style="width: 100%;">
<tr>
<th align="center">功能</th>
<th align="center">Dify.AI</th>
<th align="center">LangChain</th>
<th align="center">Flowise</th>
<th align="center">OpenAI助理API</th>
</tr>
<tr>
<td align="center">编程方法</td>
<td align="center">API + 应用程序导向</td>
<td align="center">Python代码</td>
<td align="center">应用程序导向</td>
<td align="center">API导向</td>
</tr>
<tr>
<td align="center">支持的LLMs</td>
<td align="center">丰富多样</td>
<td align="center">丰富多样</td>
<td align="center">丰富多样</td>
<td align="center">仅限OpenAI</td>
</tr>
<tr>
<td align="center">RAG引擎</td>
<td align="center">✅</td>
<td align="center">✅</td>
<td align="center">✅</td>
<td align="center">✅</td>
</tr>
<tr>
<td align="center">代理</td>
<td align="center">✅</td>
<td align="center">✅</td>
<td align="center">✅</td>
<td align="center">✅</td>
</tr>
<tr>
<td align="center">工作流程</td>
<td align="center">✅</td>
<td align="center">❌</td>
<td align="center">✅</td>
<td align="center">❌</td>
</tr>
<tr>
<td align="center">可观察性</td>
<td align="center">✅</td>
<td align="center">✅</td>
<td align="center">❌</td>
<td align="center">❌</td>
</tr>
<tr>
<td align="center">企业功能(SSO/访问控制)</td>
<td align="center">✅</td>
<td align="center">❌</td>
<td align="center">❌</td>
<td align="center">❌</td>
</tr>
<tr>
<td align="center">本地部署</td>
<td align="center">✅</td>
<td align="center">✅</td>
<td align="center">✅</td>
<td align="center">❌</td>
</tr>
</table>

## 使用 Dify

- **云 </br>**
我们提供[ Dify 云服务](https://dify.ai),任何人都可以零设置尝试。它提供了自部署版本的所有功能,并在沙盒计划中包含 200 次免费的 GPT-4 调用。

- **自托管 Dify 社区版</br>**
使用这个[入门指南](#quick-start)快速在您的环境中运行 Dify。
使用我们的[文档](https://docs.dify.ai)进行进一步的参考和更深入的说明。

- **面向企业/组织的 Dify</br>**
我们提供额外的面向企业的功能。[与我们安排会议](https://cal.com/guchenhe/30min)[给我们发送电子邮件](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry)讨论企业需求。 </br>
> 对于使用 AWS 的初创公司和中小型企业,请查看 [AWS Marketplace 上的 Dify 高级版](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6),并使用一键部署到您自己的 AWS VPC。它是一个价格实惠的 AMI 产品,提供了使用自定义徽标和品牌创建应用程序的选项。
## 保持领先

在 GitHub 上给 Dify Star,并立即收到新版本的通知。

![star-us](https://github.com/langgenius/dify/assets/13230914/b823edc1-6388-4e25-ad45-2f6b187adbb4)

## 安装社区版

Expand Down Expand Up @@ -110,6 +199,19 @@ docker compose up -d
[![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)


## Contributing

对于那些想要贡献代码的人,请参阅我们的[贡献指南](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)
同时,请考虑通过社交媒体、活动和会议来支持Dify的分享。

> 我们正在寻找贡献者来帮助将Dify翻译成除了中文和英文之外的其他语言。如果您有兴趣帮助,请参阅我们的[i18n README](https://github.com/langgenius/dify/blob/main/web/i18n/README.md)获取更多信息,并在我们的[Discord社区服务器](https://discord.gg/8Tpq4AcN9c)`global-users`频道中留言。
**Contributors**

<a href="https://github.com/langgenius/dify/graphs/contributors">
<img src="https://contrib.rocks/image?repo=langgenius/dify" />
</a>

## 社区与支持

我们欢迎您为 Dify 做出贡献,以帮助改善 Dify。包括:提交代码、问题、新想法,或分享您基于 Dify 创建的有趣且有用的 AI 应用程序。同时,我们也欢迎您在不同的活动、会议和社交媒体上分享 Dify。
Expand Down

0 comments on commit 326f925

Please sign in to comment.