Enhance Code Consistency Across Repository with .editorconfig (#19023)

This commit is contained in:
QuantumGhost 2025-04-29 18:04:33 +08:00 committed by GitHub
parent 226afd4550
commit bd1bbfee4b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
274 changed files with 1271 additions and 1217 deletions

View File

@ -34,4 +34,4 @@ if you see such error message when you open this project in codespaces:
![Alt text](troubleshooting.png)
a simple workaround is change `/signin` endpoint into another one, then login with GitHub account and close the tab, then change it back to `/signin` endpoint. Then all things will be fine.
The reason is `signin` endpoint is not allowed in codespaces, details can be found [here](https://github.com/orgs/community/discussions/5204)
The reason is `signin` endpoint is not allowed in codespaces, details can be found [here](https://github.com/orgs/community/discussions/5204)

View File

@ -2,7 +2,7 @@
// README at: https://github.com/devcontainers/templates/tree/main/src/anaconda
{
"name": "Python 3.12",
"build": {
"build": {
"context": "..",
"dockerfile": "Dockerfile"
},

View File

@ -1,3 +1,3 @@
This file copied into the container along with environment.yml* from the parent
folder. This file is included to prevents the Dockerfile COPY instruction from
failing if no environment.yml is found.
folder. This file is included to prevents the Dockerfile COPY instruction from
failing if no environment.yml is found.

View File

@ -5,18 +5,35 @@ root = true
# Unix-style newlines with a newline ending every file
[*]
charset = utf-8
end_of_line = lf
insert_final_newline = true
trim_trailing_whitespace = true
[*.py]
indent_size = 4
indent_style = space
[*.{yml,yaml}]
indent_style = space
indent_size = 2
[*.toml]
indent_size = 4
indent_style = space
# Markdown and MDX are whitespace sensitive languages.
# Do not remove trailing spaces.
[*.{md,mdx}]
trim_trailing_whitespace = false
# Matches multiple files with brace expansion notation
# Set default charset
[*.{js,tsx}]
charset = utf-8
indent_style = space
indent_size = 2
# Matches the exact files either package.json or .travis.yml
[{package.json,.travis.yml}]
# Matches the exact files package.json
[package.json]
indent_style = space
indent_size = 2

2
.gitattributes vendored
View File

@ -1,5 +1,5 @@
# Ensure that .sh scripts use LF as line separator, even if they are checked out
# to Windows(NTFS) file-system, by a user of Docker for Windows.
# to Windows(NTFS) file-system, by a user of Docker for Windows.
# These .sh scripts will be run from the Container after `docker compose up -d`.
# If they appear to be CRLF style, Dash from the Container will fail to execute
# them.

View File

@ -0,0 +1,22 @@
{
"Verbose": false,
"Debug": false,
"IgnoreDefaults": false,
"SpacesAfterTabs": false,
"NoColor": false,
"Exclude": [
"^web/public/vs/",
"^web/public/pdf.worker.min.mjs$",
"web/app/components/base/icons/src/vender/"
],
"AllowedContentTypes": [],
"PassedFiles": [],
"Disable": {
"EndOfLine": false,
"Indentation": false,
"IndentSize": true,
"InsertFinalNewline": false,
"TrimTrailingWhitespace": false,
"MaxLineLength": false
}
}

View File

@ -9,6 +9,12 @@ concurrency:
group: style-${{ github.head_ref || github.run_id }}
cancel-in-progress: true
permissions:
checks: write
statuses: write
contents: read
jobs:
python-style:
name: Python Style
@ -163,3 +169,14 @@ jobs:
VALIDATE_DOCKERFILE_HADOLINT: true
VALIDATE_XML: true
VALIDATE_YAML: true
- name: EditorConfig checks
uses: super-linter/super-linter/slim@v7
env:
DEFAULT_BRANCH: main
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
IGNORE_GENERATED_FILES: true
IGNORE_GITIGNORED_FILES: true
# EditorConfig validation
VALIDATE_EDITORCONFIG: true
EDITORCONFIG_FILE_NAME: editorconfig-checker.json

View File

@ -90,4 +90,4 @@ Recomendamos revisar este documento cuidadosamente antes de proceder con la conf
No dudes en contactarnos si encuentras algún problema durante el proceso de configuración.
## Obteniendo Ayuda
Si alguna vez te quedas atascado o tienes una pregunta urgente mientras contribuyes, simplemente envíanos tus consultas a través del issue relacionado de GitHub, o únete a nuestro [Discord](https://discord.gg/8Tpq4AcN9c) para una charla rápida.
Si alguna vez te quedas atascado o tienes una pregunta urgente mientras contribuyes, simplemente envíanos tus consultas a través del issue relacionado de GitHub, o únete a nuestro [Discord](https://discord.gg/8Tpq4AcN9c) para una charla rápida.

View File

@ -90,4 +90,4 @@ Nous recommandons de revoir attentivement ce document avant de procéder à la c
N'hésitez pas à nous contacter si vous rencontrez des problèmes pendant le processus de configuration.
## Obtenir de l'aide
Si jamais vous êtes bloqué ou avez une question urgente en contribuant, envoyez-nous simplement vos questions via le problème GitHub concerné, ou rejoignez notre [Discord](https://discord.gg/8Tpq4AcN9c) pour une discussion rapide.
Si jamais vous êtes bloqué ou avez une question urgente en contribuant, envoyez-nous simplement vos questions via le problème GitHub concerné, ou rejoignez notre [Discord](https://discord.gg/8Tpq4AcN9c) pour une discussion rapide.

View File

@ -90,4 +90,4 @@ PR 설명에 기존 이슈를 연결하거나 새 이슈를 여는 것을 잊지
설정 과정에서 문제가 발생하면 언제든지 연락해 주세요.
## 도움 받기
기여하는 동안 막히거나 긴급한 질문이 있으면, 관련 GitHub 이슈를 통해 질문을 보내거나, 빠른 대화를 위해 우리의 [Discord](https://discord.gg/8Tpq4AcN9c)에 참여하세요.
기여하는 동안 막히거나 긴급한 질문이 있으면, 관련 GitHub 이슈를 통해 질문을 보내거나, 빠른 대화를 위해 우리의 [Discord](https://discord.gg/8Tpq4AcN9c)에 참여하세요.

View File

@ -90,4 +90,4 @@ Recomendamos revisar este documento cuidadosamente antes de prosseguir com a con
Sinta-se à vontade para entrar em contato se encontrar quaisquer problemas durante o processo de configuração.
## Obtendo Ajuda
Se você ficar preso ou tiver uma dúvida urgente enquanto contribui, simplesmente envie suas perguntas através do problema relacionado no GitHub, ou entre no nosso [Discord](https://discord.gg/8Tpq4AcN9c) para uma conversa rápida.
Se você ficar preso ou tiver uma dúvida urgente enquanto contribui, simplesmente envie suas perguntas através do problema relacionado no GitHub, ou entre no nosso [Discord](https://discord.gg/8Tpq4AcN9c) para uma conversa rápida.

View File

@ -90,4 +90,4 @@ Kuruluma geçmeden önce bu belgeyi dikkatlice incelemenizi öneririz, çünkü
Kurulum süreci sırasında herhangi bir sorunla karşılaşırsanız bizimle iletişime geçmekten çekinmeyin.
## Yardım Almak
Katkıda bulunurken takılırsanız veya yanıcı bir sorunuz olursa, sorularınızı ilgili GitHub sorunu aracılığıyla bize gönderin veya hızlı bir sohbet için [Discord'umuza](https://discord.gg/8Tpq4AcN9c) katılın.
Katkıda bulunurken takılırsanız veya yanıcı bir sorunuz olursa, sorularınızı ilgili GitHub sorunu aracılığıyla bize gönderin veya hızlı bir sohbet için [Discord'umuza](https://discord.gg/8Tpq4AcN9c) katılın.

View File

@ -1,259 +1,259 @@
![cover-v5-optimized](https://github.com/langgenius/dify/assets/13230914/f9e19af5-61ba-4119-b926-d10c4c06ebab)
<p align="center">
📌 <a href="https://dify.ai/blog/introducing-dify-workflow-file-upload-a-demo-on-ai-podcast">Predstavljamo nalaganje datotek Dify Workflow: znova ustvarite Google NotebookLM Podcast</a>
</p>
<p align="center">
<a href="https://cloud.dify.ai">Dify Cloud</a> ·
<a href="https://docs.dify.ai/getting-started/install-self-hosted">Samostojno gostovanje</a> ·
<a href="https://docs.dify.ai">Dokumentacija</a> ·
<a href="https://dify.ai/pricing">Pregled ponudb izdelkov Dify</a>
</p>
<p align="center">
<a href="https://dify.ai" target="_blank">
<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&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?logo=X&color=%20%23f5f5f5"
alt="follow on X(Twitter)"></a>
<a href="https://www.linkedin.com/company/langgenius/" target="_blank">
<img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
alt="follow on LinkedIn"></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?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>
<p align="center">
<a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
<a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
<a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
<a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
<a href="./README_FR.md"><img alt="README en Français" src="https://img.shields.io/badge/Français-d9d9d9"></a>
<a href="./README_KL.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
<a href="./README_KR.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
<a href="./README_AR.md"><img alt="README بالعربية" src="https://img.shields.io/badge/العربية-d9d9d9"></a>
<a href="./README_TR.md"><img alt="Türkçe README" src="https://img.shields.io/badge/Türkçe-d9d9d9"></a>
<a href="./README_VI.md"><img alt="README Tiếng Việt" src="https://img.shields.io/badge/Ti%E1%BA%BFng%20Vi%E1%BB%87t-d9d9d9"></a>
<a href="./README_SI.md"><img alt="README Slovenščina" src="https://img.shields.io/badge/Sloven%C5%A1%C4%8Dina-d9d9d9"></a>
<a href="./README_BN.md"><img alt="README in বাংলা" src="https://img.shields.io/badge/বাংলা-d9d9d9"></a>
</p>
Dify je odprtokodna platforma za razvoj aplikacij LLM. Njegov intuitivni vmesnik združuje agentski potek dela z umetno inteligenco, cevovod RAG, zmogljivosti agentov, upravljanje modelov, funkcije opazovanja in več, kar vam omogoča hiter prehod od prototipa do proizvodnje.
## Hitri začetek
> Preden namestite Dify, se prepričajte, da vaša naprava izpolnjuje naslednje minimalne sistemske zahteve:
>
>- CPU >= 2 Core
>- RAM >= 4 GiB
</br>
Najlažji način za zagon strežnika Dify je prek docker compose . Preden zaženete Dify z naslednjimi ukazi, se prepričajte, da sta Docker in Docker Compose nameščena na vašem računalniku:
```bash
cd dify
cd docker
cp .env.example .env
docker compose up -d
```
Po zagonu lahko dostopate do nadzorne plošče Dify v brskalniku na [http://localhost/install](http://localhost/install) in začnete postopek inicializacije.
#### Iskanje pomoči
Prosimo, glejte naša pogosta vprašanja [FAQ](https://docs.dify.ai/getting-started/install-self-hosted/faqs) če naletite na težave pri nastavitvi Dify. Če imate še vedno težave, se obrnite na [skupnost ali nas](#community--contact).
> Če želite prispevati k Difyju ali narediti dodaten razvoj, glejte naš vodnik za [uvajanje iz izvorne kode](https://docs.dify.ai/getting-started/install-self-hosted/local-source-code)
## Ključne značilnosti
**1. Potek dela**:
Zgradite in preizkusite zmogljive poteke dela AI na vizualnem platnu, pri čemer izkoristite vse naslednje funkcije in več.
https://github.com/langgenius/dify/assets/13230914/356df23e-1604-483d-80a6-9517ece318aa
**2. Celovita podpora za modele**:
Brezhibna integracija s stotinami lastniških/odprtokodnih LLM-jev ducatov ponudnikov sklepanja in samostojnih rešitev, ki pokrivajo GPT, Mistral, Llama3 in vse modele, združljive z API-jem OpenAI. Celoten seznam podprtih ponudnikov modelov najdete [tukaj](https://docs.dify.ai/getting-started/readme/model-providers).
![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3)
**3. Prompt IDE**:
intuitivni vmesnik za ustvarjanje pozivov, primerjavo zmogljivosti modela in dodajanje dodatnih funkcij, kot je pretvorba besedila v govor, aplikaciji, ki temelji na klepetu.
**4. RAG Pipeline**:
E Obsežne zmogljivosti RAG, ki pokrivajo vse od vnosa dokumenta do priklica, s podporo za ekstrakcijo besedila iz datotek PDF, PPT in drugih običajnih formatov dokumentov.
**5. Agent capabilities**:
definirate lahko agente, ki temeljijo na klicanju funkcij LLM ali ReAct, in dodate vnaprej izdelana orodja ali orodja po meri za agenta. Dify ponuja več kot 50 vgrajenih orodij za agente AI, kot so Google Search, DALL·E, Stable Diffusion in WolframAlpha.
**6. LLMOps**:
Spremljajte in analizirajte dnevnike aplikacij in učinkovitost skozi čas. Pozive, nabore podatkov in modele lahko nenehno izboljšujete na podlagi proizvodnih podatkov in opomb.
**7. Backend-as-a-Service**:
AVse ponudbe Difyja so opremljene z ustreznimi API-ji, tako da lahko Dify brez težav integrirate v svojo poslovno logiko.
## Primerjava Funkcij
<table style="width: 100%;">
<tr>
<th align="center">Funkcija</th>
<th align="center">Dify.AI</th>
<th align="center">LangChain</th>
<th align="center">Flowise</th>
<th align="center">OpenAI Assistants API</th>
</tr>
<tr>
<td align="center">Programski pristop</td>
<td align="center">API + usmerjeno v aplikacije</td>
<td align="center">Python koda</td>
<td align="center">Usmerjeno v aplikacije</td>
<td align="center">Usmerjeno v API</td>
</tr>
<tr>
<td align="center">Podprti LLM-ji</td>
<td align="center">Bogata izbira</td>
<td align="center">Bogata izbira</td>
<td align="center">Bogata izbira</td>
<td align="center">Samo OpenAI</td>
</tr>
<tr>
<td align="center">RAG pogon</td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
</tr>
<tr>
<td align="center">Agent</td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
</tr>
<tr>
<td align="center">Potek dela</td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
</tr>
<tr>
<td align="center">Spremljanje</td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
</tr>
<tr>
<td align="center">Funkcija za podjetja (SSO/nadzor dostopa)</td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
</tr>
<tr>
<td align="center">Lokalna namestitev</td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
</tr>
</table>
## Uporaba Dify
- **Cloud </br>**
Gostimo storitev Dify Cloud za vsakogar, ki jo lahko preizkusite brez nastavitev. Zagotavlja vse zmožnosti različice za samostojno namestitev in vključuje 200 brezplačnih klicev GPT-4 v načrtu peskovnika.
- **Self-hosting Dify Community Edition</br>**
Hitro zaženite Dify v svojem okolju s tem [začetnim vodnikom](#quick-start) . Za dodatne reference in podrobnejša navodila uporabite našo [dokumentacijo](https://docs.dify.ai) .
- **Dify za podjetja/organizacije</br>**
Ponujamo dodatne funkcije, osredotočene na podjetja. Zabeležite svoja vprašanja prek tega klepetalnega robota ali nam pošljite e-pošto, da se pogovorimo o potrebah podjetja. </br>
> Za novoustanovljena podjetja in mala podjetja, ki uporabljajo AWS, si oglejte Dify Premium na AWS Marketplace in ga z enim klikom uvedite v svoj AWS VPC. To je cenovno ugodna ponudba AMI z možnostjo ustvarjanja aplikacij z logotipom in blagovno znamko po meri.
## Staying ahead
Star Dify on GitHub and be instantly notified of new releases.
![star-us](https://github.com/langgenius/dify/assets/13230914/b823edc1-6388-4e25-ad45-2f6b187adbb4)
## Napredne nastavitve
Če morate prilagoditi konfiguracijo, si oglejte komentarje v naši datoteki .env.example in posodobite ustrezne vrednosti v svoji .env datoteki. Poleg tega boste morda morali prilagoditi docker-compose.yamlsamo datoteko, na primer spremeniti različice slike, preslikave vrat ali namestitve nosilca, glede na vaše specifično okolje in zahteve za uvajanje. Po kakršnih koli spremembah ponovno zaženite docker-compose up -d. Celoten seznam razpoložljivih spremenljivk okolja najdete tukaj .
Če želite konfigurirati visoko razpoložljivo nastavitev, so na voljo Helm Charts in datoteke YAML, ki jih prispeva skupnost, ki omogočajo uvedbo Difyja v Kubernetes.
- [Helm Chart by @LeoQuote](https://github.com/douban/charts/tree/master/charts/dify)
- [Helm Chart by @BorisPolonsky](https://github.com/BorisPolonsky/dify-helm)
- [YAML file by @Winson-030](https://github.com/Winson-030/dify-kubernetes)
- [YAML file by @wyy-holding](https://github.com/wyy-holding/dify-k8s)
#### Uporaba Terraform za uvajanje
namestite Dify v Cloud Platform z enim klikom z uporabo [terraform](https://www.terraform.io/)
##### Azure Global
- [Azure Terraform by @nikawang](https://github.com/nikawang/dify-azure-terraform)
##### Google Cloud
- [Google Cloud Terraform by @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
#### Uporaba AWS CDK za uvajanje
Uvedite Dify v AWS z uporabo [CDK](https://aws.amazon.com/cdk/)
##### AWS
- [AWS CDK by @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
## Prispevam
Za tiste, ki bi radi prispevali kodo, si oglejte naš vodnik za prispevke . Hkrati vas prosimo, da podprete Dify tako, da ga delite na družbenih medijih ter na dogodkih in konferencah.
> Iščemo sodelavce za pomoč pri prevajanju Difyja v jezike, ki niso mandarinščina ali angleščina. Če želite pomagati, si oglejte i18n README za več informacij in nam pustite komentar v global-userskanalu našega strežnika skupnosti Discord .
## Skupnost in stik
* [Github Discussion](https://github.com/langgenius/dify/discussions). Najboljše za: izmenjavo povratnih informacij in postavljanje vprašanj.
* [GitHub Issues](https://github.com/langgenius/dify/issues). Najboljše za: hrošče, na katere naletite pri uporabi Dify.AI, in predloge funkcij. Oglejte si naš [vodnik za prispevke](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
* [Discord](https://discord.gg/FngNHpbcY7). Najboljše za: deljenje vaših aplikacij in druženje s skupnostjo.
* [X(Twitter)](https://twitter.com/dify_ai). Najboljše za: deljenje vaših aplikacij in druženje s skupnostjo.
**Contributors**
<a href="https://github.com/langgenius/dify/graphs/contributors">
<img src="https://contrib.rocks/image?repo=langgenius/dify" />
</a>
## Star history
[![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)
## Varnostno razkritje
Zaradi zaščite vaše zasebnosti se izogibajte objavljanju varnostnih vprašanj na GitHub. Namesto tega pošljite vprašanja na security@dify.ai in zagotovili vam bomo podrobnejši odgovor.
## Licenca
To skladišče je na voljo pod [odprtokodno licenco Dify](LICENSE) , ki je v bistvu Apache 2.0 z nekaj dodatnimi omejitvami.
![cover-v5-optimized](https://github.com/langgenius/dify/assets/13230914/f9e19af5-61ba-4119-b926-d10c4c06ebab)
<p align="center">
📌 <a href="https://dify.ai/blog/introducing-dify-workflow-file-upload-a-demo-on-ai-podcast">Predstavljamo nalaganje datotek Dify Workflow: znova ustvarite Google NotebookLM Podcast</a>
</p>
<p align="center">
<a href="https://cloud.dify.ai">Dify Cloud</a> ·
<a href="https://docs.dify.ai/getting-started/install-self-hosted">Samostojno gostovanje</a> ·
<a href="https://docs.dify.ai">Dokumentacija</a> ·
<a href="https://dify.ai/pricing">Pregled ponudb izdelkov Dify</a>
</p>
<p align="center">
<a href="https://dify.ai" target="_blank">
<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&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?logo=X&color=%20%23f5f5f5"
alt="follow on X(Twitter)"></a>
<a href="https://www.linkedin.com/company/langgenius/" target="_blank">
<img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
alt="follow on LinkedIn"></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?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>
<p align="center">
<a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
<a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
<a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
<a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
<a href="./README_FR.md"><img alt="README en Français" src="https://img.shields.io/badge/Français-d9d9d9"></a>
<a href="./README_KL.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
<a href="./README_KR.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
<a href="./README_AR.md"><img alt="README بالعربية" src="https://img.shields.io/badge/العربية-d9d9d9"></a>
<a href="./README_TR.md"><img alt="Türkçe README" src="https://img.shields.io/badge/Türkçe-d9d9d9"></a>
<a href="./README_VI.md"><img alt="README Tiếng Việt" src="https://img.shields.io/badge/Ti%E1%BA%BFng%20Vi%E1%BB%87t-d9d9d9"></a>
<a href="./README_SI.md"><img alt="README Slovenščina" src="https://img.shields.io/badge/Sloven%C5%A1%C4%8Dina-d9d9d9"></a>
<a href="./README_BN.md"><img alt="README in বাংলা" src="https://img.shields.io/badge/বাংলা-d9d9d9"></a>
</p>
Dify je odprtokodna platforma za razvoj aplikacij LLM. Njegov intuitivni vmesnik združuje agentski potek dela z umetno inteligenco, cevovod RAG, zmogljivosti agentov, upravljanje modelov, funkcije opazovanja in več, kar vam omogoča hiter prehod od prototipa do proizvodnje.
## Hitri začetek
> Preden namestite Dify, se prepričajte, da vaša naprava izpolnjuje naslednje minimalne sistemske zahteve:
>
>- CPU >= 2 Core
>- RAM >= 4 GiB
</br>
Najlažji način za zagon strežnika Dify je prek docker compose . Preden zaženete Dify z naslednjimi ukazi, se prepričajte, da sta Docker in Docker Compose nameščena na vašem računalniku:
```bash
cd dify
cd docker
cp .env.example .env
docker compose up -d
```
Po zagonu lahko dostopate do nadzorne plošče Dify v brskalniku na [http://localhost/install](http://localhost/install) in začnete postopek inicializacije.
#### Iskanje pomoči
Prosimo, glejte naša pogosta vprašanja [FAQ](https://docs.dify.ai/getting-started/install-self-hosted/faqs) če naletite na težave pri nastavitvi Dify. Če imate še vedno težave, se obrnite na [skupnost ali nas](#community--contact).
> Če želite prispevati k Difyju ali narediti dodaten razvoj, glejte naš vodnik za [uvajanje iz izvorne kode](https://docs.dify.ai/getting-started/install-self-hosted/local-source-code)
## Ključne značilnosti
**1. Potek dela**:
Zgradite in preizkusite zmogljive poteke dela AI na vizualnem platnu, pri čemer izkoristite vse naslednje funkcije in več.
https://github.com/langgenius/dify/assets/13230914/356df23e-1604-483d-80a6-9517ece318aa
**2. Celovita podpora za modele**:
Brezhibna integracija s stotinami lastniških/odprtokodnih LLM-jev ducatov ponudnikov sklepanja in samostojnih rešitev, ki pokrivajo GPT, Mistral, Llama3 in vse modele, združljive z API-jem OpenAI. Celoten seznam podprtih ponudnikov modelov najdete [tukaj](https://docs.dify.ai/getting-started/readme/model-providers).
![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3)
**3. Prompt IDE**:
intuitivni vmesnik za ustvarjanje pozivov, primerjavo zmogljivosti modela in dodajanje dodatnih funkcij, kot je pretvorba besedila v govor, aplikaciji, ki temelji na klepetu.
**4. RAG Pipeline**:
E Obsežne zmogljivosti RAG, ki pokrivajo vse od vnosa dokumenta do priklica, s podporo za ekstrakcijo besedila iz datotek PDF, PPT in drugih običajnih formatov dokumentov.
**5. Agent capabilities**:
definirate lahko agente, ki temeljijo na klicanju funkcij LLM ali ReAct, in dodate vnaprej izdelana orodja ali orodja po meri za agenta. Dify ponuja več kot 50 vgrajenih orodij za agente AI, kot so Google Search, DALL·E, Stable Diffusion in WolframAlpha.
**6. LLMOps**:
Spremljajte in analizirajte dnevnike aplikacij in učinkovitost skozi čas. Pozive, nabore podatkov in modele lahko nenehno izboljšujete na podlagi proizvodnih podatkov in opomb.
**7. Backend-as-a-Service**:
AVse ponudbe Difyja so opremljene z ustreznimi API-ji, tako da lahko Dify brez težav integrirate v svojo poslovno logiko.
## Primerjava Funkcij
<table style="width: 100%;">
<tr>
<th align="center">Funkcija</th>
<th align="center">Dify.AI</th>
<th align="center">LangChain</th>
<th align="center">Flowise</th>
<th align="center">OpenAI Assistants API</th>
</tr>
<tr>
<td align="center">Programski pristop</td>
<td align="center">API + usmerjeno v aplikacije</td>
<td align="center">Python koda</td>
<td align="center">Usmerjeno v aplikacije</td>
<td align="center">Usmerjeno v API</td>
</tr>
<tr>
<td align="center">Podprti LLM-ji</td>
<td align="center">Bogata izbira</td>
<td align="center">Bogata izbira</td>
<td align="center">Bogata izbira</td>
<td align="center">Samo OpenAI</td>
</tr>
<tr>
<td align="center">RAG pogon</td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
</tr>
<tr>
<td align="center">Agent</td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
</tr>
<tr>
<td align="center">Potek dela</td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
</tr>
<tr>
<td align="center">Spremljanje</td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
</tr>
<tr>
<td align="center">Funkcija za podjetja (SSO/nadzor dostopa)</td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
</tr>
<tr>
<td align="center">Lokalna namestitev</td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
</tr>
</table>
## Uporaba Dify
- **Cloud </br>**
Gostimo storitev Dify Cloud za vsakogar, ki jo lahko preizkusite brez nastavitev. Zagotavlja vse zmožnosti različice za samostojno namestitev in vključuje 200 brezplačnih klicev GPT-4 v načrtu peskovnika.
- **Self-hosting Dify Community Edition</br>**
Hitro zaženite Dify v svojem okolju s tem [začetnim vodnikom](#quick-start) . Za dodatne reference in podrobnejša navodila uporabite našo [dokumentacijo](https://docs.dify.ai) .
- **Dify za podjetja/organizacije</br>**
Ponujamo dodatne funkcije, osredotočene na podjetja. Zabeležite svoja vprašanja prek tega klepetalnega robota ali nam pošljite e-pošto, da se pogovorimo o potrebah podjetja. </br>
> Za novoustanovljena podjetja in mala podjetja, ki uporabljajo AWS, si oglejte Dify Premium na AWS Marketplace in ga z enim klikom uvedite v svoj AWS VPC. To je cenovno ugodna ponudba AMI z možnostjo ustvarjanja aplikacij z logotipom in blagovno znamko po meri.
## Staying ahead
Star Dify on GitHub and be instantly notified of new releases.
![star-us](https://github.com/langgenius/dify/assets/13230914/b823edc1-6388-4e25-ad45-2f6b187adbb4)
## Napredne nastavitve
Če morate prilagoditi konfiguracijo, si oglejte komentarje v naši datoteki .env.example in posodobite ustrezne vrednosti v svoji .env datoteki. Poleg tega boste morda morali prilagoditi docker-compose.yamlsamo datoteko, na primer spremeniti različice slike, preslikave vrat ali namestitve nosilca, glede na vaše specifično okolje in zahteve za uvajanje. Po kakršnih koli spremembah ponovno zaženite docker-compose up -d. Celoten seznam razpoložljivih spremenljivk okolja najdete tukaj .
Če želite konfigurirati visoko razpoložljivo nastavitev, so na voljo Helm Charts in datoteke YAML, ki jih prispeva skupnost, ki omogočajo uvedbo Difyja v Kubernetes.
- [Helm Chart by @LeoQuote](https://github.com/douban/charts/tree/master/charts/dify)
- [Helm Chart by @BorisPolonsky](https://github.com/BorisPolonsky/dify-helm)
- [YAML file by @Winson-030](https://github.com/Winson-030/dify-kubernetes)
- [YAML file by @wyy-holding](https://github.com/wyy-holding/dify-k8s)
#### Uporaba Terraform za uvajanje
namestite Dify v Cloud Platform z enim klikom z uporabo [terraform](https://www.terraform.io/)
##### Azure Global
- [Azure Terraform by @nikawang](https://github.com/nikawang/dify-azure-terraform)
##### Google Cloud
- [Google Cloud Terraform by @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
#### Uporaba AWS CDK za uvajanje
Uvedite Dify v AWS z uporabo [CDK](https://aws.amazon.com/cdk/)
##### AWS
- [AWS CDK by @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
## Prispevam
Za tiste, ki bi radi prispevali kodo, si oglejte naš vodnik za prispevke . Hkrati vas prosimo, da podprete Dify tako, da ga delite na družbenih medijih ter na dogodkih in konferencah.
> Iščemo sodelavce za pomoč pri prevajanju Difyja v jezike, ki niso mandarinščina ali angleščina. Če želite pomagati, si oglejte i18n README za več informacij in nam pustite komentar v global-userskanalu našega strežnika skupnosti Discord .
## Skupnost in stik
* [Github Discussion](https://github.com/langgenius/dify/discussions). Najboljše za: izmenjavo povratnih informacij in postavljanje vprašanj.
* [GitHub Issues](https://github.com/langgenius/dify/issues). Najboljše za: hrošče, na katere naletite pri uporabi Dify.AI, in predloge funkcij. Oglejte si naš [vodnik za prispevke](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
* [Discord](https://discord.gg/FngNHpbcY7). Najboljše za: deljenje vaših aplikacij in druženje s skupnostjo.
* [X(Twitter)](https://twitter.com/dify_ai). Najboljše za: deljenje vaših aplikacij in druženje s skupnostjo.
**Contributors**
<a href="https://github.com/langgenius/dify/graphs/contributors">
<img src="https://contrib.rocks/image?repo=langgenius/dify" />
</a>
## Star history
[![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)
## Varnostno razkritje
Zaradi zaščite vaše zasebnosti se izogibajte objavljanju varnostnih vprašanj na GitHub. Namesto tega pošljite vprašanja na security@dify.ai in zagotovili vam bomo podrobnejši odgovor.
## Licenca
To skladišče je na voljo pod [odprtokodno licenco Dify](LICENSE) , ki je v bistvu Apache 2.0 z nekaj dodatnimi omejitvami.

View File

@ -16,4 +16,4 @@ logs
.ruff_cache
# venv
.venv
.venv

View File

@ -444,13 +444,13 @@ def convert_to_agent_apps():
WHERE a.mode = 'chat'
AND am.agent_mode is not null
AND (
am.agent_mode like '%"strategy": "function_call"%'
am.agent_mode like '%"strategy": "function_call"%'
OR am.agent_mode like '%"strategy": "react"%'
)
)
AND (
am.agent_mode like '{"enabled": true%'
am.agent_mode like '{"enabled": true%'
OR am.agent_mode like '{"max_iteration": %'
) ORDER BY a.created_at DESC LIMIT 1000
) ORDER BY a.created_at DESC LIMIT 1000
"""
with db.engine.begin() as conn:

View File

@ -1,4 +1,4 @@
ENGLISH_REACT_COMPLETION_PROMPT_TEMPLATES = """Respond to the human as helpfully and accurately as possible.
ENGLISH_REACT_COMPLETION_PROMPT_TEMPLATES = """Respond to the human as helpfully and accurately as possible.
{{instruction}}
@ -47,7 +47,7 @@ Thought:""" # noqa: E501
ENGLISH_REACT_COMPLETION_AGENT_SCRATCHPAD_TEMPLATES = """Observation: {{observation}}
Thought:"""
ENGLISH_REACT_CHAT_PROMPT_TEMPLATES = """Respond to the human as helpfully and accurately as possible.
ENGLISH_REACT_CHAT_PROMPT_TEMPLATES = """Respond to the human as helpfully and accurately as possible.
{{instruction}}

View File

@ -1 +1 @@
1
1

View File

@ -10,13 +10,13 @@ class NodeJsTemplateTransformer(TemplateTransformer):
f"""
// declare main function
{cls._code_placeholder}
// decode and prepare input object
var inputs_obj = JSON.parse(Buffer.from('{cls._inputs_placeholder}', 'base64').toString('utf-8'))
// execute main function
var output_obj = main(inputs_obj)
// convert output to json and print
var output_json = JSON.stringify(output_obj)
var result = `<<RESULT>>${{output_json}}<<RESULT>>`

View File

@ -21,20 +21,20 @@ class Jinja2TemplateTransformer(TemplateTransformer):
import jinja2
template = jinja2.Template('''{cls._code_placeholder}''')
return template.render(**inputs)
import json
from base64 import b64decode
# decode and prepare input dict
inputs_obj = json.loads(b64decode('{cls._inputs_placeholder}').decode('utf-8'))
# execute main function
output = main(**inputs_obj)
# convert output and print
result = f'''<<RESULT>>{{output}}<<RESULT>>'''
print(result)
""")
return runner_script
@ -43,15 +43,15 @@ class Jinja2TemplateTransformer(TemplateTransformer):
preload_script = dedent("""
import jinja2
from base64 import b64decode
def _jinja2_preload_():
# prepare jinja2 environment, load template and render before to avoid sandbox issue
template = jinja2.Template('{{s}}')
template.render(s='a')
if __name__ == '__main__':
_jinja2_preload_()
""")
return preload_script

View File

@ -9,16 +9,16 @@ class Python3TemplateTransformer(TemplateTransformer):
runner_script = dedent(f"""
# declare main function
{cls._code_placeholder}
import json
from base64 import b64decode
# decode and prepare input dict
inputs_obj = json.loads(b64decode('{cls._inputs_placeholder}').decode('utf-8'))
# execute main function
output_obj = main(**inputs_obj)
# convert output to json and print
output_json = json.dumps(output_obj, indent=4)
result = f'''<<RESULT>>{{output_json}}<<RESULT>>'''

View File

@ -1,5 +1,5 @@
# Written by YORKI MINAKO🤡, Edited by Xiaoyi
CONVERSATION_TITLE_PROMPT = """You need to decompose the user's input into "subject" and "intention" in order to accurately figure out what the user's input language actually is.
CONVERSATION_TITLE_PROMPT = """You need to decompose the user's input into "subject" and "intention" in order to accurately figure out what the user's input language actually is.
Notice: the language type user uses could be diverse, which can be English, Chinese, Italian, Español, Arabic, Japanese, French, and etc.
ENSURE your output is in the SAME language as the user's input!
Your output is restricted only to: (Input language) Intention + Subject(short as possible)
@ -58,7 +58,7 @@ User Input: yo, 你今天咋样?
"Your Output": "查询今日我的状态☺️"
}
User Input:
User Input:
""" # noqa: E501
PYTHON_CODE_GENERATOR_PROMPT_TEMPLATE = (
@ -163,11 +163,11 @@ Here is a task description for which I would like you to create a high-quality p
{{TASK_DESCRIPTION}}
</task_description>
Based on task description, please create a well-structured prompt template that another AI could use to consistently complete the task. The prompt template should include:
- Do not include <input> or <output> section and variables in the prompt, assume user will add them at their own will.
- Clear instructions for the AI that will be using this prompt, demarcated with <instruction> tags. The instructions should provide step-by-step directions on how to complete the task using the input variables. Also Specifies in the instructions that the output should not contain any xml tag.
- Relevant examples if needed to clarify the task further, demarcated with <example> tags. Do not include variables in the prompt. Give three pairs of input and output examples.
- Do not include <input> or <output> section and variables in the prompt, assume user will add them at their own will.
- Clear instructions for the AI that will be using this prompt, demarcated with <instruction> tags. The instructions should provide step-by-step directions on how to complete the task using the input variables. Also Specifies in the instructions that the output should not contain any xml tag.
- Relevant examples if needed to clarify the task further, demarcated with <example> tags. Do not include variables in the prompt. Give three pairs of input and output examples.
- Include other relevant sections demarcated with appropriate XML tags like <examples>, <instruction>.
- Use the same language as task description.
- Use the same language as task description.
- Output in ``` xml ``` and start with <instruction>
Please generate the full prompt template with at least 300 words and output only the prompt template.
""" # noqa: E501
@ -178,28 +178,28 @@ Here is a task description for which I would like you to create a high-quality p
{{TASK_DESCRIPTION}}
</task_description>
Based on task description, please create a well-structured prompt template that another AI could use to consistently complete the task. The prompt template should include:
- Descriptive variable names surrounded by {{ }} (two curly brackets) to indicate where the actual values will be substituted in. Choose variable names that clearly indicate the type of value expected. Variable names have to be composed of number, english alphabets and underline and nothing else.
- Clear instructions for the AI that will be using this prompt, demarcated with <instruction> tags. The instructions should provide step-by-step directions on how to complete the task using the input variables. Also Specifies in the instructions that the output should not contain any xml tag.
- Relevant examples if needed to clarify the task further, demarcated with <example> tags. Do not use curly brackets any other than in <instruction> section.
- Descriptive variable names surrounded by {{ }} (two curly brackets) to indicate where the actual values will be substituted in. Choose variable names that clearly indicate the type of value expected. Variable names have to be composed of number, english alphabets and underline and nothing else.
- Clear instructions for the AI that will be using this prompt, demarcated with <instruction> tags. The instructions should provide step-by-step directions on how to complete the task using the input variables. Also Specifies in the instructions that the output should not contain any xml tag.
- Relevant examples if needed to clarify the task further, demarcated with <example> tags. Do not use curly brackets any other than in <instruction> section.
- Any other relevant sections demarcated with appropriate XML tags like <input>, <output>, etc.
- Use the same language as task description.
- Use the same language as task description.
- Output in ``` xml ``` and start with <instruction>
Please generate the full prompt template and output only the prompt template.
""" # noqa: E501
RULE_CONFIG_PARAMETER_GENERATE_TEMPLATE = """
I need to extract the following information from the input text. The <information to be extracted> tag specifies the 'type', 'description' and 'required' of the information to be extracted.
I need to extract the following information from the input text. The <information to be extracted> tag specifies the 'type', 'description' and 'required' of the information to be extracted.
<information to be extracted>
variables name bounded two double curly brackets. Variable name has to be composed of number, english alphabets and underline and nothing else.
variables name bounded two double curly brackets. Variable name has to be composed of number, english alphabets and underline and nothing else.
</information to be extracted>
Step 1: Carefully read the input and understand the structure of the expected output.
Step 2: Extract relevant parameters from the provided text based on the name and description of object.
Step 2: Extract relevant parameters from the provided text based on the name and description of object.
Step 3: Structure the extracted parameters to JSON object as specified in <structure>.
Step 4: Ensure that the list of variable_names is properly formatted and valid. The output should not contain any XML tags. Output an empty list if there is no valid variable name in input text.
Step 4: Ensure that the list of variable_names is properly formatted and valid. The output should not contain any XML tags. Output an empty list if there is no valid variable name in input text.
### Structure
Here is the structure of the expected output, I should always follow the output structure.
Here is the structure of the expected output, I should always follow the output structure.
["variable_name_1", "variable_name_2"]
### Input Text
@ -214,13 +214,13 @@ I should always output a valid list. Output nothing other than the list of varia
RULE_CONFIG_STATEMENT_GENERATE_TEMPLATE = """
<instruction>
Step 1: Identify the purpose of the chatbot from the variable {{TASK_DESCRIPTION}} and infer chatbot's tone (e.g., friendly, professional, etc.) to add personality traits.
Step 1: Identify the purpose of the chatbot from the variable {{TASK_DESCRIPTION}} and infer chatbot's tone (e.g., friendly, professional, etc.) to add personality traits.
Step 2: Create a coherent and engaging opening statement.
Step 3: Ensure the output is welcoming and clearly explains what the chatbot is designed to do. Do not include any XML tags in the output.
Please use the same language as the user's input language. If user uses chinese then generate opening statement in chinese, if user uses english then generate opening statement in english.
Example Input:
Please use the same language as the user's input language. If user uses chinese then generate opening statement in chinese, if user uses english then generate opening statement in english.
Example Input:
Provide customer support for an e-commerce website
Example Output:
Example Output:
Welcome! I'm here to assist you with any questions or issues you might have with your shopping experience. Whether you're looking for product information, need help with your order, or have any other inquiries, feel free to ask. I'm friendly, helpful, and ready to support you in any way I can.
<Task>
Here is the task description: {{INPUT_TEXT}}
@ -276,15 +276,15 @@ Your task is to convert simple user descriptions into properly formatted JSON Sc
{
"type": "object",
"properties": {
"email": {
"email": {
"type": "string",
"format": "email"
},
"password": {
"password": {
"type": "string",
"minLength": 8
},
"age": {
"age": {
"type": "integer",
"minimum": 18
}

View File

@ -307,4 +307,4 @@ Runtime Errors:
"""
```
For interface method details, see: [Interfaces](./interfaces.md). For specific implementations, refer to: [llm.py](https://github.com/langgenius/dify-runtime/blob/main/lib/model_providers/anthropic/llm/llm.py).
For interface method details, see: [Interfaces](./interfaces.md). For specific implementations, refer to: [llm.py](https://github.com/langgenius/dify-runtime/blob/main/lib/model_providers/anthropic/llm/llm.py).

View File

@ -170,4 +170,4 @@ Runtime Errors:
"""
```
For interface method explanations, see: [Interfaces](./interfaces.md). For detailed implementation, refer to: [llm.py](https://github.com/langgenius/dify-runtime/blob/main/lib/model_providers/anthropic/llm/llm.py).
For interface method explanations, see: [Interfaces](./interfaces.md). For detailed implementation, refer to: [llm.py](https://github.com/langgenius/dify-runtime/blob/main/lib/model_providers/anthropic/llm/llm.py).

View File

@ -294,4 +294,4 @@ provider_credential_schema:
"""
```
接口方法说明见:[Interfaces](./interfaces.md),具体实现可参考:[llm.py](https://github.com/langgenius/dify-runtime/blob/main/lib/model_providers/anthropic/llm/llm.py)。
接口方法说明见:[Interfaces](./interfaces.md),具体实现可参考:[llm.py](https://github.com/langgenius/dify-runtime/blob/main/lib/model_providers/anthropic/llm/llm.py)。

View File

@ -169,4 +169,4 @@ pricing: # 价格信息
"""
```
接口方法说明见:[Interfaces](./interfaces.md),具体实现可参考:[llm.py](https://github.com/langgenius/dify-runtime/blob/main/lib/model_providers/anthropic/llm/llm.py)。
接口方法说明见:[Interfaces](./interfaces.md),具体实现可参考:[llm.py](https://github.com/langgenius/dify-runtime/blob/main/lib/model_providers/anthropic/llm/llm.py)。

View File

@ -1 +1 @@
3
3

View File

@ -1 +1 @@
2
2

View File

@ -239,8 +239,8 @@ class PluginModelBackwardsInvocation(BaseBackwardsInvocation):
content = payload.text
SUMMARY_PROMPT = """You are a professional language researcher, you are interested in the language
and you can quickly aimed at the main point of an webpage and reproduce it in your own words but
retain the original meaning and keep the key points.
and you can quickly aimed at the main point of an webpage and reproduce it in your own words but
retain the original meaning and keep the key points.
however, the text you got is too long, what you got is possible a part of the text.
Please summarize the text you got.

View File

@ -10,4 +10,4 @@
],
"query_prompt": "\n\n用户{{#query#}}",
"stops": ["用户:"]
}
}

View File

@ -6,4 +6,4 @@
],
"query_prompt": "{{#query#}}",
"stops": null
}
}

View File

@ -6,4 +6,4 @@
],
"query_prompt": "{{#query#}}",
"stops": null
}
}

View File

@ -156,8 +156,8 @@ class AnalyticdbVectorBySql:
values = []
id_prefix = str(uuid.uuid4()) + "_"
sql = f"""
INSERT INTO {self.table_name}
(id, ref_doc_id, vector, page_content, metadata_, to_tsvector)
INSERT INTO {self.table_name}
(id, ref_doc_id, vector, page_content, metadata_, to_tsvector)
VALUES (%s, %s, %s, %s, %s, to_tsvector('zh_cn', %s));
"""
for i, doc in enumerate(documents):
@ -242,7 +242,7 @@ class AnalyticdbVectorBySql:
where_clause += f"AND metadata_->>'document_id' IN ({document_ids})"
with self._get_cursor() as cur:
cur.execute(
f"""SELECT id, vector, page_content, metadata_,
f"""SELECT id, vector, page_content, metadata_,
ts_rank(to_tsvector, to_tsquery_from_text(%s, 'zh_cn'), 32) AS score
FROM {self.table_name}
WHERE to_tsvector@@to_tsquery_from_text(%s, 'zh_cn') {where_clause}

View File

@ -203,7 +203,7 @@ class OceanBaseVector(BaseVector):
full_sql = f"""SELECT metadata, text, MATCH (text) AGAINST (:query) AS score
FROM {self._collection_name}
WHERE MATCH (text) AGAINST (:query) > 0
WHERE MATCH (text) AGAINST (:query) > 0
{where_clause}
ORDER BY score DESC
LIMIT {top_k}"""

View File

@ -59,12 +59,12 @@ CREATE TABLE IF NOT EXISTS {table_name} (
"""
SQL_CREATE_INDEX_PQ = """
CREATE INDEX IF NOT EXISTS embedding_{table_name}_pq_idx ON {table_name}
CREATE INDEX IF NOT EXISTS embedding_{table_name}_pq_idx ON {table_name}
USING hnsw (embedding vector_cosine_ops) WITH (m = 16, ef_construction = 64, enable_pq=on, pq_m={pq_m});
"""
SQL_CREATE_INDEX = """
CREATE INDEX IF NOT EXISTS embedding_cosine_{table_name}_idx ON {table_name}
CREATE INDEX IF NOT EXISTS embedding_cosine_{table_name}_idx ON {table_name}
USING hnsw (embedding vector_cosine_ops) WITH (m = 16, ef_construction = 64);
"""

View File

@ -59,8 +59,8 @@ CREATE TABLE IF NOT EXISTS {table_name} (
)
"""
SQL_CREATE_INDEX = """
CREATE INDEX IF NOT EXISTS idx_docs_{table_name} ON {table_name}(text)
INDEXTYPE IS CTXSYS.CONTEXT PARAMETERS
CREATE INDEX IF NOT EXISTS idx_docs_{table_name} ON {table_name}(text)
INDEXTYPE IS CTXSYS.CONTEXT PARAMETERS
('FILTER CTXSYS.NULL_FILTER SECTION GROUP CTXSYS.HTML_SECTION_GROUP LEXER world_lexer')
"""
@ -164,7 +164,7 @@ class OracleVector(BaseVector):
with conn.cursor() as cur:
try:
cur.execute(
f"""INSERT INTO {self.table_name} (id, text, meta, embedding)
f"""INSERT INTO {self.table_name} (id, text, meta, embedding)
VALUES (:1, :2, :3, :4)""",
value,
)
@ -227,8 +227,8 @@ class OracleVector(BaseVector):
conn.outputtypehandler = self.output_type_handler
with conn.cursor() as cur:
cur.execute(
f"""SELECT meta, text, vector_distance(embedding,(select to_vector(:1) from dual),cosine)
AS distance FROM {self.table_name}
f"""SELECT meta, text, vector_distance(embedding,(select to_vector(:1) from dual),cosine)
AS distance FROM {self.table_name}
{where_clause} ORDER BY distance fetch first {top_k} rows only""",
[numpy.array(query_vector)],
)
@ -290,7 +290,7 @@ class OracleVector(BaseVector):
document_ids = ", ".join(f"'{id}'" for id in document_ids_filter)
where_clause = f" AND metadata->>'document_id' in ({document_ids}) "
cur.execute(
f"""select meta, text, embedding FROM {self.table_name}
f"""select meta, text, embedding FROM {self.table_name}
WHERE CONTAINS(text, :kk, 1) > 0 {where_clause}
order by score(1) desc fetch first {top_k} rows only""",
kk=" ACCUM ".join(entities),

View File

@ -61,7 +61,7 @@ CREATE TABLE IF NOT EXISTS {table_name} (
"""
SQL_CREATE_INDEX = """
CREATE INDEX IF NOT EXISTS embedding_cosine_v1_idx ON {table_name}
CREATE INDEX IF NOT EXISTS embedding_cosine_v1_idx ON {table_name}
USING hnsw (embedding vector_cosine_ops) WITH (m = 16, ef_construction = 64);
"""

View File

@ -58,7 +58,7 @@ CREATE TABLE IF NOT EXISTS {table_name} (
"""
SQL_CREATE_INDEX = """
CREATE INDEX IF NOT EXISTS embedding_cosine_v1_idx ON {table_name}
CREATE INDEX IF NOT EXISTS embedding_cosine_v1_idx ON {table_name}
USING hnsw (embedding floatvector_cosine_ops) WITH (m = 16, ef_construction = 64);
"""

View File

@ -205,9 +205,9 @@ class TiDBVector(BaseVector):
with Session(self._engine) as session:
select_statement = sql_text(f"""
SELECT meta, text, distance
SELECT meta, text, distance
FROM (
SELECT
SELECT
meta,
text,
{tidb_dist_func}(vector, :query_vector_str) AS distance

View File

@ -50,7 +50,7 @@ You are a text metadata extract engine that extract text's metadata based on use
# Your task is to ONLY extract the metadatas that exist in the input text from the provided metadata list and Use the following operators ["=", "!=", ">", "<", ">=", "<="] to express logical relationships, then return result in JSON format with the key "metadata_fields" and value "metadata_field_value" and comparison operator "comparison_operator".
### Format
The input text is in the variable input_text. Metadata are specified as a list in the variable metadata_fields.
### Constraint
### Constraint
DO NOT include anything other than the JSON array in your response.
### Example
Here is the chat example between human and assistant, inside <example></example> XML tags.
@ -59,7 +59,7 @@ User:{{"input_text": ["I want to know which companys email address test@examp
Assistant:{{"metadata_map": [{{"metadata_field_name": "email", "metadata_field_value": "test@example.com", "comparison_operator": "="}}]}}
User:{{"input_text": "What are the movies with a score of more than 9 in 2024?", "metadata_fields": ["name", "year", "rating", "country"]}}
Assistant:{{"metadata_map": [{{"metadata_field_name": "year", "metadata_field_value": "2024", "comparison_operator": "="}, {{"metadata_field_name": "rating", "metadata_field_value": "9", "comparison_operator": ">"}}]}}
</example>
</example>
### User Input
{{"input_text" : "{input_text}", "metadata_fields" : {metadata_fields}}}
### Assistant Output

View File

@ -6,8 +6,8 @@ from core.tools.entities.tool_entities import ToolProviderType
from core.tools.utils.model_invocation_utils import ModelInvocationUtils
_SUMMARY_PROMPT = """You are a professional language researcher, you are interested in the language
and you can quickly aimed at the main point of an webpage and reproduce it in your own words but
retain the original meaning and keep the key points.
and you can quickly aimed at the main point of an webpage and reproduce it in your own words but
retain the original meaning and keep the key points.
however, the text you got is too long, what you got is possible a part of the text.
Please summarize the text you got.
"""

View File

@ -50,7 +50,7 @@ You are a text metadata extract engine that extract text's metadata based on use
# Your task is to ONLY extract the metadatas that exist in the input text from the provided metadata list and Use the following operators ["=", "!=", ">", "<", ">=", "<="] to express logical relationships, then return result in JSON format with the key "metadata_fields" and value "metadata_field_value" and comparison operator "comparison_operator".
### Format
The input text is in the variable input_text. Metadata are specified as a list in the variable metadata_fields.
### Constraint
### Constraint
DO NOT include anything other than the JSON array in your response.
### Example
Here is the chat example between human and assistant, inside <example></example> XML tags.
@ -59,7 +59,7 @@ User:{{"input_text": ["I want to know which companys email address test@examp
Assistant:{{"metadata_map": [{{"metadata_field_name": "email", "metadata_field_value": "test@example.com", "comparison_operator": "="}}]}}
User:{{"input_text": "What are the movies with a score of more than 9 in 2024?", "metadata_fields": ["name", "year", "rating", "country"]}}
Assistant:{{"metadata_map": [{{"metadata_field_name": "year", "metadata_field_value": "2024", "comparison_operator": "="}, {{"metadata_field_name": "rating", "metadata_field_value": "9", "comparison_operator": ">"}}]}}
</example>
</example>
### User Input
{{"input_text" : "{input_text}", "metadata_fields" : {metadata_fields}}}
### Assistant Output

View File

@ -17,7 +17,7 @@ Some additional information is provided below. Always adhere to these instructio
</instruction>
Steps:
1. Review the chat history provided within the <histories> tags.
2. Extract the relevant information based on the criteria given, output multiple values if there is multiple relevant information that match the criteria in the given text.
2. Extract the relevant information based on the criteria given, output multiple values if there is multiple relevant information that match the criteria in the given text.
3. Generate a well-formatted output using the defined functions and arguments.
4. Use the `extract_parameter` function to create structured outputs with appropriate parameters.
5. Do not include any XML tags in your output.
@ -89,13 +89,13 @@ Some extra information are provided below, I should always follow the instructio
</instructions>
### Extract parameter Workflow
I need to extract the following information from the input text. The <information to be extracted> tag specifies the 'type', 'description' and 'required' of the information to be extracted.
I need to extract the following information from the input text. The <information to be extracted> tag specifies the 'type', 'description' and 'required' of the information to be extracted.
<information to be extracted>
{{ structure }}
</information to be extracted>
Step 1: Carefully read the input and understand the structure of the expected output.
Step 2: Extract relevant parameters from the provided text based on the name and description of object.
Step 2: Extract relevant parameters from the provided text based on the name and description of object.
Step 3: Structure the extracted parameters to JSON object as specified in <structure>.
Step 4: Ensure that the JSON object is properly formatted and valid. The output should not contain any XML tags. Only the JSON object should be outputted.
@ -106,10 +106,10 @@ Here are the chat histories between human and assistant, inside <histories></his
</histories>
### Structure
Here is the structure of the expected output, I should always follow the output structure.
Here is the structure of the expected output, I should always follow the output structure.
{{γγγ
'properties1': 'relevant text extracted from input',
'properties2': 'relevant text extracted from input',
'properties1': 'relevant text extracted from input',
'properties2': 'relevant text extracted from input',
}}γγγ
### Input Text
@ -119,7 +119,7 @@ Inside <text></text> XML tags, there is a text that I should extract parameters
</text>
### Answer
I should always output a valid JSON object. Output nothing other than the JSON object.
I should always output a valid JSON object. Output nothing other than the JSON object.
```JSON
""" # noqa: E501

View File

@ -55,7 +55,7 @@ You are a text classification engine that analyzes text data and assigns categor
Your task is to assign one categories ONLY to the input text and only one category may be assigned returned in the output. Additionally, you need to extract the key words from the text that are related to the classification.
### Format
The input text is in the variable input_text. Categories are specified as a category list with two filed category_id and category_name in the variable categories. Classification instructions may be included to improve the classification accuracy.
### Constraint
### Constraint
DO NOT include anything other than the JSON array in your response.
### Example
Here is the chat example between human and assistant, inside <example></example> XML tags.
@ -64,7 +64,7 @@ User:{{"input_text": ["I recently had a great experience with your company. The
Assistant:{{"keywords": ["recently", "great experience", "company", "service", "prompt", "staff", "friendly"],"category_id": "f5660049-284f-41a7-b301-fd24176a711c","category_name": "Customer Service"}}
User:{{"input_text": ["bad service, slow to bring the food"], "categories": [{{"category_id":"80fb86a0-4454-4bf5-924c-f253fdd83c02","category_name":"Food Quality"}},{{"category_id":"f6ff5bc3-aca0-4e4a-8627-e760d0aca78f","category_name":"Experience"}},{{"category_id":"cc771f63-74e7-4c61-882e-3eda9d8ba5d7","category_name":"Price"}}], "classification_instructions": []}}
Assistant:{{"keywords": ["bad service", "slow", "food", "tip", "terrible", "waitresses"],"category_id": "f6ff5bc3-aca0-4e4a-8627-e760d0aca78f","category_name": "Experience"}}
</example>
</example>
### Memory
Here are the chat histories between human and assistant, inside <histories></histories> XML tags.
<histories>

View File

@ -21,14 +21,14 @@ def upgrade():
# ### commands auto generated by Alembic - please adjust! ###
# Get the database connection
conn = op.get_bind()
# Use SQLAlchemy inspector to get the columns of the 'tool_files' table
inspector = sa.inspect(conn)
columns = [col['name'] for col in inspector.get_columns('tool_files')]
# If 'name' or 'size' columns already exist, exit the upgrade function
if 'name' in columns or 'size' in columns:
return
return
with op.batch_alter_table('tool_files', schema=None) as batch_op:
batch_op.add_column(sa.Column('name', sa.String(), nullable=True))

View File

@ -35,4 +35,4 @@ def downgrade():
# batch_op.drop_column('retry_index')
pass
# ### end Alembic commands ###
# ### end Alembic commands ###

View File

@ -23,7 +23,7 @@ def upgrade():
conn = op.get_bind()
inspector = inspect(conn)
has_column = 'retry_index' in [col['name'] for col in inspector.get_columns('workflow_node_executions')]
if has_column:
with op.batch_alter_table('workflow_node_executions', schema=None) as batch_op:
batch_op.drop_column('retry_index')

View File

@ -1,7 +1,7 @@
"""init
Revision ID: 64b051264f32
Revises:
Revises:
Create Date: 2023-05-13 14:26:59.085018
"""

View File

@ -99,12 +99,12 @@ def upgrade():
id=id,
tenant_id=tenant_id,
user_id=user_id,
provider='google',
provider='google',
encrypted_credentials=encrypted_credentials,
created_at=created_at,
updated_at=updated_at
)
# ### end Alembic commands ###

View File

@ -86,9 +86,9 @@ limit 1000"""
update_retrieval_model_sql = ", retrieval_model = :retrieval_model"
params["retrieval_model"] = json.dumps(retrieval_model)
sql = f"""update {table_name}
set {provider_column_name} =
concat('{DEFAULT_PLUGIN_ID}/', {provider_column_name}, '/', {provider_column_name})
sql = f"""update {table_name}
set {provider_column_name} =
concat('{DEFAULT_PLUGIN_ID}/', {provider_column_name}, '/', {provider_column_name})
{update_retrieval_model_sql}
where id = :record_id"""
conn.execute(db.text(sql), params)
@ -131,10 +131,10 @@ limit 1000"""
while True:
sql = f"""
SELECT id, {provider_column_name} AS provider_name
SELECT id, {provider_column_name} AS provider_name
FROM {table_name}
WHERE {provider_column_name} NOT LIKE '%/%'
AND {provider_column_name} IS NOT NULL
WHERE {provider_column_name} NOT LIKE '%/%'
AND {provider_column_name} IS NOT NULL
AND {provider_column_name} != ''
AND id > :last_id
ORDER BY id ASC
@ -183,8 +183,8 @@ limit 1000"""
if batch_updates:
update_sql = f"""
UPDATE {table_name}
SET {provider_column_name} = :updated_value
UPDATE {table_name}
SET {provider_column_name} = :updated_value
WHERE id = :record_id
"""
conn.execute(db.text(update_sql), [{"updated_value": u, "record_id": r} for u, r in batch_updates])

View File

@ -77,7 +77,7 @@
<h1>Some Documents in Your Knowledge Base Have Been Disabled</h1>
<p>Dear {{userName}},</p>
<p>
We're sorry for the inconvenience. To ensure optimal performance, documents
We're sorry for the inconvenience. To ensure optimal performance, documents
that havent been updated or accessed in the past 30 days have been disabled in
your knowledge bases:
</p>
@ -97,4 +97,4 @@
</div>
</div>
</body>
</html>
</html>

View File

@ -122,4 +122,4 @@
</div>
</body>
</html>
</html>

View File

@ -102,4 +102,4 @@
</div>
</body>
</html>
</html>

View File

@ -1 +1 @@
.env.test
.env.test

View File

@ -1 +1 @@
.env.test
.env.test

View File

@ -11,4 +11,4 @@ dev/pytest/pytest_tools.sh
dev/pytest/pytest_workflow.sh
# Unit tests
dev/pytest/pytest_unit_tests.sh
dev/pytest/pytest_unit_tests.sh

View File

@ -10,4 +10,4 @@ pytest api/tests/integration_tests/model_runtime/anthropic \
api/tests/integration_tests/model_runtime/fireworks \
api/tests/integration_tests/model_runtime/nomic \
api/tests/integration_tests/model_runtime/mixedbread \
api/tests/integration_tests/model_runtime/voyage
api/tests/integration_tests/model_runtime/voyage

View File

@ -1,4 +1,4 @@
FROM couchbase/server:latest AS stage_base
# FROM couchbase:latest AS stage_base
# FROM couchbase:latest AS stage_base
COPY init-cbserver.sh /opt/couchbase/init/
RUN chmod +x /opt/couchbase/init/init-cbserver.sh
RUN chmod +x /opt/couchbase/init/init-cbserver.sh

View File

@ -1,8 +1,8 @@
#!/bin/bash
# used to start couchbase server - can't get around this as docker compose only allows you to start one command - so we have to start couchbase like the standard couchbase Dockerfile would
# used to start couchbase server - can't get around this as docker compose only allows you to start one command - so we have to start couchbase like the standard couchbase Dockerfile would
# https://github.com/couchbase/docker/blob/master/enterprise/couchbase-server/7.2.0/Dockerfile#L88
/entrypoint.sh couchbase-server &
/entrypoint.sh couchbase-server &
# track if setup is complete so we don't try to setup again
FILE=/opt/couchbase/init/setupComplete.txt
@ -36,9 +36,9 @@ if ! [ -f "$FILE" ]; then
--bucket-ramsize $COUCHBASE_BUCKET_RAMSIZE \
--bucket-type couchbase
# create file so we know that the cluster is setup and don't run the setup again
# create file so we know that the cluster is setup and don't run the setup again
touch $FILE
fi
fi
# docker compose will stop the container from running unless we do this
# known issue and workaround
tail -f /dev/null

View File

@ -144,4 +144,4 @@ PLUGIN_AZURE_BLOB_STORAGE_CONNECTION_STRING=
# Plugin oss tencent cos
PLUGIN_TENCENT_COS_SECRET_KEY=
PLUGIN_TENCENT_COS_SECRET_ID=
PLUGIN_TENCENT_COS_REGION=
PLUGIN_TENCENT_COS_REGION=

View File

@ -39,4 +39,4 @@ envsubst "$env_vars" < /etc/nginx/proxy.conf.template > /etc/nginx/proxy.conf
envsubst "$env_vars" < /etc/nginx/conf.d/default.conf.template > /etc/nginx/conf.d/default.conf
# Start Nginx using the default entrypoint
exec nginx -g 'daemon off;'
exec nginx -g 'daemon off;'

View File

@ -6,4 +6,4 @@ ssl_certificate_key ${SSL_CERTIFICATE_KEY_PATH};
ssl_protocols ${NGINX_SSL_PROTOCOLS};
ssl_prefer_server_ciphers on;
ssl_session_cache shared:SSL:10m;
ssl_session_timeout 10m;
ssl_session_timeout 10m;

View File

@ -31,4 +31,4 @@ http {
client_max_body_size ${NGINX_CLIENT_MAX_BODY_SIZE};
include /etc/nginx/conf.d/*.conf;
}
}

View File

@ -44,7 +44,7 @@ refresh_pattern . 0 20% 4320
# cache_dir ufs /var/spool/squid 100 16 256
# upstream proxy, set to your own upstream proxy IP to avoid SSRF attacks
# cache_peer 172.1.1.1 parent 3128 0 no-query no-digest no-netdb-exchange default
# cache_peer 172.1.1.1 parent 3128 0 no-query no-digest no-netdb-exchange default
################################## Reverse Proxy To Sandbox ################################
http_port ${REVERSE_PROXY_PORT} accel vhost
@ -53,4 +53,4 @@ acl src_all src all
http_access allow src_all
# Unless the option's size is increased, an error will occur when uploading more than two files.
client_request_buffer_max_size 100 MB
client_request_buffer_max_size 100 MB

View File

@ -8,6 +8,6 @@ if [ -f ${DB_INITIALIZED} ]; then
exit
else
echo 'File does not exist. Standards for first time Start up this DB'
"$ORACLE_HOME"/bin/sqlplus -s "/ as sysdba" @"/opt/oracle/scripts/startup/init_user.script";
"$ORACLE_HOME"/bin/sqlplus -s "/ as sysdba" @"/opt/oracle/scripts/startup/init_user.script";
touch ${DB_INITIALIZED}
fi

View File

@ -1,5 +1,5 @@
show pdbs;
ALTER SYSTEM SET PROCESSES=500 SCOPE=SPFILE;
ALTER SYSTEM SET PROCESSES=500 SCOPE=SPFILE;
alter session set container= freepdb1;
create user dify identified by dify DEFAULT TABLESPACE users quota unlimited on users;
grant DB_DEVELOPER_ROLE to dify;

View File

@ -1,4 +1,4 @@
# PD Configuration File reference:
# https://docs.pingcap.com/tidb/stable/pd-configuration-file#pd-configuration-file
[replication]
max-replicas = 1
max-replicas = 1

View File

@ -14,4 +14,4 @@
<access_management>1</access_management>
</default>
</users>
</clickhouse>
</clickhouse>

View File

@ -1 +1 @@
ALTER SYSTEM SET ob_vector_memory_limit_percentage = 30;
ALTER SYSTEM SET ob_vector_memory_limit_percentage = 30;

View File

@ -45,4 +45,4 @@ package-lock.json
.yarnrc.yml
# pmpm
pnpm-lock.yaml
pnpm-lock.yaml

View File

@ -26,7 +26,7 @@ export declare class DifyClient {
params?: Params,
stream?: boolean,
headerParams?: HeaderParams
): Promise<any>;
): Promise<any>;
messageFeedback(message_id: string, rating: number, user: User): Promise<any>;
@ -64,9 +64,9 @@ export declare class ChatClient extends DifyClient {
getConversations(
user: User,
first_id?: string | null,
limit?: number | null,
user: User,
first_id?: string | null,
limit?: number | null,
pinned?: boolean | null
): Promise<any>;
@ -80,7 +80,7 @@ export declare class ChatClient extends DifyClient {
renameConversation(conversation_id: string, name: string, user: User,auto_generate:boolean): Promise<any>;
deleteConversation(conversation_id: string, user: User): Promise<any>;
audioToText(data: FormData): Promise<any>;
}
@ -88,4 +88,4 @@ export declare class WorkflowClient extends DifyClient {
run(inputs: any, user: User, stream?: boolean,): Promise<any>;
stop(task_id: string, user: User): Promise<any>;
}
}

View File

@ -334,12 +334,12 @@ export class ChatClient extends DifyClient {
export class WorkflowClient extends DifyClient {
run(inputs,user,stream) {
const data = {
inputs,
const data = {
inputs,
response_mode: stream ? "streaming" : "blocking",
user
user
};
return this.sendRequest(
routes.runWorkflow.method,
routes.runWorkflow.url(),
@ -357,4 +357,4 @@ export class WorkflowClient extends DifyClient {
data
);
}
}
}

View File

@ -62,4 +62,4 @@ describe('Send Requests', () => {
errorMessage
)
})
})
})

View File

@ -32,4 +32,4 @@
"babel-jest": "^29.5.0",
"jest": "^29.5.0"
}
}
}

View File

@ -92,4 +92,4 @@ Replace 'your-api-key-here' with your actual Dify API key.
## License
This SDK is released under the MIT License.
This SDK is released under the MIT License.

View File

@ -119,14 +119,14 @@ class ChatClient extends DifyClient {
return $this->send_request('POST', 'chat-messages', $data, null, $response_mode === 'streaming');
}
public function get_suggestions($message_id, $user) {
$params = [
'user' => $user
];
return $this->send_request('GET', "messages/{$message_id}/suggested", null, $params);
}
public function stop_message($task_id, $user) {
$data = ['user' => $user];
return $this->send_request('POST', "chat-messages/{$task_id}/stop", $data);
@ -157,7 +157,7 @@ class ChatClient extends DifyClient {
return $this->send_request('GET', 'messages', null, $params);
}
public function rename_conversation($conversation_id, $name,$auto_generate, $user) {
$data = [
'name' => $name,
@ -202,5 +202,5 @@ class WorkflowClient extends DifyClient{
];
return $this->send_request('POST', "workflows/tasks/{$task_id}/stop",$data);
}
}
}

View File

@ -1 +1 @@
recursive-include dify_client *.py
recursive-include dify_client *.py

View File

@ -6,4 +6,4 @@ rm -rf build dist *.egg-info
pip install setuptools wheel twine
python setup.py sdist bdist_wheel
twine upload dist/*
twine upload dist/*

View File

@ -21,4 +21,4 @@ node_modules
# Jetbrains
.idea
.idea

View File

@ -4,4 +4,4 @@
"firsttris.vscode-jest-runner",
"kisstkondoros.vscode-codemetrics"
]
}
}

View File

@ -3,4 +3,4 @@
height: 0;
border-radius: 16px 16px 0px 0px;
box-shadow: 0px 0px 5px rgba(0, 0, 0, 0.05), 0px 0px 2px -1px rgba(0, 0, 0, 0.03);
}
}

View File

@ -214,4 +214,4 @@
.listItem:hover .unavailable {
@apply opacity-100;
}
}

View File

@ -5,7 +5,7 @@
.completionPic {
background-image: url('./completion.png')
}
.expertPic {
background-image: url('./expert.png')
}
}

View File

@ -1,3 +1,3 @@
.item {
background-color: rgba(21, 94, 239, 0.05);
}
}

View File

@ -5,4 +5,4 @@
.icon {
box-shadow: 0px 12px 16px -4px rgba(16, 24, 40, 0.08), 0px 4px 6px -2px rgba(16, 24, 40, 0.03);
}
}

View File

@ -25,4 +25,4 @@
.boxHeader:hover .optionWrap {
display: flex;
}
}

View File

@ -4,4 +4,4 @@
-webkit-text-fill-color: transparent;
background-clip: text;
text-fill-color: transparent;
}
}

View File

@ -3,4 +3,4 @@
right: -16px;
bottom: -16px;
border-top: 1px solid #F3F4F6;
}
}

View File

@ -19,4 +19,4 @@
.settingBtn:hover {
background-color: rgba(0, 0, 0, 0.05);
}
}

View File

@ -4,4 +4,4 @@
.weightedScoreSliderTrack-1 {
background: transparent !important;
}
}

View File

@ -11,4 +11,4 @@
height: 3px;
background-color: rgba(68, 76, 231, 0.18);
transform: skewX(-30deg);
}
}

View File

@ -87,7 +87,7 @@ const Tools = () => {
<div className='flex grow items-center'>
<div
className={`
group mr-1 flex h-6 w-6 items-center justify-center rounded-md
group mr-1 flex h-6 w-6 items-center justify-center rounded-md
${externalDataToolsConfig.length && 'hover:bg-white hover:shadow-xs'}
`}
onClick={() => setExpanded(v => !v)}

View File

@ -17,4 +17,4 @@
}
.pluginInstallIcon {
background-image: url(../assets/chromeplugin-install.svg);
}
}

View File

@ -42,4 +42,4 @@
@apply text-text-destructive bg-state-destructive-hover
}
}
}

View File

@ -20,4 +20,4 @@
.appIcon.rounded {
@apply rounded-full;
}
}

View File

@ -7,4 +7,4 @@
background-image: url(~@/app/components/develop/secret-key/assets/pause.svg);
background-position: center;
background-repeat: no-repeat;
}
}

View File

@ -25,4 +25,4 @@
.badge.badge-accent {
@apply text-text-accent-secondary border border-text-accent-secondary
}
}
}

View File

@ -22,7 +22,7 @@
}
.btn-primary {
@apply
@apply
shadow
bg-components-button-primary-bg
border-components-button-primary-border
@ -32,7 +32,7 @@
}
.btn-primary.btn-destructive {
@apply
@apply
bg-components-button-destructive-primary-bg
border-components-button-destructive-primary-border
hover:bg-components-button-destructive-primary-bg-hover
@ -41,7 +41,7 @@
}
.btn-primary.btn-disabled {
@apply
@apply
shadow-none
bg-components-button-primary-bg-disabled
border-components-button-primary-border-disabled
@ -49,7 +49,7 @@
}
.btn-primary.btn-destructive.btn-disabled {
@apply
@apply
shadow-none
bg-components-button-destructive-primary-bg-disabled
border-components-button-destructive-primary-border-disabled
@ -57,130 +57,130 @@
}
.btn-secondary {
@apply
@apply
border-[0.5px]
shadow-xs
bg-components-button-secondary-bg
border-components-button-secondary-border
hover:bg-components-button-secondary-bg-hover
hover:border-components-button-secondary-border-hover
bg-components-button-secondary-bg
border-components-button-secondary-border
hover:bg-components-button-secondary-bg-hover
hover:border-components-button-secondary-border-hover
text-components-button-secondary-text;
}
.btn-secondary.btn-disabled {
@apply
bg-components-button-secondary-bg-disabled
border-components-button-secondary-border-disabled
@apply
bg-components-button-secondary-bg-disabled
border-components-button-secondary-border-disabled
text-components-button-secondary-text-disabled;
}
.btn-secondary.btn-destructive {
@apply
bg-components-button-destructive-secondary-bg
border-components-button-destructive-secondary-border
hover:bg-components-button-destructive-secondary-bg-hover
hover:border-components-button-destructive-secondary-border-hover
@apply
bg-components-button-destructive-secondary-bg
border-components-button-destructive-secondary-border
hover:bg-components-button-destructive-secondary-bg-hover
hover:border-components-button-destructive-secondary-border-hover
text-components-button-destructive-secondary-text;
}
.btn-secondary.btn-destructive.btn-disabled {
@apply
bg-components-button-destructive-secondary-bg-disabled
border-components-button-destructive-secondary-border-disabled
@apply
bg-components-button-destructive-secondary-bg-disabled
border-components-button-destructive-secondary-border-disabled
text-components-button-destructive-secondary-text-disabled;
}
.btn-secondary-accent {
@apply
@apply
border-[0.5px]
shadow-xs
bg-components-button-secondary-bg
border-components-button-secondary-border
hover:bg-components-button-secondary-bg-hover
hover:border-components-button-secondary-border-hover
bg-components-button-secondary-bg
border-components-button-secondary-border
hover:bg-components-button-secondary-bg-hover
hover:border-components-button-secondary-border-hover
text-components-button-secondary-accent-text;
}
.btn-secondary-accent.btn-disabled {
@apply
bg-components-button-secondary-bg-disabled
border-components-button-secondary-border-disabled
@apply
bg-components-button-secondary-bg-disabled
border-components-button-secondary-border-disabled
text-components-button-secondary-accent-text-disabled;
}
.btn-warning {
@apply
bg-components-button-destructive-primary-bg
border-components-button-destructive-primary-border
hover:bg-components-button-destructive-primary-bg-hover
hover:border-components-button-destructive-primary-border-hover
@apply
bg-components-button-destructive-primary-bg
border-components-button-destructive-primary-border
hover:bg-components-button-destructive-primary-bg-hover
hover:border-components-button-destructive-primary-border-hover
text-components-button-destructive-primary-text;
}
.btn-warning.btn-disabled {
@apply
bg-components-button-destructive-primary-bg-disabled
border-components-button-destructive-primary-border-disabled
@apply
bg-components-button-destructive-primary-bg-disabled
border-components-button-destructive-primary-border-disabled
text-components-button-destructive-primary-text-disabled;
}
.btn-tertiary {
@apply
bg-components-button-tertiary-bg
hover:bg-components-button-tertiary-bg-hover
@apply
bg-components-button-tertiary-bg
hover:bg-components-button-tertiary-bg-hover
text-components-button-tertiary-text;
}
.btn-tertiary.btn-disabled {
@apply
bg-components-button-tertiary-bg-disabled
@apply
bg-components-button-tertiary-bg-disabled
text-components-button-tertiary-text-disabled;
}
.btn-tertiary.btn-destructive {
@apply
bg-components-button-destructive-tertiary-bg
hover:bg-components-button-destructive-tertiary-bg-hover
@apply
bg-components-button-destructive-tertiary-bg
hover:bg-components-button-destructive-tertiary-bg-hover
text-components-button-destructive-tertiary-text;
}
.btn-tertiary.btn-destructive.btn-disabled {
@apply
bg-components-button-destructive-tertiary-bg-disabled
@apply
bg-components-button-destructive-tertiary-bg-disabled
text-components-button-destructive-tertiary-text-disabled;
}
.btn-ghost {
@apply
hover:bg-components-button-ghost-bg-hover
@apply
hover:bg-components-button-ghost-bg-hover
text-components-button-ghost-text;
}
.btn-ghost.btn-disabled {
@apply
@apply
text-components-button-ghost-text-disabled;
}
.btn-ghost.btn-destructive {
@apply
hover:bg-components-button-destructive-ghost-bg-hover
@apply
hover:bg-components-button-destructive-ghost-bg-hover
text-components-button-destructive-ghost-text;
}
.btn-ghost.btn-destructive.btn-disabled {
@apply
@apply
text-components-button-destructive-ghost-text-disabled;
}
.btn-ghost-accent {
@apply
@apply
hover:bg-state-accent-hover
text-components-button-secondary-accent-text;
}
.btn-ghost-accent.btn-disabled {
@apply
@apply
text-components-button-secondary-accent-text-disabled;
}
}
}

View File

@ -2,25 +2,25 @@ export const markdownContentSVG = `
\`\`\`svg
<svg width="400" height="600" xmlns="http://www.w3.org/2000/svg">
<rect width="100%" height="100%" fill="#F0F8FF"/>
<text x="50%" y="60" font-family="楷体" font-size="32" fill="#4682B4" text-anchor="middle">Logo设计</text>
<line x1="50" y1="80" x2="350" y2="80" stroke="#B0C4DE" stroke-width="2"/>
<text x="50%" y="120" font-family="Arial" font-size="24" fill="#708090" text-anchor="middle"></text>
<text x="50%" y="150" font-family="MS Mincho" font-size="20" fill="#778899" text-anchor="middle"></text>
<text x="50%" y="200" font-family="汇文明朝体" font-size="18" fill="#696969" text-anchor="middle">
<tspan x="50%" dy="25"></tspan>
<tspan x="50%" dy="25"></tspan>
<tspan x="50%" dy="25"></tspan>
<tspan x="50%" dy="25"></tspan>
</text>
<circle cx="200" cy="400" r="80" fill="none" stroke="#4169E1" stroke-width="3"/>
<line x1="200" y1="320" x2="200" y2="480" stroke="#4169E1" stroke-width="3"/>
<line x1="120" y1="400" x2="280" y2="400" stroke="#4169E1" stroke-width="3"/>
<text x="50%" y="550" font-family="微软雅黑" font-size="16" fill="#1E90FF" text-anchor="middle"> </text>
</svg>
\`\`\`

View File

@ -79,4 +79,4 @@
.avatar::after {
left: 5px;
}
}

Some files were not shown because too many files have changed in this diff Show More