fix: iteration node use the main thread pool

Signed-off-by: yihong0618 <zouzou0208@gmail.com>

.devcontainer/Dockerfile

@@ -1,5 +1,5 @@
-FROM mcr.microsoft.com/devcontainers/python:3.10
+FROM mcr.microsoft.com/devcontainers/python:3.12
 
 # [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>
+#     && apt-get -y install --no-install-recommends <your-package-list-here>

.devcontainer/devcontainer.json

@@ -1,7 +1,7 @@
 // For format details, see https://aka.ms/devcontainer.json. For config options, see the
 // README at: https://github.com/devcontainers/templates/tree/main/src/anaconda
 {
-	"name": "Python 3.10",
+	"name": "Python 3.12",
 	"build": { 
 		"context": "..",
 		"dockerfile": "Dockerfile"

.github/actions/setup-poetry/action.yml

@@ -4,7 +4,7 @@ inputs:
   python-version:
     description: Python version to use and the Poetry installed with
     required: true
-    default: '3.10'
+    default: '3.11'
   poetry-version:
     description: Poetry version to set up
     required: true

.github/workflows/api-tests.yml

@@ -20,7 +20,6 @@ jobs:
     strategy:
       matrix:
         python-version:
-          - "3.10"
           - "3.11"
           - "3.12"
 

.github/workflows/db-migration-test.yml

@@ -48,6 +48,8 @@ jobs:
           cp .env.example .env
 
       - name: Run DB Migration
+        env:
+          DEBUG: true
         run: |
           cd api
           poetry run python -m flask upgrade-db

.github/workflows/vdb-tests.yml

@@ -8,6 +8,8 @@ on:
       - api/core/rag/datasource/**
       - docker/**
       - .github/workflows/vdb-tests.yml
+      - api/poetry.lock
+      - api/pyproject.toml
 
 concurrency:
   group: vdb-tests-${{ github.head_ref || github.run_id }}
@@ -20,7 +22,6 @@ jobs:
     strategy:
       matrix:
         python-version:
-          - "3.10"
           - "3.11"
           - "3.12"
 

CONTRIBUTING_CN.md

@@ -71,7 +71,7 @@ Dify 依赖以下工具和库：
 - [Docker Compose](https://docs.docker.com/compose/install/)
 - [Node.js v18.x (LTS)](http://nodejs.org)
 - [npm](https://www.npmjs.com/) version 8.x.x or [Yarn](https://yarnpkg.com/)
-- [Python](https://www.python.org/) version 3.10.x
+- [Python](https://www.python.org/) version 3.11.x or 3.12.x
 
 ### 4. 安装
 

CONTRIBUTING_JA.md

@@ -74,7 +74,7 @@ Dify を構築するには次の依存関係が必要です。それらがシス
 - [Docker Compose](https://docs.docker.com/compose/install/)
 - [Node.js v18.x (LTS)](http://nodejs.org)
 - [npm](https://www.npmjs.com/) version 8.x.x or [Yarn](https://yarnpkg.com/)
-- [Python](https://www.python.org/) version 3.10.x
+- [Python](https://www.python.org/) version 3.11.x or 3.12.x
 
 ### 4. インストール
 

CONTRIBUTING_VI.md

@@ -73,7 +73,7 @@ Dify yêu cầu các phụ thuộc sau để build, hãy đảm bảo chúng đ
 - [Docker Compose](https://docs.docker.com/compose/install/)
 - [Node.js v18.x (LTS)](http://nodejs.org)
 - [npm](https://www.npmjs.com/) phiên bản 8.x.x hoặc [Yarn](https://yarnpkg.com/)
-- [Python](https://www.python.org/) phiên bản 3.10.x
+- [Python](https://www.python.org/) phiên bản 3.11.x hoặc 3.12.x
 
 ### 4. Cài đặt
 
@@ -153,4 +153,4 @@ Và thế là xong! Khi PR của bạn được merge, bạn sẽ được giớ
 
 ## Nhận trợ giúp
 
-Nếu bạn gặp khó khăn hoặc có câu hỏi cấp bách trong quá trình đóng góp, hãy đặt câu hỏi của bạn trong vấn đề GitHub liên quan, hoặc tham gia [Discord](https://discord.gg/8Tpq4AcN9c) của chúng tôi để trò chuyện nhanh chóng.
+Nếu bạn gặp khó khăn hoặc có câu hỏi cấp bách trong quá trình đóng góp, hãy đặt câu hỏi của bạn trong vấn đề GitHub liên quan, hoặc tham gia [Discord](https://discord.gg/8Tpq4AcN9c) của chúng tôi để trò chuyện nhanh chóng.

README.md

@@ -147,6 +147,13 @@ Deploy Dify to Cloud Platform with a single click using [terraform](https://www.
 ##### Google Cloud
 - [Google Cloud Terraform by @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### Using AWS CDK for Deployment
+
+Deploy Dify to AWS with [CDK](https://aws.amazon.com/cdk/)
+
+##### AWS 
+- [AWS CDK by @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## Contributing
 
 For those who'd like to contribute code, see our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). 

README_AR.md

@@ -190,6 +190,13 @@ docker compose up -d
 ##### Google Cloud
 - [Google Cloud Terraform بواسطة @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### استخدام AWS CDK للنشر
+
+انشر Dify على AWS باستخدام [CDK](https://aws.amazon.com/cdk/)
+
+##### AWS 
+- [AWS CDK بواسطة @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## المساهمة
 
 لأولئك الذين يرغبون في المساهمة، انظر إلى [دليل المساهمة](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) لدينا. 
@@ -222,3 +229,10 @@ docker compose up -d
 ## الرخصة
 
 هذا المستودع متاح تحت [رخصة البرنامج الحر Dify](LICENSE)، والتي تعتبر بشكل أساسي Apache 2.0 مع بعض القيود الإضافية.
+## الكشف عن الأمان
+
+لحماية خصوصيتك، يرجى تجنب نشر مشكلات الأمان على GitHub. بدلاً من ذلك، أرسل أسئلتك إلى security@dify.ai وسنقدم لك إجابة أكثر تفصيلاً.
+
+## الرخصة
+
+هذا المستودع متاح تحت [رخصة البرنامج الحر Dify](LICENSE)، والتي تعتبر بشكل أساسي Apache 2.0 مع بعض القيود الإضافية.

README_CN.md

@@ -213,6 +213,13 @@ docker compose up -d
 ##### Google Cloud
 - [Google Cloud Terraform by @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### 使用 AWS CDK 部署
+
+使用 [CDK](https://aws.amazon.com/cdk/) 将 Dify 部署到 AWS
+
+##### AWS 
+- [AWS CDK by @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## Star History
 
 [![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)

README_ES.md

@@ -215,6 +215,13 @@ Despliega Dify en una plataforma en la nube con un solo clic utilizando [terrafo
 ##### Google Cloud
 - [Google Cloud Terraform por @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### Usando AWS CDK para el Despliegue
+
+Despliegue Dify en AWS usando [CDK](https://aws.amazon.com/cdk/)
+
+##### AWS 
+- [AWS CDK por @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## Contribuir
 
 Para aquellos que deseen contribuir con código, consulten nuestra [Guía de contribución](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). 
@@ -248,3 +255,10 @@ Para proteger tu privacidad, evita publicar problemas de seguridad en GitHub. En
 ## Licencia
 
 Este repositorio está disponible bajo la [Licencia de Código Abierto de Dify](LICENSE), que es esencialmente Apache 2.0 con algunas restricciones adicionales.
+## Divulgación de Seguridad
+
+Para proteger tu privacidad, evita publicar problemas de seguridad en GitHub. En su lugar, envía tus preguntas a security@dify.ai y te proporcionaremos una respuesta más detallada.
+
+## Licencia
+
+Este repositorio está disponible bajo la [Licencia de Código Abierto de Dify](LICENSE), que es esencialmente Apache 2.0 con algunas restricciones adicionales.

README_FR.md

@@ -213,6 +213,13 @@ Déployez Dify sur une plateforme cloud en un clic en utilisant [terraform](http
 ##### Google Cloud
 - [Google Cloud Terraform par @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### Utilisation d'AWS CDK pour le déploiement
+
+Déployez Dify sur AWS en utilisant [CDK](https://aws.amazon.com/cdk/)
+
+##### AWS 
+- [AWS CDK par @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## Contribuer
 
 Pour ceux qui souhaitent contribuer du code, consultez notre [Guide de contribution](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). 
@@ -246,3 +253,10 @@ Pour protéger votre vie privée, veuillez éviter de publier des problèmes de
 ## Licence
 
 Ce référentiel est disponible sous la [Licence open source Dify](LICENSE), qui est essentiellement l'Apache 2.0 avec quelques restrictions supplémentaires.
+## Divulgation de sécurité
+
+Pour protéger votre vie privée, veuillez éviter de publier des problèmes de sécurité sur GitHub. Au lieu de cela, envoyez vos questions à security@dify.ai et nous vous fournirons une réponse plus détaillée.
+
+## Licence
+
+Ce référentiel est disponible sous la [Licence open source Dify](LICENSE), qui est essentiellement l'Apache 2.0 avec quelques restrictions supplémentaires.

README_JA.md

@@ -212,6 +212,13 @@ docker compose up -d
 ##### Google Cloud
 - [@sotazumによるGoogle Cloud Terraform](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### AWS CDK を使用したデプロイ
+
+[CDK](https://aws.amazon.com/cdk/) を使用して、DifyをAWSにデプロイします
+
+##### AWS 
+- [@KevinZhaoによるAWS CDK](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## 貢献
 
 コードに貢献したい方は、[Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)を参照してください。

README_KL.md

@@ -213,6 +213,13 @@ wa'logh nIqHom neH ghun deployment toy'wI' [terraform](https://www.terraform.io/
 ##### Google Cloud
 - [Google Cloud Terraform qachlot @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### AWS CDK atorlugh pilersitsineq
+
+wa'logh nIqHom neH ghun deployment toy'wI' [CDK](https://aws.amazon.com/cdk/) lo'laH.
+
+##### AWS 
+- [AWS CDK qachlot @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## Contributing
 
 For those who'd like to contribute code, see our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). 

README_KR.md

@@ -205,6 +205,13 @@ Dify를 Kubernetes에 배포하고 프리미엄 스케일링 설정을 구성했
 ##### Google Cloud
 - [sotazum의 Google Cloud Terraform](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### AWS CDK를 사용한 배포
+
+[CDK](https://aws.amazon.com/cdk/)를 사용하여 AWS에 Dify 배포
+
+##### AWS 
+- [KevinZhao의 AWS CDK](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## 기여
 
 코드에 기여하고 싶은 분들은 [기여 가이드](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)를 참조하세요.

README_PT.md

@@ -211,6 +211,13 @@ Implante o Dify na Plataforma Cloud com um único clique usando [terraform](http
 ##### Google Cloud
 - [Google Cloud Terraform por @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### Usando AWS CDK para Implantação
+
+Implante o Dify na AWS usando [CDK](https://aws.amazon.com/cdk/)
+
+##### AWS 
+- [AWS CDK por @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## Contribuindo
 
 Para aqueles que desejam contribuir com código, veja nosso [Guia de Contribuição](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). 

README_SI.md

@@ -145,6 +145,13 @@ namestite Dify v Cloud Platform z enim klikom z uporabo [terraform](https://www.
 ##### 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. 

README_TR.md

@@ -211,6 +211,13 @@ Dify'ı bulut platformuna tek tıklamayla dağıtın [terraform](https://www.ter
 ##### Google Cloud
 - [Google Cloud Terraform tarafından @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### AWS CDK ile Dağıtım
+
+[CDK](https://aws.amazon.com/cdk/) kullanarak Dify'ı AWS'ye dağıtın
+
+##### AWS 
+- [AWS CDK tarafından @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## Katkıda Bulunma
 
 Kod katkısında bulunmak isteyenler için [Katkı Kılavuzumuza](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) bakabilirsiniz.

README_VI.md

@@ -207,6 +207,13 @@ Triển khai Dify lên nền tảng đám mây với một cú nhấp chuột b
 ##### Google Cloud
 - [Google Cloud Terraform bởi @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### Sử dụng AWS CDK để Triển khai
+
+Triển khai Dify trên AWS bằng [CDK](https://aws.amazon.com/cdk/)
+
+##### AWS 
+- [AWS CDK bởi @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## Đóng góp
 
 Đối với những người muốn đóng góp mã, xem [Hướng dẫn Đóng góp](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) của chúng tôi. 

api/.env.example

@@ -329,6 +329,7 @@ NOTION_INTERNAL_SECRET=you-internal-secret
 ETL_TYPE=dify
 UNSTRUCTURED_API_URL=
 UNSTRUCTURED_API_KEY=
+SCARF_NO_ANALYTICS=true
 
 #ssrf
 SSRF_PROXY_HTTP_URL=
@@ -382,7 +383,7 @@ LOG_DATEFORMAT=%Y-%m-%d %H:%M:%S
 LOG_TZ=UTC
 
 # Indexing configuration
-INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH=1000
+INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH=4000
 
 # Workflow runtime configuration
 WORKFLOW_MAX_EXECUTION_STEPS=500
@@ -410,4 +411,6 @@ POSITION_PROVIDER_EXCLUDES=
 # Reset password token expiry minutes
 RESET_PASSWORD_TOKEN_EXPIRY_MINUTES=5
 
-CREATE_TIDB_SERVICE_JOB_ENABLED=false
+CREATE_TIDB_SERVICE_JOB_ENABLED=false
+
+RETRIEVAL_TOP_N=0

api/.ruff.toml

@@ -0,0 +1,93 @@
+exclude = [
+    "migrations/*",
+]
+line-length = 120
+
+[format]
+quote-style = "double"
+
+[lint]
+preview = true
+select = [
+    "B", # flake8-bugbear rules
+    "C4", # flake8-comprehensions
+    "E", # pycodestyle E rules
+    "F", # pyflakes rules
+    "FURB", # refurb rules
+    "I", # isort rules
+    "N", # pep8-naming
+    "PT", # flake8-pytest-style rules
+    "PLC0208", # iteration-over-set
+    "PLC2801", # unnecessary-dunder-call
+    "PLC0414", # useless-import-alias
+    "PLR0402", # manual-from-import
+    "PLR1711", # useless-return
+    "PLR1714", # repeated-equality-comparison
+    "RUF013", # implicit-optional
+    "RUF019", # unnecessary-key-check
+    "RUF100", # unused-noqa
+    "RUF101", # redirected-noqa
+    "RUF200", # invalid-pyproject-toml
+    "S506", # unsafe-yaml-load
+    "SIM", # flake8-simplify rules
+    "TRY400", # error-instead-of-exception
+    "TRY401", # verbose-log-message
+    "UP", # pyupgrade rules
+    "W191", # tab-indentation
+    "W605", # invalid-escape-sequence
+]
+
+ignore = [
+    "E402", # module-import-not-at-top-of-file
+    "E711", # none-comparison
+    "E712", # true-false-comparison
+    "E721", # type-comparison
+    "E722", # bare-except
+    "E731", # lambda-assignment
+    "F821", # undefined-name
+    "F841", # unused-variable
+    "FURB113", # repeated-append
+    "FURB152", # math-constant
+    "UP007", # non-pep604-annotation
+    "UP032", # f-string
+    "B005", # strip-with-multi-characters
+    "B006", # mutable-argument-default
+    "B007", # unused-loop-control-variable
+    "B026", # star-arg-unpacking-after-keyword-arg
+    "B904", # raise-without-from-inside-except
+    "B905", # zip-without-explicit-strict
+    "N806", # non-lowercase-variable-in-function
+    "N815", # mixed-case-variable-in-class-scope
+    "PT011", # pytest-raises-too-broad
+    "SIM102", # collapsible-if
+    "SIM103", # needless-bool
+    "SIM105", # suppressible-exception
+    "SIM107", # return-in-try-except-finally
+    "SIM108", # if-else-block-instead-of-if-exp
+    "SIM113", # eumerate-for-loop
+    "SIM117", # multiple-with-statements
+    "SIM210", # if-expr-with-true-false
+    "SIM300", # yoda-conditions,
+]
+
+[lint.per-file-ignores]
+"__init__.py" = [
+    "F401", # unused-import
+    "F811", # redefined-while-unused
+]
+"configs/*" = [
+    "N802", # invalid-function-name
+]
+"libs/gmpy2_pkcs10aep_cipher.py" = [
+    "N803", # invalid-argument-name
+]
+"tests/*" = [
+    "F811", # redefined-while-unused
+    "F401", # unused-import
+]
+
+[lint.pyflakes]
+extend-generics = [
+    "_pytest.monkeypatch",
+    "tests.integration_tests",
+]

api/Dockerfile

@@ -55,7 +55,7 @@ RUN apt-get update \
     && echo "deb http://deb.debian.org/debian testing main" > /etc/apt/sources.list \
     && apt-get update \
     # For Security
-    && apt-get install -y --no-install-recommends expat=2.6.4-1 libldap-2.5-0=2.5.18+dfsg-3+b1 perl=5.40.0-7 libsqlite3-0=3.46.1-1 zlib1g=1:1.3.dfsg+really1.3.1-1+b1 \
+    && apt-get install -y --no-install-recommends expat=2.6.4-1 libldap-2.5-0=2.5.18+dfsg-3+b1 perl=5.40.0-8 libsqlite3-0=3.46.1-1 zlib1g=1:1.3.dfsg+really1.3.1-1+b1 \
     # install a chinese font to support the use of tools like matplotlib
     && apt-get install -y fonts-noto-cjk \
     && apt-get autoremove -y \

api/app.py

@@ -1,111 +1,13 @@
-import os
-import sys
-
-from configs import dify_config
-
-if not dify_config.DEBUG:
-    from gevent import monkey
-
-    monkey.patch_all()
-
-    import grpc.experimental.gevent
-
-    grpc.experimental.gevent.init_gevent()
-
-import json
-import threading
-import time
-import warnings
-
-from flask import Response
-
 from app_factory import create_app
+from libs import threadings_utils, version_utils
 
-# DO NOT REMOVE BELOW
-from events import event_handlers  # noqa: F401
-from extensions.ext_database import db
-
-# TODO: Find a way to avoid importing models here
-from models import account, dataset, model, source, task, tool, tools, web  # noqa: F401
-
-# DO NOT REMOVE ABOVE
-
-if sys.version_info[:2] == (3, 10):
-    print("Warning: Python 3.10 will not be supported in the next version.")
-
-
-warnings.simplefilter("ignore", ResourceWarning)
-
-os.environ["TZ"] = "UTC"
-# windows platform not support tzset
-if hasattr(time, "tzset"):
-    time.tzset()
-
+# preparation before creating app
+version_utils.check_supported_python_version()
+threadings_utils.apply_gevent_threading_patch()
 
 # create app
 app = create_app()
 celery = app.extensions["celery"]
 
-if dify_config.TESTING:
-    print("App is running in TESTING mode")
-
-
-@app.after_request
-def after_request(response):
-    """Add Version headers to the response."""
-    response.headers.add("X-Version", dify_config.CURRENT_VERSION)
-    response.headers.add("X-Env", dify_config.DEPLOY_ENV)
-    return response
-
-
-@app.route("/health")
-def health():
-    return Response(
-        json.dumps({"pid": os.getpid(), "status": "ok", "version": dify_config.CURRENT_VERSION}),
-        status=200,
-        content_type="application/json",
-    )
-
-
-@app.route("/threads")
-def threads():
-    num_threads = threading.active_count()
-    threads = threading.enumerate()
-
-    thread_list = []
-    for thread in threads:
-        thread_name = thread.name
-        thread_id = thread.ident
-        is_alive = thread.is_alive()
-
-        thread_list.append(
-            {
-                "name": thread_name,
-                "id": thread_id,
-                "is_alive": is_alive,
-            }
-        )
-
-    return {
-        "pid": os.getpid(),
-        "thread_num": num_threads,
-        "threads": thread_list,
-    }
-
-
-@app.route("/db-pool-stat")
-def pool_stat():
-    engine = db.engine
-    return {
-        "pid": os.getpid(),
-        "pool_size": engine.pool.size(),
-        "checked_in_connections": engine.pool.checkedin(),
-        "checked_out_connections": engine.pool.checkedout(),
-        "overflow_connections": engine.pool.overflow(),
-        "connection_timeout": engine.pool.timeout(),
-        "recycle_time": db.engine.pool._recycle,
-    }
-
-
 if __name__ == "__main__":
     app.run(host="0.0.0.0", port=5001)

api/app_factory.py

@@ -1,54 +1,15 @@
+import logging
 import os
+import time
 
 from configs import dify_config
-
-if not dify_config.DEBUG:
-    from gevent import monkey
-
-    monkey.patch_all()
-
-    import grpc.experimental.gevent
-
-    grpc.experimental.gevent.init_gevent()
-
-import json
-
-from flask import Flask, Response, request
-from flask_cors import CORS
-from werkzeug.exceptions import Unauthorized
-
-import contexts
-from commands import register_commands
-from configs import dify_config
-from extensions import (
-    ext_celery,
-    ext_code_based_extension,
-    ext_compress,
-    ext_database,
-    ext_hosting_provider,
-    ext_logging,
-    ext_login,
-    ext_mail,
-    ext_migrate,
-    ext_proxy_fix,
-    ext_redis,
-    ext_sentry,
-    ext_storage,
-)
-from extensions.ext_database import db
-from extensions.ext_login import login_manager
-from libs.passport import PassportService
-from services.account_service import AccountService
-
-
-class DifyApp(Flask):
-    pass
+from dify_app import DifyApp
 
 
 # ----------------------------
 # Application Factory Function
 # ----------------------------
-def create_flask_app_with_configs() -> Flask:
+def create_flask_app_with_configs() -> DifyApp:
     """
     create a raw flask app
     with configs loaded from .env file
@@ -68,111 +29,72 @@ def create_flask_app_with_configs() -> Flask:
     return dify_app
 
 
-def create_app() -> Flask:
+def create_app() -> DifyApp:
+    start_time = time.perf_counter()
     app = create_flask_app_with_configs()
-    app.secret_key = dify_config.SECRET_KEY
     initialize_extensions(app)
-    register_blueprints(app)
-    register_commands(app)
-
+    end_time = time.perf_counter()
+    if dify_config.DEBUG:
+        logging.info(f"Finished create_app ({round((end_time - start_time) * 1000, 2)} ms)")
     return app
 
 
-def initialize_extensions(app):
-    # Since the application instance is now created, pass it to each Flask
-    # extension instance to bind it to the Flask application instance (app)
-    ext_logging.init_app(app)
-    ext_compress.init_app(app)
-    ext_code_based_extension.init()
-    ext_database.init_app(app)
-    ext_migrate.init(app, db)
-    ext_redis.init_app(app)
-    ext_storage.init_app(app)
-    ext_celery.init_app(app)
-    ext_login.init_app(app)
-    ext_mail.init_app(app)
-    ext_hosting_provider.init_app(app)
-    ext_sentry.init_app(app)
-    ext_proxy_fix.init_app(app)
-
-
-# Flask-Login configuration
-@login_manager.request_loader
-def load_user_from_request(request_from_flask_login):
-    """Load user based on the request."""
-    if request.blueprint not in {"console", "inner_api"}:
-        return None
-    # Check if the user_id contains a dot, indicating the old format
-    auth_header = request.headers.get("Authorization", "")
-    if not auth_header:
-        auth_token = request.args.get("_token")
-        if not auth_token:
-            raise Unauthorized("Invalid Authorization token.")
-    else:
-        if " " not in auth_header:
-            raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
-        auth_scheme, auth_token = auth_header.split(None, 1)
-        auth_scheme = auth_scheme.lower()
-        if auth_scheme != "bearer":
-            raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
-
-    decoded = PassportService().verify(auth_token)
-    user_id = decoded.get("user_id")
-
-    logged_in_account = AccountService.load_logged_in_account(account_id=user_id)
-    if logged_in_account:
-        contexts.tenant_id.set(logged_in_account.current_tenant_id)
-    return logged_in_account
-
-
-@login_manager.unauthorized_handler
-def unauthorized_handler():
-    """Handle unauthorized requests."""
-    return Response(
-        json.dumps({"code": "unauthorized", "message": "Unauthorized."}),
-        status=401,
-        content_type="application/json",
+def initialize_extensions(app: DifyApp):
+    from extensions import (
+        ext_app_metrics,
+        ext_blueprints,
+        ext_celery,
+        ext_code_based_extension,
+        ext_commands,
+        ext_compress,
+        ext_database,
+        ext_hosting_provider,
+        ext_import_modules,
+        ext_logging,
+        ext_login,
+        ext_mail,
+        ext_migrate,
+        ext_proxy_fix,
+        ext_redis,
+        ext_sentry,
+        ext_set_secretkey,
+        ext_storage,
+        ext_timezone,
+        ext_warnings,
     )
 
+    extensions = [
+        ext_timezone,
+        ext_logging,
+        ext_warnings,
+        ext_import_modules,
+        ext_set_secretkey,
+        ext_compress,
+        ext_code_based_extension,
+        ext_database,
+        ext_app_metrics,
+        ext_migrate,
+        ext_redis,
+        ext_storage,
+        ext_celery,
+        ext_login,
+        ext_mail,
+        ext_hosting_provider,
+        ext_sentry,
+        ext_proxy_fix,
+        ext_blueprints,
+        ext_commands,
+    ]
+    for ext in extensions:
+        short_name = ext.__name__.split(".")[-1]
+        is_enabled = ext.is_enabled() if hasattr(ext, "is_enabled") else True
+        if not is_enabled:
+            if dify_config.DEBUG:
+                logging.info(f"Skipped {short_name}")
+            continue
 
-# register blueprint routers
-def register_blueprints(app):
-    from controllers.console import bp as console_app_bp
-    from controllers.files import bp as files_bp
-    from controllers.inner_api import bp as inner_api_bp
-    from controllers.service_api import bp as service_api_bp
-    from controllers.web import bp as web_bp
-
-    CORS(
-        service_api_bp,
-        allow_headers=["Content-Type", "Authorization", "X-App-Code"],
-        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
-    )
-    app.register_blueprint(service_api_bp)
-
-    CORS(
-        web_bp,
-        resources={r"/*": {"origins": dify_config.WEB_API_CORS_ALLOW_ORIGINS}},
-        supports_credentials=True,
-        allow_headers=["Content-Type", "Authorization", "X-App-Code"],
-        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
-        expose_headers=["X-Version", "X-Env"],
-    )
-
-    app.register_blueprint(web_bp)
-
-    CORS(
-        console_app_bp,
-        resources={r"/*": {"origins": dify_config.CONSOLE_CORS_ALLOW_ORIGINS}},
-        supports_credentials=True,
-        allow_headers=["Content-Type", "Authorization"],
-        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
-        expose_headers=["X-Version", "X-Env"],
-    )
-
-    app.register_blueprint(console_app_bp)
-
-    CORS(files_bp, allow_headers=["Content-Type"], methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"])
-    app.register_blueprint(files_bp)
-
-    app.register_blueprint(inner_api_bp)
+        start_time = time.perf_counter()
+        ext.init_app(app)
+        end_time = time.perf_counter()
+        if dify_config.DEBUG:
+            logging.info(f"Loaded {short_name} ({round((end_time - start_time) * 1000, 2)} ms)")

api/commands.py

@@ -640,15 +640,3 @@ where sites.id is null limit 1000"""
                 break
 
     click.echo(click.style("Fix for missing app-related sites completed successfully!", fg="green"))
-
-
-def register_commands(app):
-    app.cli.add_command(reset_password)
-    app.cli.add_command(reset_email)
-    app.cli.add_command(reset_encrypt_key_pair)
-    app.cli.add_command(vdb_migrate)
-    app.cli.add_command(convert_to_agent_apps)
-    app.cli.add_command(add_qdrant_doc_id_index)
-    app.cli.add_command(create_tenant)
-    app.cli.add_command(upgrade_db)
-    app.cli.add_command(fix_app_site_missing)

api/configs/deploy/__init__.py

@@ -17,11 +17,6 @@ class DeploymentConfig(BaseSettings):
         default=False,
     )
 
-    TESTING: bool = Field(
-        description="Enable testing mode for running automated tests",
-        default=False,
-    )
-
     EDITION: str = Field(
         description="Deployment edition of the application (e.g., 'SELF_HOSTED', 'CLOUD')",
         default="SELF_HOSTED",

api/configs/feature/__init__.py

@@ -585,6 +585,11 @@ class RagEtlConfig(BaseSettings):
         default=None,
     )
 
+    SCARF_NO_ANALYTICS: Optional[str] = Field(
+        description="This is about whether to disable Scarf analytics in Unstructured library.",
+        default="false",
+    )
+
 
 class DataSetConfig(BaseSettings):
     """
@@ -621,6 +626,8 @@ class DataSetConfig(BaseSettings):
         default=30,
     )
 
+    RETRIEVAL_TOP_N: int = Field(description="number of retrieval top_n", default=0)
+
 
 class WorkspaceConfig(BaseSettings):
     """
@@ -640,7 +647,7 @@ class IndexingConfig(BaseSettings):
 
     INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH: PositiveInt = Field(
         description="Maximum token length for text segmentation during indexing",
-        default=1000,
+        default=4000,
     )
 
 

api/configs/packaging/__init__.py

@@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):
 
     CURRENT_VERSION: str = Field(
         description="Dify version",
-        default="0.11.2",
+        default="0.12.1",
     )
 
     COMMIT_SHA: str = Field(

api/constants/languages.py

@@ -18,6 +18,7 @@ language_timezone_mapping = {
     "tr-TR": "Europe/Istanbul",
     "fa-IR": "Asia/Tehran",
     "sl-SI": "Europe/Ljubljana",
+    "th-TH": "Asia/Bangkok",
 }
 
 languages = list(language_timezone_mapping.keys())

api/controllers/console/__init__.py

@@ -62,7 +62,6 @@ from .datasets import (
     external,
     hit_testing,
     website,
-    fta_test,
 )
 
 # Import explore controllers

api/controllers/console/app/app.py

@@ -190,7 +190,7 @@ class AppCopyApi(Resource):
             )
             session.commit()
 
-            stmt = select(App).where(App.id == result.app.id)
+            stmt = select(App).where(App.id == result.app_id)
             app = session.scalar(stmt)
 
         return app, 201

api/controllers/console/app/conversation.py

@@ -1,4 +1,4 @@
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 
 import pytz
 from flask_login import current_user
@@ -314,7 +314,7 @@ def _get_conversation(app_model, conversation_id):
         raise NotFound("Conversation Not Exists.")
 
     if not conversation.read_at:
-        conversation.read_at = datetime.now(timezone.utc).replace(tzinfo=None)
+        conversation.read_at = datetime.now(UTC).replace(tzinfo=None)
         conversation.read_account_id = current_user.id
         db.session.commit()
 

api/controllers/console/app/site.py

@@ -1,4 +1,4 @@
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 
 from flask_login import current_user
 from flask_restful import Resource, marshal_with, reqparse
@@ -75,7 +75,7 @@ class AppSite(Resource):
                 setattr(site, attr_name, value)
 
         site.updated_by = current_user.id
-        site.updated_at = datetime.now(timezone.utc).replace(tzinfo=None)
+        site.updated_at = datetime.now(UTC).replace(tzinfo=None)
         db.session.commit()
 
         return site
@@ -99,7 +99,7 @@ class AppSiteAccessTokenReset(Resource):
 
         site.code = Site.generate_code(16)
         site.updated_by = current_user.id
-        site.updated_at = datetime.now(timezone.utc).replace(tzinfo=None)
+        site.updated_at = datetime.now(UTC).replace(tzinfo=None)
         db.session.commit()
 
         return site

api/controllers/console/auth/activate.py

@@ -65,7 +65,7 @@ class ActivateApi(Resource):
         account.timezone = args["timezone"]
         account.interface_theme = "light"
         account.status = AccountStatus.ACTIVE.value
-        account.initialized_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+        account.initialized_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
         db.session.commit()
 
         token_pair = AccountService.login(account, ip_address=extract_remote_ip(request))

api/controllers/console/auth/data_source_oauth.py

@@ -34,7 +34,6 @@ class OAuthDataSource(Resource):
         OAUTH_DATASOURCE_PROVIDERS = get_oauth_providers()
         with current_app.app_context():
             oauth_provider = OAUTH_DATASOURCE_PROVIDERS.get(provider)
-            print(vars(oauth_provider))
         if not oauth_provider:
             return {"error": "Invalid provider"}, 400
         if dify_config.NOTION_INTEGRATION_TYPE == "internal":

api/controllers/console/auth/oauth.py

@@ -1,5 +1,5 @@
 import logging
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 from typing import Optional
 
 import requests
@@ -52,7 +52,6 @@ class OAuthLogin(Resource):
         OAUTH_PROVIDERS = get_oauth_providers()
         with current_app.app_context():
             oauth_provider = OAUTH_PROVIDERS.get(provider)
-            print(vars(oauth_provider))
         if not oauth_provider:
             return {"error": "Invalid provider"}, 400
 
@@ -106,7 +105,7 @@ class OAuthCallback(Resource):
 
         if account.status == AccountStatus.PENDING.value:
             account.status = AccountStatus.ACTIVE.value
-            account.initialized_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            account.initialized_at = datetime.now(UTC).replace(tzinfo=None)
             db.session.commit()
 
         try:

api/controllers/console/datasets/data_source.py

@@ -83,7 +83,7 @@ class DataSourceApi(Resource):
         if action == "enable":
             if data_source_binding.disabled:
                 data_source_binding.disabled = False
-                data_source_binding.updated_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+                data_source_binding.updated_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
                 db.session.add(data_source_binding)
                 db.session.commit()
             else:
@@ -92,7 +92,7 @@ class DataSourceApi(Resource):
         if action == "disable":
             if not data_source_binding.disabled:
                 data_source_binding.disabled = True
-                data_source_binding.updated_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+                data_source_binding.updated_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
                 db.session.add(data_source_binding)
                 db.session.commit()
             else:

api/controllers/console/datasets/datasets_document.py

@@ -1,6 +1,6 @@
 import logging
 from argparse import ArgumentTypeError
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 
 from flask import request
 from flask_login import current_user
@@ -106,6 +106,7 @@ class GetProcessRuleApi(Resource):
         # get default rules
         mode = DocumentService.DEFAULT_RULES["mode"]
         rules = DocumentService.DEFAULT_RULES["rules"]
+        limits = DocumentService.DEFAULT_RULES["limits"]
         if document_id:
             # get the latest process rule
             document = Document.query.get_or_404(document_id)
@@ -132,7 +133,7 @@ class GetProcessRuleApi(Resource):
                 mode = dataset_process_rule.mode
                 rules = dataset_process_rule.rules_dict
 
-        return {"mode": mode, "rules": rules}
+        return {"mode": mode, "rules": rules, "limits": limits}
 
 
 class DatasetDocumentListApi(Resource):
@@ -665,7 +666,7 @@ class DocumentProcessingApi(DocumentResource):
                 raise InvalidActionError("Document not in indexing state.")
 
             document.paused_by = current_user.id
-            document.paused_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            document.paused_at = datetime.now(UTC).replace(tzinfo=None)
             document.is_paused = True
             db.session.commit()
 
@@ -745,7 +746,7 @@ class DocumentMetadataApi(DocumentResource):
                     document.doc_metadata[key] = value
 
         document.doc_type = doc_type
-        document.updated_at = datetime.now(timezone.utc).replace(tzinfo=None)
+        document.updated_at = datetime.now(UTC).replace(tzinfo=None)
         db.session.commit()
 
         return {"result": "success", "message": "Document metadata updated."}, 200
@@ -787,7 +788,7 @@ class DocumentStatusApi(DocumentResource):
             document.enabled = True
             document.disabled_at = None
             document.disabled_by = None
-            document.updated_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            document.updated_at = datetime.now(UTC).replace(tzinfo=None)
             db.session.commit()
 
             # Set cache to prevent indexing the same document multiple times
@@ -804,9 +805,9 @@ class DocumentStatusApi(DocumentResource):
                 raise InvalidActionError("Document already disabled.")
 
             document.enabled = False
-            document.disabled_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            document.disabled_at = datetime.now(UTC).replace(tzinfo=None)
             document.disabled_by = current_user.id
-            document.updated_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            document.updated_at = datetime.now(UTC).replace(tzinfo=None)
             db.session.commit()
 
             # Set cache to prevent indexing the same document multiple times
@@ -821,9 +822,9 @@ class DocumentStatusApi(DocumentResource):
                 raise InvalidActionError("Document already archived.")
 
             document.archived = True
-            document.archived_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            document.archived_at = datetime.now(UTC).replace(tzinfo=None)
             document.archived_by = current_user.id
-            document.updated_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            document.updated_at = datetime.now(UTC).replace(tzinfo=None)
             db.session.commit()
 
             if document.enabled:
@@ -840,7 +841,7 @@ class DocumentStatusApi(DocumentResource):
             document.archived = False
             document.archived_at = None
             document.archived_by = None
-            document.updated_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            document.updated_at = datetime.now(UTC).replace(tzinfo=None)
             db.session.commit()
 
             # Set cache to prevent indexing the same document multiple times

api/controllers/console/datasets/datasets_segments.py

@@ -1,5 +1,5 @@
 import uuid
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 
 import pandas as pd
 from flask import request
@@ -188,7 +188,7 @@ class DatasetDocumentSegmentApi(Resource):
                 raise InvalidActionError("Segment is already disabled.")
 
             segment.enabled = False
-            segment.disabled_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            segment.disabled_at = datetime.now(UTC).replace(tzinfo=None)
             segment.disabled_by = current_user.id
             db.session.commit()
 

api/controllers/console/datasets/fta_test.py

@@ -1,145 +0,0 @@
-import json
-
-import requests
-from flask import Response
-from flask_restful import Resource, reqparse
-from sqlalchemy import text
-
-from controllers.console import api
-from extensions.ext_database import db
-from extensions.ext_storage import storage
-from models.fta import ComponentFailure, ComponentFailureStats
-
-
-class FATTestApi(Resource):
-    def post(self):
-        parser = reqparse.RequestParser()
-        parser.add_argument("log_process_data", nullable=False, required=True, type=str, location="args")
-        args = parser.parse_args()
-        print(args["log_process_data"])
-        # Extract the JSON string from the text field
-        json_str = args["log_process_data"].strip("```json\\n").strip("```").strip().replace("\\n", "")
-        log_data = json.loads(json_str)
-        db.session.query(ComponentFailure).delete()
-        for data in log_data:
-            if not isinstance(data, dict):
-                raise TypeError("Data must be a dictionary.")
-
-            required_keys = {"Date", "Component", "FailureMode", "Cause", "RepairAction", "Technician"}
-            if not required_keys.issubset(data.keys()):
-                raise ValueError(f"Data dictionary must contain the following keys: {required_keys}")
-
-            try:
-                # Clear existing stats
-                component_failure = ComponentFailure(
-                    Date=data["Date"],
-                    Component=data["Component"],
-                    FailureMode=data["FailureMode"],
-                    Cause=data["Cause"],
-                    RepairAction=data["RepairAction"],
-                    Technician=data["Technician"],
-                )
-                db.session.add(component_failure)
-                db.session.commit()
-            except Exception as e:
-                print(e)
-        # Clear existing stats
-        db.session.query(ComponentFailureStats).delete()
-
-        # Insert calculated statistics
-        try:
-            db.session.execute(
-                text("""
-                    INSERT INTO component_failure_stats ("Component", "FailureMode", "Cause", "PossibleAction", "Probability", "MTBF")
-                    SELECT 
-                        cf."Component",
-                        cf."FailureMode",
-                        cf."Cause",
-                        cf."RepairAction" as "PossibleAction",
-                        COUNT(*) * 1.0 / (SELECT COUNT(*) FROM component_failure WHERE "Component" = cf."Component") AS "Probability",
-                        COALESCE(AVG(EXTRACT(EPOCH FROM (next_failure_date::timestamp - cf."Date"::timestamp)) / 86400.0),0)AS "MTBF"
-                    FROM (
-                        SELECT 
-                            "Component",
-                            "FailureMode",
-                            "Cause",
-                            "RepairAction",
-                            "Date", 
-                            LEAD("Date") OVER (PARTITION BY "Component", "FailureMode", "Cause" ORDER BY "Date") AS next_failure_date
-                        FROM 
-                            component_failure
-                    ) cf
-                    GROUP BY 
-                        cf."Component", cf."FailureMode", cf."Cause", cf."RepairAction";
-            """)
-            )
-            db.session.commit()
-        except Exception as e:
-            db.session.rollback()
-            print(f"Error during stats calculation: {e}")
-        # output format
-        # [
-        #     (17, 'Hydraulic system', 'Leak', 'Hose rupture', 'Replaced hydraulic hose', 0.3333333333333333, None),
-        #     (18, 'Hydraulic system', 'Leak', 'Seal Wear', 'Replaced the faulty seal', 0.3333333333333333, None),
-        #     (19, 'Hydraulic system', 'Pressure drop', 'Fluid leak', 'Replaced hydraulic fluid and seals', 0.3333333333333333, None)
-        # ]
-
-        component_failure_stats = db.session.query(ComponentFailureStats).all()
-        # Convert stats to list of tuples format
-        stats_list = []
-        for stat in component_failure_stats:
-            stats_list.append(
-                (
-                    stat.StatID,
-                    stat.Component,
-                    stat.FailureMode,
-                    stat.Cause,
-                    stat.PossibleAction,
-                    stat.Probability,
-                    stat.MTBF,
-                )
-            )
-        return {"data": stats_list}, 200
-
-
-# generate-fault-tree
-class GenerateFaultTreeApi(Resource):
-    def post(self):
-        parser = reqparse.RequestParser()
-        parser.add_argument("llm_text", nullable=False, required=True, type=str, location="args")
-        args = parser.parse_args()
-        entities = args["llm_text"].replace("```", "").replace("\\n", "\n")
-        print(entities)
-        request_data = {"fault_tree_text": entities}
-        url = "https://fta.cognitech-dev.live/generate-fault-tree"
-        headers = {"accept": "application/json", "Content-Type": "application/json"}
-
-        response = requests.post(url, json=request_data, headers=headers)
-        print(response.json())
-        return {"data": response.json()}, 200
-
-
-class ExtractSVGApi(Resource):
-    def post(self):
-        parser = reqparse.RequestParser()
-        parser.add_argument("svg_text", nullable=False, required=True, type=str, location="args")
-        args = parser.parse_args()
-        # svg_text = ''.join(args["svg_text"].splitlines())
-        svg_text = args["svg_text"].replace("\n", "")
-        svg_text = svg_text.replace('"', '"')
-        print(svg_text)
-        svg_text_json = json.loads(svg_text)
-        svg_content = svg_text_json.get("data").get("svg_content")[0]
-        svg_content = svg_content.replace("\n", "").replace('"', '"')
-        file_key = "fta_svg/" + "fat.svg"
-        if storage.exists(file_key):
-            storage.delete(file_key)
-        storage.save(file_key, svg_content.encode("utf-8"))
-        generator = storage.load(file_key, stream=True)
-
-        return Response(generator, mimetype="image/svg+xml")
-
-
-api.add_resource(FATTestApi, "/fta/db-handler")
-api.add_resource(GenerateFaultTreeApi, "/fta/generate-fault-tree")
-api.add_resource(ExtractSVGApi, "/fta/extract-svg")

api/controllers/console/explore/completion.py

@@ -1,5 +1,5 @@
 import logging
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 
 from flask_login import current_user
 from flask_restful import reqparse
@@ -46,7 +46,7 @@ class CompletionApi(InstalledAppResource):
         streaming = args["response_mode"] == "streaming"
         args["auto_generate_name"] = False
 
-        installed_app.last_used_at = datetime.now(timezone.utc).replace(tzinfo=None)
+        installed_app.last_used_at = datetime.now(UTC).replace(tzinfo=None)
         db.session.commit()
 
         try:
@@ -106,7 +106,7 @@ class ChatApi(InstalledAppResource):
 
         args["auto_generate_name"] = False
 
-        installed_app.last_used_at = datetime.now(timezone.utc).replace(tzinfo=None)
+        installed_app.last_used_at = datetime.now(UTC).replace(tzinfo=None)
         db.session.commit()
 
         try:

api/controllers/console/explore/installed_app.py

@@ -1,4 +1,4 @@
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 
 from flask_login import current_user
 from flask_restful import Resource, inputs, marshal_with, reqparse
@@ -81,7 +81,7 @@ class InstalledAppsListApi(Resource):
                 tenant_id=current_tenant_id,
                 app_owner_tenant_id=app.tenant_id,
                 is_pinned=False,
-                last_used_at=datetime.now(timezone.utc).replace(tzinfo=None),
+                last_used_at=datetime.now(UTC).replace(tzinfo=None),
             )
             db.session.add(new_installed_app)
             db.session.commit()

api/controllers/console/workspace/account.py

@@ -60,7 +60,7 @@ class AccountInitApi(Resource):
                 raise InvalidInvitationCodeError()
 
             invitation_code.status = "used"
-            invitation_code.used_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+            invitation_code.used_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
             invitation_code.used_by_tenant_id = account.current_tenant_id
             invitation_code.used_by_account_id = account.id
 
@@ -68,7 +68,7 @@ class AccountInitApi(Resource):
         account.timezone = args["timezone"]
         account.interface_theme = "light"
         account.status = "active"
-        account.initialized_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+        account.initialized_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
         db.session.commit()
 
         return {"result": "success"}

api/controllers/service_api/app/app.py

@@ -48,7 +48,8 @@ class AppInfoApi(Resource):
     @validate_app_token
     def get(self, app_model: App):
         """Get app information"""
-        return {"name": app_model.name, "description": app_model.description}
+        tags = [tag.name for tag in app_model.tags]
+        return {"name": app_model.name, "description": app_model.description, "tags": tags}
 
 
 api.add_resource(AppParameterApi, "/parameters")

api/controllers/service_api/wraps.py

@@ -1,5 +1,5 @@
 from collections.abc import Callable
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 from enum import Enum
 from functools import wraps
 from typing import Optional
@@ -198,7 +198,7 @@ def validate_and_get_api_token(scope=None):
     if not api_token:
         raise Unauthorized("Access token is invalid")
 
-    api_token.last_used_at = datetime.now(timezone.utc).replace(tzinfo=None)
+    api_token.last_used_at = datetime.now(UTC).replace(tzinfo=None)
     db.session.commit()
 
     return api_token

api/core/agent/base_agent_runner.py

@@ -2,7 +2,7 @@ import json
 import logging
 import uuid
 from collections.abc import Mapping, Sequence
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 from typing import Optional, Union, cast
 
 from core.agent.entities import AgentEntity, AgentToolEntity
@@ -412,7 +412,7 @@ class BaseAgentRunner(AppRunner):
             .first()
         )
 
-        db_variables.updated_at = datetime.now(timezone.utc).replace(tzinfo=None)
+        db_variables.updated_at = datetime.now(UTC).replace(tzinfo=None)
         db_variables.variables_str = json.dumps(jsonable_encoder(tool_variables.pool))
         db.session.commit()
         db.session.close()

api/core/app/app_config/easy_ui_based_app/dataset/manager.py

@@ -1,3 +1,4 @@
+import uuid
 from typing import Optional
 
 from core.app.app_config.entities import DatasetEntity, DatasetRetrieveConfigEntity

api/core/app/app_config/easy_ui_based_app/model_config/manager.py

@@ -1,3 +1,6 @@
+from collections.abc import Mapping
+from typing import Any
+
 from core.app.app_config.entities import ModelConfigEntity
 from core.model_runtime.entities.model_entities import ModelPropertyKey, ModelType
 from core.model_runtime.model_providers import model_provider_factory
@@ -36,7 +39,7 @@ class ModelConfigManager:
         )
 
     @classmethod
-    def validate_and_set_defaults(cls, tenant_id: str, config: dict) -> tuple[dict, list[str]]:
+    def validate_and_set_defaults(cls, tenant_id: str, config: Mapping[str, Any]) -> tuple[dict, list[str]]:
         """
         Validate and set defaults for model config
 

api/core/app/app_config/easy_ui_based_app/prompt_template/manager.py

@@ -1,4 +1,5 @@
 from core.app.app_config.entities import (
+    AdvancedChatMessageEntity,
     AdvancedChatPromptTemplateEntity,
     AdvancedCompletionPromptTemplateEntity,
     PromptTemplateEntity,
@@ -25,7 +26,9 @@ class PromptTemplateConfigManager:
                 chat_prompt_messages = []
                 for message in chat_prompt_config.get("prompt", []):
                     chat_prompt_messages.append(
-                        {"text": message["text"], "role": PromptMessageRole.value_of(message["role"])}
+                        AdvancedChatMessageEntity(
+                            **{"text": message["text"], "role": PromptMessageRole.value_of(message["role"])}
+                        )
                     )
 
                 advanced_chat_prompt_template = AdvancedChatPromptTemplateEntity(messages=chat_prompt_messages)

api/core/app/app_config/entities.py

@@ -1,5 +1,5 @@
 from collections.abc import Sequence
-from enum import Enum
+from enum import Enum, StrEnum
 from typing import Any, Optional
 
 from pydantic import BaseModel, Field, field_validator
@@ -88,7 +88,7 @@ class PromptTemplateEntity(BaseModel):
     advanced_completion_prompt_template: Optional[AdvancedCompletionPromptTemplateEntity] = None
 
 
-class VariableEntityType(str, Enum):
+class VariableEntityType(StrEnum):
     TEXT_INPUT = "text-input"
     SELECT = "select"
     PARAGRAPH = "paragraph"

api/core/app/apps/advanced_chat/app_generator.py

@@ -2,8 +2,8 @@ import contextvars
 import logging
 import threading
 import uuid
-from collections.abc import Generator
-from typing import Any, Literal, Optional, Union, overload
+from collections.abc import Generator, Mapping
+from typing import Any, Optional, Union
 
 from flask import Flask, current_app
 from pydantic import ValidationError
@@ -23,6 +23,7 @@ from core.app.entities.app_invoke_entities import AdvancedChatAppGenerateEntity,
 from core.app.entities.task_entities import ChatbotAppBlockingResponse, ChatbotAppStreamResponse
 from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
 from core.ops.ops_trace_manager import TraceQueueManager
+from core.prompt.utils.get_thread_messages_length import get_thread_messages_length
 from extensions.ext_database import db
 from factories import file_factory
 from models.account import Account
@@ -33,37 +34,17 @@ logger = logging.getLogger(__name__)
 
 
 class AdvancedChatAppGenerator(MessageBasedAppGenerator):
-    @overload
-    def generate(
-        self,
-        app_model: App,
-        workflow: Workflow,
-        user: Union[Account, EndUser],
-        args: dict,
-        invoke_from: InvokeFrom,
-        stream: Literal[True] = True,
-    ) -> Generator[str, None, None]: ...
-
-    @overload
-    def generate(
-        self,
-        app_model: App,
-        workflow: Workflow,
-        user: Union[Account, EndUser],
-        args: dict,
-        invoke_from: InvokeFrom,
-        stream: Literal[False] = False,
-    ) -> dict: ...
+    _dialogue_count: int
 
     def generate(
         self,
         app_model: App,
         workflow: Workflow,
         user: Union[Account, EndUser],
-        args: dict,
+        args: Mapping[str, Any],
         invoke_from: InvokeFrom,
-        stream: bool = True,
-    ) -> dict[str, Any] | Generator[str, Any, None]:
+        streaming: bool = True,
+    ) -> Mapping[str, Any] | Generator[str, None, None]:
         """
         Generate App response.
 
@@ -127,12 +108,14 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
             conversation_id=conversation.id if conversation else None,
             inputs=conversation.inputs
             if conversation
-            else self._prepare_user_inputs(user_inputs=inputs, app_config=app_config),
+            else self._prepare_user_inputs(
+                user_inputs=inputs, variables=app_config.variables, tenant_id=app_model.tenant_id
+            ),
             query=query,
             files=file_objs,
             parent_message_id=args.get("parent_message_id") if invoke_from != InvokeFrom.SERVICE_API else UUID_NIL,
             user_id=user.id,
-            stream=stream,
+            stream=streaming,
             invoke_from=invoke_from,
             extras=extras,
             trace_manager=trace_manager,
@@ -146,12 +129,12 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
             invoke_from=invoke_from,
             application_generate_entity=application_generate_entity,
             conversation=conversation,
-            stream=stream,
+            stream=streaming,
         )
 
     def single_iteration_generate(
-        self, app_model: App, workflow: Workflow, node_id: str, user: Account, args: dict, stream: bool = True
-    ) -> dict[str, Any] | Generator[str, Any, None]:
+        self, app_model: App, workflow: Workflow, node_id: str, user: Account, args: dict, streaming: bool = True
+    ) -> Mapping[str, Any] | Generator[str, None, None]:
         """
         Generate App response.
 
@@ -180,7 +163,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
             query="",
             files=[],
             user_id=user.id,
-            stream=stream,
+            stream=streaming,
             invoke_from=InvokeFrom.DEBUGGER,
             extras={"auto_generate_conversation_name": False},
             single_iteration_run=AdvancedChatAppGenerateEntity.SingleIterationRunEntity(
@@ -195,7 +178,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
             invoke_from=InvokeFrom.DEBUGGER,
             application_generate_entity=application_generate_entity,
             conversation=None,
-            stream=stream,
+            stream=streaming,
         )
 
     def _generate(
@@ -207,7 +190,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
         application_generate_entity: AdvancedChatAppGenerateEntity,
         conversation: Optional[Conversation] = None,
         stream: bool = True,
-    ) -> dict[str, Any] | Generator[str, Any, None]:
+    ) -> Mapping[str, Any] | Generator[str, None, None]:
         """
         Generate App response.
 
@@ -231,6 +214,9 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
             db.session.commit()
             db.session.refresh(conversation)
 
+        # get conversation dialogue count
+        self._dialogue_count = get_thread_messages_length(conversation.id)
+
         # init queue manager
         queue_manager = MessageBasedAppQueueManager(
             task_id=application_generate_entity.task_id,
@@ -301,6 +287,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
                     queue_manager=queue_manager,
                     conversation=conversation,
                     message=message,
+                    dialogue_count=self._dialogue_count,
                 )
 
                 runner.run()
@@ -354,6 +341,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
             message=message,
             user=user,
             stream=stream,
+            dialogue_count=self._dialogue_count,
         )
 
         try:

api/core/app/apps/advanced_chat/app_runner.py

@@ -39,12 +39,14 @@ class AdvancedChatAppRunner(WorkflowBasedAppRunner):
         queue_manager: AppQueueManager,
         conversation: Conversation,
         message: Message,
+        dialogue_count: int,
     ) -> None:
         super().__init__(queue_manager)
 
         self.application_generate_entity = application_generate_entity
         self.conversation = conversation
         self.message = message
+        self._dialogue_count = dialogue_count
 
     def run(self) -> None:
         app_config = self.application_generate_entity.app_config
@@ -122,19 +124,13 @@ class AdvancedChatAppRunner(WorkflowBasedAppRunner):
 
                 session.commit()
 
-            # Increment dialogue count.
-            self.conversation.dialogue_count += 1
-
-            conversation_dialogue_count = self.conversation.dialogue_count
-            db.session.commit()
-
             # Create a variable pool.
             system_inputs = {
                 SystemVariableKey.QUERY: query,
                 SystemVariableKey.FILES: files,
                 SystemVariableKey.CONVERSATION_ID: self.conversation.id,
                 SystemVariableKey.USER_ID: user_id,
-                SystemVariableKey.DIALOGUE_COUNT: conversation_dialogue_count,
+                SystemVariableKey.DIALOGUE_COUNT: self._dialogue_count,
                 SystemVariableKey.APP_ID: app_config.app_id,
                 SystemVariableKey.WORKFLOW_ID: app_config.workflow_id,
                 SystemVariableKey.WORKFLOW_RUN_ID: self.application_generate_entity.workflow_run_id,

api/core/app/apps/advanced_chat/generate_task_pipeline.py

@@ -88,6 +88,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
         message: Message,
         user: Union[Account, EndUser],
         stream: bool,
+        dialogue_count: int,
     ) -> None:
         """
         Initialize AdvancedChatAppGenerateTaskPipeline.
@@ -98,6 +99,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
         :param message: message
         :param user: user
         :param stream: stream
+        :param dialogue_count: dialogue count
         """
         super().__init__(application_generate_entity, queue_manager, user, stream)
 
@@ -114,7 +116,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
             SystemVariableKey.FILES: application_generate_entity.files,
             SystemVariableKey.CONVERSATION_ID: conversation.id,
             SystemVariableKey.USER_ID: user_id,
-            SystemVariableKey.DIALOGUE_COUNT: conversation.dialogue_count,
+            SystemVariableKey.DIALOGUE_COUNT: dialogue_count,
             SystemVariableKey.APP_ID: application_generate_entity.app_config.app_id,
             SystemVariableKey.WORKFLOW_ID: workflow.id,
             SystemVariableKey.WORKFLOW_RUN_ID: application_generate_entity.workflow_run_id,
@@ -125,6 +127,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
 
         self._conversation_name_generate_thread = None
         self._recorded_files: list[Mapping[str, Any]] = []
+        self.total_tokens: int = 0
 
     def process(self):
         """
@@ -358,6 +361,8 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
                 if not workflow_run:
                     raise Exception("Workflow run not initialized.")
 
+                # FIXME for issue #11221 quick fix maybe have a better solution
+                self.total_tokens += event.metadata.get("total_tokens", 0) if event.metadata else 0
                 yield self._workflow_iteration_completed_to_stream_response(
                     task_id=self._application_generate_entity.task_id, workflow_run=workflow_run, event=event
                 )
@@ -371,7 +376,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
                 workflow_run = self._handle_workflow_run_success(
                     workflow_run=workflow_run,
                     start_at=graph_runtime_state.start_at,
-                    total_tokens=graph_runtime_state.total_tokens,
+                    total_tokens=graph_runtime_state.total_tokens or self.total_tokens,
                     total_steps=graph_runtime_state.node_run_steps,
                     outputs=event.outputs,
                     conversation_id=self._conversation.id,

api/core/app/apps/agent_chat/app_config_manager.py

@@ -1,5 +1,6 @@
 import uuid
-from typing import Optional
+from collections.abc import Mapping
+from typing import Any, Optional
 
 from core.agent.entities import AgentEntity
 from core.app.app_config.base_app_config_manager import BaseAppConfigManager
@@ -85,7 +86,7 @@ class AgentChatAppConfigManager(BaseAppConfigManager):
         return app_config
 
     @classmethod
-    def config_validate(cls, tenant_id: str, config: dict) -> dict:
+    def config_validate(cls, tenant_id: str, config: Mapping[str, Any]) -> dict:
         """
         Validate for agent chat app model config
 

api/core/app/apps/agent_chat/app_generator.py

@@ -1,8 +1,8 @@
 import logging
 import threading
 import uuid
-from collections.abc import Generator
-from typing import Any, Literal, Union, overload
+from collections.abc import Generator, Mapping
+from typing import Any, Union
 
 from flask import Flask, current_app
 from pydantic import ValidationError
@@ -28,34 +28,15 @@ logger = logging.getLogger(__name__)
 
 
 class AgentChatAppGenerator(MessageBasedAppGenerator):
-    @overload
     def generate(
         self,
+        *,
         app_model: App,
         user: Union[Account, EndUser],
-        args: dict,
+        args: Mapping[str, Any],
         invoke_from: InvokeFrom,
-        stream: Literal[True] = True,
-    ) -> Generator[dict, None, None]: ...
-
-    @overload
-    def generate(
-        self,
-        app_model: App,
-        user: Union[Account, EndUser],
-        args: dict,
-        invoke_from: InvokeFrom,
-        stream: Literal[False] = False,
-    ) -> dict: ...
-
-    def generate(
-        self,
-        app_model: App,
-        user: Union[Account, EndUser],
-        args: Any,
-        invoke_from: InvokeFrom,
-        stream: bool = True,
-    ) -> Union[dict, Generator[dict, None, None]]:
+        streaming: bool = True,
+    ) -> Mapping[str, Any] | Generator[str, None, None]:
         """
         Generate App response.
 
@@ -65,7 +46,7 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
         :param invoke_from: invoke from source
         :param stream: is stream
         """
-        if not stream:
+        if not streaming:
             raise ValueError("Agent Chat App does not support blocking mode")
 
         if not args.get("query"):
@@ -96,7 +77,8 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
 
             # validate config
             override_model_config_dict = AgentChatAppConfigManager.config_validate(
-                tenant_id=app_model.tenant_id, config=args.get("model_config")
+                tenant_id=app_model.tenant_id,
+                config=args["model_config"],
             )
 
             # always enable retriever resource in debugger mode
@@ -134,12 +116,14 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
             conversation_id=conversation.id if conversation else None,
             inputs=conversation.inputs
             if conversation
-            else self._prepare_user_inputs(user_inputs=inputs, app_config=app_config),
+            else self._prepare_user_inputs(
+                user_inputs=inputs, variables=app_config.variables, tenant_id=app_model.tenant_id
+            ),
             query=query,
             files=file_objs,
             parent_message_id=args.get("parent_message_id") if invoke_from != InvokeFrom.SERVICE_API else UUID_NIL,
             user_id=user.id,
-            stream=stream,
+            stream=streaming,
             invoke_from=invoke_from,
             extras=extras,
             call_depth=0,
@@ -180,7 +164,7 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
             conversation=conversation,
             message=message,
             user=user,
-            stream=stream,
+            stream=streaming,
         )
 
         return AgentChatAppGenerateResponseConverter.convert(response=response, invoke_from=invoke_from)

api/core/app/apps/base_app_generate_response_converter.py

@@ -1,6 +1,6 @@
 import logging
 from abc import ABC, abstractmethod
-from collections.abc import Generator
+from collections.abc import Generator, Mapping
 from typing import Any, Union
 
 from core.app.entities.app_invoke_entities import InvokeFrom
@@ -14,8 +14,10 @@ class AppGenerateResponseConverter(ABC):
 
     @classmethod
     def convert(
-        cls, response: Union[AppBlockingResponse, Generator[AppStreamResponse, Any, None]], invoke_from: InvokeFrom
-    ) -> dict[str, Any] | Generator[str, Any, None]:
+        cls,
+        response: Union[AppBlockingResponse, Generator[AppStreamResponse, Any, None]],
+        invoke_from: InvokeFrom,
+    ) -> Mapping[str, Any] | Generator[str, None, None]:
         if invoke_from in {InvokeFrom.DEBUGGER, InvokeFrom.SERVICE_API}:
             if isinstance(response, AppBlockingResponse):
                 return cls.convert_blocking_full_response(response)

api/core/app/apps/base_app_generator.py

@@ -1,4 +1,4 @@
-from collections.abc import Mapping
+from collections.abc import Mapping, Sequence
 from typing import TYPE_CHECKING, Any, Optional
 
 from core.app.app_config.entities import VariableEntityType
@@ -6,7 +6,7 @@ from core.file import File, FileUploadConfig
 from factories import file_factory
 
 if TYPE_CHECKING:
-    from core.app.app_config.entities import AppConfig, VariableEntity
+    from core.app.app_config.entities import VariableEntity
 
 
 class BaseAppGenerator:
@@ -14,23 +14,23 @@ class BaseAppGenerator:
         self,
         *,
         user_inputs: Optional[Mapping[str, Any]],
-        app_config: "AppConfig",
+        variables: Sequence["VariableEntity"],
+        tenant_id: str,
     ) -> Mapping[str, Any]:
         user_inputs = user_inputs or {}
         # Filter input variables from form configuration, handle required fields, default values, and option values
-        variables = app_config.variables
         user_inputs = {
             var.variable: self._validate_inputs(value=user_inputs.get(var.variable), variable_entity=var)
             for var in variables
         }
         user_inputs = {k: self._sanitize_value(v) for k, v in user_inputs.items()}
         # Convert files in inputs to File
-        entity_dictionary = {item.variable: item for item in app_config.variables}
+        entity_dictionary = {item.variable: item for item in variables}
         # Convert single file to File
         files_inputs = {
             k: file_factory.build_from_mapping(
                 mapping=v,
-                tenant_id=app_config.tenant_id,
+                tenant_id=tenant_id,
                 config=FileUploadConfig(
                     allowed_file_types=entity_dictionary[k].allowed_file_types,
                     allowed_file_extensions=entity_dictionary[k].allowed_file_extensions,
@@ -44,7 +44,7 @@ class BaseAppGenerator:
         file_list_inputs = {
             k: file_factory.build_from_mappings(
                 mappings=v,
-                tenant_id=app_config.tenant_id,
+                tenant_id=tenant_id,
                 config=FileUploadConfig(
                     allowed_file_types=entity_dictionary[k].allowed_file_types,
                     allowed_file_extensions=entity_dictionary[k].allowed_file_extensions,

api/core/app/apps/chat/app_generator.py

@@ -55,7 +55,7 @@ class ChatAppGenerator(MessageBasedAppGenerator):
         user: Union[Account, EndUser],
         args: Any,
         invoke_from: InvokeFrom,
-        stream: bool = True,
+        streaming: bool = True,
     ) -> Union[dict, Generator[str, None, None]]:
         """
         Generate App response.
@@ -132,7 +132,9 @@ class ChatAppGenerator(MessageBasedAppGenerator):
             conversation_id=conversation.id if conversation else None,
             inputs=conversation.inputs
             if conversation
-            else self._prepare_user_inputs(user_inputs=inputs, app_config=app_config),
+            else self._prepare_user_inputs(
+                user_inputs=inputs, variables=app_config.variables, tenant_id=app_model.tenant_id
+            ),
             query=query,
             files=file_objs,
             parent_message_id=args.get("parent_message_id") if invoke_from != InvokeFrom.SERVICE_API else UUID_NIL,
@@ -140,7 +142,7 @@ class ChatAppGenerator(MessageBasedAppGenerator):
             invoke_from=invoke_from,
             extras=extras,
             trace_manager=trace_manager,
-            stream=stream,
+            stream=streaming,
         )
 
         # init generate records
@@ -177,7 +179,7 @@ class ChatAppGenerator(MessageBasedAppGenerator):
             conversation=conversation,
             message=message,
             user=user,
-            stream=stream,
+            stream=streaming,
         )
 
         return ChatAppGenerateResponseConverter.convert(response=response, invoke_from=invoke_from)

api/core/app/apps/completion/app_generator.py

@@ -50,7 +50,7 @@ class CompletionAppGenerator(MessageBasedAppGenerator):
     ) -> dict: ...
 
     def generate(
-        self, app_model: App, user: Union[Account, EndUser], args: Any, invoke_from: InvokeFrom, stream: bool = True
+        self, app_model: App, user: Union[Account, EndUser], args: Any, invoke_from: InvokeFrom, streaming: bool = True
     ) -> Union[dict, Generator[str, None, None]]:
         """
         Generate App response.
@@ -113,11 +113,13 @@ class CompletionAppGenerator(MessageBasedAppGenerator):
             app_config=app_config,
             model_conf=ModelConfigConverter.convert(app_config),
             file_upload_config=file_extra_config,
-            inputs=self._prepare_user_inputs(user_inputs=inputs, app_config=app_config),
+            inputs=self._prepare_user_inputs(
+                user_inputs=inputs, variables=app_config.variables, tenant_id=app_model.tenant_id
+            ),
             query=query,
             files=file_objs,
             user_id=user.id,
-            stream=stream,
+            stream=streaming,
             invoke_from=invoke_from,
             extras=extras,
             trace_manager=trace_manager,
@@ -156,7 +158,7 @@ class CompletionAppGenerator(MessageBasedAppGenerator):
             conversation=conversation,
             message=message,
             user=user,
-            stream=stream,
+            stream=streaming,
         )
 
         return CompletionAppGenerateResponseConverter.convert(response=response, invoke_from=invoke_from)

api/core/app/apps/message_based_app_generator.py

@@ -1,7 +1,7 @@
 import json
 import logging
 from collections.abc import Generator
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 from typing import Optional, Union
 
 from sqlalchemy import and_
@@ -200,7 +200,7 @@ class MessageBasedAppGenerator(BaseAppGenerator):
             db.session.commit()
             db.session.refresh(conversation)
         else:
-            conversation.updated_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            conversation.updated_at = datetime.now(UTC).replace(tzinfo=None)
             db.session.commit()
 
         message = Message(

api/core/app/apps/workflow/app_generator.py

@@ -3,7 +3,7 @@ import logging
 import threading
 import uuid
 from collections.abc import Generator, Mapping, Sequence
-from typing import Any, Literal, Optional, Union, overload
+from typing import Any, Optional, Union
 
 from flask import Flask, current_app
 from pydantic import ValidationError
@@ -30,43 +30,18 @@ logger = logging.getLogger(__name__)
 
 
 class WorkflowAppGenerator(BaseAppGenerator):
-    @overload
     def generate(
         self,
+        *,
         app_model: App,
         workflow: Workflow,
-        user: Union[Account, EndUser],
-        args: dict,
-        invoke_from: InvokeFrom,
-        stream: Literal[True] = True,
-        call_depth: int = 0,
-        workflow_thread_pool_id: Optional[str] = None,
-    ) -> Generator[str, None, None]: ...
-
-    @overload
-    def generate(
-        self,
-        app_model: App,
-        workflow: Workflow,
-        user: Union[Account, EndUser],
-        args: dict,
-        invoke_from: InvokeFrom,
-        stream: Literal[False] = False,
-        call_depth: int = 0,
-        workflow_thread_pool_id: Optional[str] = None,
-    ) -> dict: ...
-
-    def generate(
-        self,
-        app_model: App,
-        workflow: Workflow,
-        user: Union[Account, EndUser],
+        user: Account | EndUser,
         args: Mapping[str, Any],
         invoke_from: InvokeFrom,
-        stream: bool = True,
+        streaming: bool = True,
         call_depth: int = 0,
         workflow_thread_pool_id: Optional[str] = None,
-    ):
+    ) -> Mapping[str, Any] | Generator[str, None, None]:
         files: Sequence[Mapping[str, Any]] = args.get("files") or []
 
         # parse files
@@ -96,10 +71,12 @@ class WorkflowAppGenerator(BaseAppGenerator):
             task_id=str(uuid.uuid4()),
             app_config=app_config,
             file_upload_config=file_extra_config,
-            inputs=self._prepare_user_inputs(user_inputs=inputs, app_config=app_config),
+            inputs=self._prepare_user_inputs(
+                user_inputs=inputs, variables=app_config.variables, tenant_id=app_model.tenant_id
+            ),
             files=system_files,
             user_id=user.id,
-            stream=stream,
+            stream=streaming,
             invoke_from=invoke_from,
             call_depth=call_depth,
             trace_manager=trace_manager,
@@ -113,7 +90,7 @@ class WorkflowAppGenerator(BaseAppGenerator):
             user=user,
             application_generate_entity=application_generate_entity,
             invoke_from=invoke_from,
-            stream=stream,
+            streaming=streaming,
             workflow_thread_pool_id=workflow_thread_pool_id,
         )
 
@@ -125,20 +102,9 @@ class WorkflowAppGenerator(BaseAppGenerator):
         user: Union[Account, EndUser],
         application_generate_entity: WorkflowAppGenerateEntity,
         invoke_from: InvokeFrom,
-        stream: bool = True,
+        streaming: bool = True,
         workflow_thread_pool_id: Optional[str] = None,
-    ) -> dict[str, Any] | Generator[str, None, None]:
-        """
-        Generate App response.
-
-        :param app_model: App
-        :param workflow: Workflow
-        :param user: account or end user
-        :param application_generate_entity: application generate entity
-        :param invoke_from: invoke from source
-        :param stream: is stream
-        :param workflow_thread_pool_id: workflow thread pool id
-        """
+    ) -> Mapping[str, Any] | Generator[str, None, None]:
         # init queue manager
         queue_manager = WorkflowAppQueueManager(
             task_id=application_generate_entity.task_id,
@@ -167,14 +133,20 @@ class WorkflowAppGenerator(BaseAppGenerator):
             workflow=workflow,
             queue_manager=queue_manager,
             user=user,
-            stream=stream,
+            stream=streaming,
         )
 
         return WorkflowAppGenerateResponseConverter.convert(response=response, invoke_from=invoke_from)
 
     def single_iteration_generate(
-        self, app_model: App, workflow: Workflow, node_id: str, user: Account, args: dict, stream: bool = True
-    ) -> dict[str, Any] | Generator[str, Any, None]:
+        self,
+        app_model: App,
+        workflow: Workflow,
+        node_id: str,
+        user: Account,
+        args: Mapping[str, Any],
+        streaming: bool = True,
+    ) -> Mapping[str, Any] | Generator[str, None, None]:
         """
         Generate App response.
 
@@ -201,7 +173,7 @@ class WorkflowAppGenerator(BaseAppGenerator):
             inputs={},
             files=[],
             user_id=user.id,
-            stream=stream,
+            stream=streaming,
             invoke_from=InvokeFrom.DEBUGGER,
             extras={"auto_generate_conversation_name": False},
             single_iteration_run=WorkflowAppGenerateEntity.SingleIterationRunEntity(
@@ -216,7 +188,7 @@ class WorkflowAppGenerator(BaseAppGenerator):
             user=user,
             invoke_from=InvokeFrom.DEBUGGER,
             application_generate_entity=application_generate_entity,
-            stream=stream,
+            streaming=streaming,
         )
 
     def _generate_worker(

api/core/app/apps/workflow/generate_task_pipeline.py

@@ -106,6 +106,7 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
 
         self._task_state = WorkflowTaskState()
         self._wip_workflow_node_executions = {}
+        self.total_tokens: int = 0
 
     def process(self) -> Union[WorkflowAppBlockingResponse, Generator[WorkflowAppStreamResponse, None, None]]:
         """
@@ -319,6 +320,8 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
                 if not workflow_run:
                     raise Exception("Workflow run not initialized.")
 
+                # FIXME for issue #11221 quick fix maybe have a better solution
+                self.total_tokens += event.metadata.get("total_tokens", 0) if event.metadata else 0
                 yield self._workflow_iteration_completed_to_stream_response(
                     task_id=self._application_generate_entity.task_id, workflow_run=workflow_run, event=event
                 )
@@ -332,7 +335,7 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
                 workflow_run = self._handle_workflow_run_success(
                     workflow_run=workflow_run,
                     start_at=graph_runtime_state.start_at,
-                    total_tokens=graph_runtime_state.total_tokens,
+                    total_tokens=graph_runtime_state.total_tokens or self.total_tokens,
                     total_steps=graph_runtime_state.node_run_steps,
                     outputs=event.outputs,
                     conversation_id=None,

api/core/app/apps/workflow_app_runner.py

@@ -43,7 +43,6 @@ from core.workflow.graph_engine.entities.event import (
 )
 from core.workflow.graph_engine.entities.graph import Graph
 from core.workflow.nodes import NodeType
-from core.workflow.nodes.iteration import IterationNodeData
 from core.workflow.nodes.node_mapping import node_type_classes_mapping
 from core.workflow.workflow_entry import WorkflowEntry
 from extensions.ext_database import db
@@ -160,8 +159,6 @@ class WorkflowBasedAppRunner(AppRunner):
             user_inputs=user_inputs,
             variable_pool=variable_pool,
             tenant_id=workflow.tenant_id,
-            node_type=node_type,
-            node_data=IterationNodeData(**iteration_node_config.get("data", {})),
         )
 
         return graph, variable_pool

api/core/app/entities/queue_entities.py

@@ -1,5 +1,5 @@
 from datetime import datetime
-from enum import Enum
+from enum import Enum, StrEnum
 from typing import Any, Optional
 
 from pydantic import BaseModel, field_validator
@@ -11,7 +11,7 @@ from core.workflow.nodes import NodeType
 from core.workflow.nodes.base import BaseNodeData
 
 
-class QueueEvent(str, Enum):
+class QueueEvent(StrEnum):
     """
     QueueEvent enum
     """

api/core/app/features/rate_limiting/rate_limit.py

@@ -1,9 +1,9 @@
 import logging
 import time
 import uuid
-from collections.abc import Generator
+from collections.abc import Generator, Mapping
 from datetime import timedelta
-from typing import Optional, Union
+from typing import Any, Optional, Union
 
 from core.errors.error import AppInvokeQuotaExceededError
 from extensions.ext_redis import redis_client
@@ -88,20 +88,17 @@ class RateLimit:
     def gen_request_key() -> str:
         return str(uuid.uuid4())
 
-    def generate(self, generator: Union[Generator, callable, dict], request_id: str):
-        if isinstance(generator, dict):
+    def generate(self, generator: Union[Generator[str, None, None], Mapping[str, Any]], request_id: str):
+        if isinstance(generator, Mapping):
             return generator
         else:
-            return RateLimitGenerator(self, generator, request_id)
+            return RateLimitGenerator(rate_limit=self, generator=generator, request_id=request_id)
 
 
 class RateLimitGenerator:
-    def __init__(self, rate_limit: RateLimit, generator: Union[Generator, callable], request_id: str):
+    def __init__(self, rate_limit: RateLimit, generator: Generator[str, None, None], request_id: str):
         self.rate_limit = rate_limit
-        if callable(generator):
-            self.generator = generator()
-        else:
-            self.generator = generator
+        self.generator = generator
         self.request_id = request_id
         self.closed = False
 

api/core/app/task_pipeline/workflow_cycle_manage.py

@@ -1,8 +1,9 @@
 import json
 import time
 from collections.abc import Mapping, Sequence
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 from typing import Any, Optional, Union, cast
+from uuid import uuid4
 
 from sqlalchemy.orm import Session
 
@@ -80,38 +81,38 @@ class WorkflowCycleManage:
 
             inputs[f"sys.{key.value}"] = value
 
-        inputs = WorkflowEntry.handle_special_values(inputs)
-
         triggered_from = (
             WorkflowRunTriggeredFrom.DEBUGGING
             if self._application_generate_entity.invoke_from == InvokeFrom.DEBUGGER
             else WorkflowRunTriggeredFrom.APP_RUN
         )
 
-        # init workflow run
-        workflow_run = WorkflowRun()
-        workflow_run_id = self._workflow_system_variables[SystemVariableKey.WORKFLOW_RUN_ID]
-        if workflow_run_id:
-            workflow_run.id = workflow_run_id
-        workflow_run.tenant_id = self._workflow.tenant_id
-        workflow_run.app_id = self._workflow.app_id
-        workflow_run.sequence_number = new_sequence_number
-        workflow_run.workflow_id = self._workflow.id
-        workflow_run.type = self._workflow.type
-        workflow_run.triggered_from = triggered_from.value
-        workflow_run.version = self._workflow.version
-        workflow_run.graph = self._workflow.graph
-        workflow_run.inputs = json.dumps(inputs)
-        workflow_run.status = WorkflowRunStatus.RUNNING.value
-        workflow_run.created_by_role = (
-            CreatedByRole.ACCOUNT.value if isinstance(self._user, Account) else CreatedByRole.END_USER.value
-        )
-        workflow_run.created_by = self._user.id
+        # handle special values
+        inputs = WorkflowEntry.handle_special_values(inputs)
 
-        db.session.add(workflow_run)
-        db.session.commit()
-        db.session.refresh(workflow_run)
-        db.session.close()
+        # init workflow run
+        with Session(db.engine, expire_on_commit=False) as session:
+            workflow_run = WorkflowRun()
+            system_id = self._workflow_system_variables[SystemVariableKey.WORKFLOW_RUN_ID]
+            workflow_run.id = system_id or str(uuid4())
+            workflow_run.tenant_id = self._workflow.tenant_id
+            workflow_run.app_id = self._workflow.app_id
+            workflow_run.sequence_number = new_sequence_number
+            workflow_run.workflow_id = self._workflow.id
+            workflow_run.type = self._workflow.type
+            workflow_run.triggered_from = triggered_from.value
+            workflow_run.version = self._workflow.version
+            workflow_run.graph = self._workflow.graph
+            workflow_run.inputs = json.dumps(inputs)
+            workflow_run.status = WorkflowRunStatus.RUNNING
+            workflow_run.created_by_role = (
+                CreatedByRole.ACCOUNT if isinstance(self._user, Account) else CreatedByRole.END_USER
+            )
+            workflow_run.created_by = self._user.id
+            workflow_run.created_at = datetime.now(UTC).replace(tzinfo=None)
+
+            session.add(workflow_run)
+            session.commit()
 
         return workflow_run
 
@@ -144,7 +145,7 @@ class WorkflowCycleManage:
         workflow_run.elapsed_time = time.perf_counter() - start_at
         workflow_run.total_tokens = total_tokens
         workflow_run.total_steps = total_steps
-        workflow_run.finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
+        workflow_run.finished_at = datetime.now(UTC).replace(tzinfo=None)
 
         db.session.commit()
         db.session.refresh(workflow_run)
@@ -191,7 +192,7 @@ class WorkflowCycleManage:
         workflow_run.elapsed_time = time.perf_counter() - start_at
         workflow_run.total_tokens = total_tokens
         workflow_run.total_steps = total_steps
-        workflow_run.finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
+        workflow_run.finished_at = datetime.now(UTC).replace(tzinfo=None)
 
         db.session.commit()
 
@@ -211,7 +212,7 @@ class WorkflowCycleManage:
         for workflow_node_execution in running_workflow_node_executions:
             workflow_node_execution.status = WorkflowNodeExecutionStatus.FAILED.value
             workflow_node_execution.error = error
-            workflow_node_execution.finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            workflow_node_execution.finished_at = datetime.now(UTC).replace(tzinfo=None)
             workflow_node_execution.elapsed_time = (
                 workflow_node_execution.finished_at - workflow_node_execution.created_at
             ).total_seconds()
@@ -262,7 +263,7 @@ class WorkflowCycleManage:
                     NodeRunMetadataKey.ITERATION_ID: event.in_iteration_id,
                 }
             )
-            workflow_node_execution.created_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            workflow_node_execution.created_at = datetime.now(UTC).replace(tzinfo=None)
 
             session.add(workflow_node_execution)
             session.commit()
@@ -285,7 +286,7 @@ class WorkflowCycleManage:
         execution_metadata = (
             json.dumps(jsonable_encoder(event.execution_metadata)) if event.execution_metadata else None
         )
-        finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
+        finished_at = datetime.now(UTC).replace(tzinfo=None)
         elapsed_time = (finished_at - event.start_at).total_seconds()
 
         db.session.query(WorkflowNodeExecution).filter(WorkflowNodeExecution.id == workflow_node_execution.id).update(
@@ -329,7 +330,7 @@ class WorkflowCycleManage:
         inputs = WorkflowEntry.handle_special_values(event.inputs)
         process_data = WorkflowEntry.handle_special_values(event.process_data)
         outputs = WorkflowEntry.handle_special_values(event.outputs)
-        finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
+        finished_at = datetime.now(UTC).replace(tzinfo=None)
         elapsed_time = (finished_at - event.start_at).total_seconds()
         execution_metadata = (
             json.dumps(jsonable_encoder(event.execution_metadata)) if event.execution_metadata else None
@@ -339,7 +340,7 @@ class WorkflowCycleManage:
                 WorkflowNodeExecution.status: WorkflowNodeExecutionStatus.FAILED.value,
                 WorkflowNodeExecution.error: event.error,
                 WorkflowNodeExecution.inputs: json.dumps(inputs) if inputs else None,
-                WorkflowNodeExecution.process_data: json.dumps(event.process_data) if event.process_data else None,
+                WorkflowNodeExecution.process_data: json.dumps(process_data) if process_data else None,
                 WorkflowNodeExecution.outputs: json.dumps(outputs) if outputs else None,
                 WorkflowNodeExecution.finished_at: finished_at,
                 WorkflowNodeExecution.elapsed_time: elapsed_time,
@@ -657,7 +658,7 @@ class WorkflowCycleManage:
                 if event.error is None
                 else WorkflowNodeExecutionStatus.FAILED,
                 error=None,
-                elapsed_time=(datetime.now(timezone.utc).replace(tzinfo=None) - event.start_at).total_seconds(),
+                elapsed_time=(datetime.now(UTC).replace(tzinfo=None) - event.start_at).total_seconds(),
                 total_tokens=event.metadata.get("total_tokens", 0) if event.metadata else 0,
                 execution_metadata=event.metadata,
                 finished_at=int(time.time()),

api/core/entities/provider_configuration.py

@@ -240,7 +240,7 @@ class ProviderConfiguration(BaseModel):
         if provider_record:
             provider_record.encrypted_config = json.dumps(credentials)
             provider_record.is_valid = True
-            provider_record.updated_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+            provider_record.updated_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
             db.session.commit()
         else:
             provider_record = Provider(
@@ -394,7 +394,7 @@ class ProviderConfiguration(BaseModel):
         if provider_model_record:
             provider_model_record.encrypted_config = json.dumps(credentials)
             provider_model_record.is_valid = True
-            provider_model_record.updated_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+            provider_model_record.updated_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
             db.session.commit()
         else:
             provider_model_record = ProviderModel(
@@ -468,7 +468,7 @@ class ProviderConfiguration(BaseModel):
 
         if model_setting:
             model_setting.enabled = True
-            model_setting.updated_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+            model_setting.updated_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
             db.session.commit()
         else:
             model_setting = ProviderModelSetting(
@@ -503,7 +503,7 @@ class ProviderConfiguration(BaseModel):
 
         if model_setting:
             model_setting.enabled = False
-            model_setting.updated_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+            model_setting.updated_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
             db.session.commit()
         else:
             model_setting = ProviderModelSetting(
@@ -570,7 +570,7 @@ class ProviderConfiguration(BaseModel):
 
         if model_setting:
             model_setting.load_balancing_enabled = True
-            model_setting.updated_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+            model_setting.updated_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
             db.session.commit()
         else:
             model_setting = ProviderModelSetting(
@@ -605,7 +605,7 @@ class ProviderConfiguration(BaseModel):
 
         if model_setting:
             model_setting.load_balancing_enabled = False
-            model_setting.updated_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+            model_setting.updated_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
             db.session.commit()
         else:
             model_setting = ProviderModelSetting(

api/core/file/enums.py

@@ -1,7 +1,7 @@
-from enum import Enum
+from enum import StrEnum
 
 
-class FileType(str, Enum):
+class FileType(StrEnum):
     IMAGE = "image"
     DOCUMENT = "document"
     AUDIO = "audio"
@@ -16,7 +16,7 @@ class FileType(str, Enum):
         raise ValueError(f"No matching enum found for value '{value}'")
 
 
-class FileTransferMethod(str, Enum):
+class FileTransferMethod(StrEnum):
     REMOTE_URL = "remote_url"
     LOCAL_FILE = "local_file"
     TOOL_FILE = "tool_file"
@@ -29,7 +29,7 @@ class FileTransferMethod(str, Enum):
         raise ValueError(f"No matching enum found for value '{value}'")
 
 
-class FileBelongsTo(str, Enum):
+class FileBelongsTo(StrEnum):
     USER = "user"
     ASSISTANT = "assistant"
 
@@ -41,7 +41,7 @@ class FileBelongsTo(str, Enum):
         raise ValueError(f"No matching enum found for value '{value}'")
 
 
-class FileAttribute(str, Enum):
+class FileAttribute(StrEnum):
     TYPE = "type"
     SIZE = "size"
     NAME = "name"
@@ -51,5 +51,5 @@ class FileAttribute(str, Enum):
     EXTENSION = "extension"
 
 
-class ArrayFileAttribute(str, Enum):
+class ArrayFileAttribute(StrEnum):
     LENGTH = "length"

api/core/file/file_manager.py

@@ -1,6 +1,4 @@
 import base64
-import tempfile
-from pathlib import Path
 
 from configs import dify_config
 from core.file import file_repository
@@ -20,38 +18,6 @@ from .models import File, FileTransferMethod, FileType
 from .tool_file_parser import ToolFileParser
 
 
-def download_to_target_path(f: File, temp_dir: str, /):
-    if f.transfer_method == FileTransferMethod.TOOL_FILE:
-        tool_file = file_repository.get_tool_file(session=db.session(), file=f)
-        suffix = Path(tool_file.file_key).suffix
-        target_path = f"{temp_dir}/{next(tempfile._get_candidate_names())}{suffix}"
-        _download_file_to_target_path(tool_file.file_key, target_path)
-        return target_path
-    elif f.transfer_method == FileTransferMethod.LOCAL_FILE:
-        upload_file = file_repository.get_upload_file(session=db.session(), file=f)
-        suffix = Path(upload_file.key).suffix
-        target_path = f"{temp_dir}/{next(tempfile._get_candidate_names())}{suffix}"
-        _download_file_to_target_path(upload_file.key, target_path)
-        return target_path
-    else:
-        raise ValueError(f"Unsupported transfer method: {f.transfer_method}")
-
-
-def _download_file_to_target_path(path: str, target_path: str, /):
-    """
-    Download and return the contents of a file as bytes.
-
-    This function loads the file from storage and ensures it's in bytes format.
-
-    Args:
-        path (str): The path to the file in storage.
-        target_path (str): The path to the target file.
-    Raises:
-        ValueError: If the loaded file is not a bytes object.
-    """
-    storage.download(path, target_path)
-
-
 def get_attr(*, file: File, attr: FileAttribute):
     match attr:
         case FileAttribute.TYPE:

api/core/helper/code_executor/code_executor.py

@@ -1,6 +1,6 @@
 import logging
 from collections.abc import Mapping
-from enum import Enum
+from enum import StrEnum
 from threading import Lock
 from typing import Any, Optional
 
@@ -31,7 +31,7 @@ class CodeExecutionResponse(BaseModel):
     data: Data
 
 
-class CodeLanguage(str, Enum):
+class CodeLanguage(StrEnum):
     PYTHON3 = "python3"
     JINJA2 = "jinja2"
     JAVASCRIPT = "javascript"

api/core/helper/ssrf_proxy.py

@@ -53,8 +53,6 @@ def make_request(method, url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):
                     response = client.request(method=method, url=url, **kwargs)
 
             if response.status_code not in STATUS_FORCELIST:
-                if stream:
-                    return response.iter_bytes()
                 return response
             else:
                 logging.warning(f"Received status code {response.status_code} for URL {url} which is in the force list")

api/core/indexing_runner.py

@@ -86,7 +86,7 @@ class IndexingRunner:
             except ProviderTokenNotInitError as e:
                 dataset_document.indexing_status = "error"
                 dataset_document.error = str(e.description)
-                dataset_document.stopped_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+                dataset_document.stopped_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
                 db.session.commit()
             except ObjectDeletedError:
                 logging.warning("Document deleted, document id: {}".format(dataset_document.id))
@@ -94,7 +94,7 @@ class IndexingRunner:
                 logging.exception("consume document failed")
                 dataset_document.indexing_status = "error"
                 dataset_document.error = str(e)
-                dataset_document.stopped_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+                dataset_document.stopped_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
                 db.session.commit()
 
     def run_in_splitting_status(self, dataset_document: DatasetDocument):
@@ -142,13 +142,13 @@ class IndexingRunner:
         except ProviderTokenNotInitError as e:
             dataset_document.indexing_status = "error"
             dataset_document.error = str(e.description)
-            dataset_document.stopped_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+            dataset_document.stopped_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
             db.session.commit()
         except Exception as e:
             logging.exception("consume document failed")
             dataset_document.indexing_status = "error"
             dataset_document.error = str(e)
-            dataset_document.stopped_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+            dataset_document.stopped_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
             db.session.commit()
 
     def run_in_indexing_status(self, dataset_document: DatasetDocument):
@@ -200,13 +200,13 @@ class IndexingRunner:
         except ProviderTokenNotInitError as e:
             dataset_document.indexing_status = "error"
             dataset_document.error = str(e.description)
-            dataset_document.stopped_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+            dataset_document.stopped_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
             db.session.commit()
         except Exception as e:
             logging.exception("consume document failed")
             dataset_document.indexing_status = "error"
             dataset_document.error = str(e)
-            dataset_document.stopped_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+            dataset_document.stopped_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
             db.session.commit()
 
     def indexing_estimate(
@@ -372,7 +372,7 @@ class IndexingRunner:
             after_indexing_status="splitting",
             extra_update_params={
                 DatasetDocument.word_count: sum(len(text_doc.page_content) for text_doc in text_docs),
-                DatasetDocument.parsing_completed_at: datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None),
+                DatasetDocument.parsing_completed_at: datetime.datetime.now(datetime.UTC).replace(tzinfo=None),
             },
         )
 
@@ -464,7 +464,7 @@ class IndexingRunner:
         doc_store.add_documents(documents)
 
         # update document status to indexing
-        cur_time = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+        cur_time = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
         self._update_document_index_status(
             document_id=dataset_document.id,
             after_indexing_status="indexing",
@@ -479,7 +479,7 @@ class IndexingRunner:
             dataset_document_id=dataset_document.id,
             update_params={
                 DocumentSegment.status: "indexing",
-                DocumentSegment.indexing_at: datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None),
+                DocumentSegment.indexing_at: datetime.datetime.now(datetime.UTC).replace(tzinfo=None),
             },
         )
 
@@ -680,7 +680,7 @@ class IndexingRunner:
             after_indexing_status="completed",
             extra_update_params={
                 DatasetDocument.tokens: tokens,
-                DatasetDocument.completed_at: datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None),
+                DatasetDocument.completed_at: datetime.datetime.now(datetime.UTC).replace(tzinfo=None),
                 DatasetDocument.indexing_latency: indexing_end_at - indexing_start_at,
                 DatasetDocument.error: None,
             },
@@ -705,7 +705,7 @@ class IndexingRunner:
                     {
                         DocumentSegment.status: "completed",
                         DocumentSegment.enabled: True,
-                        DocumentSegment.completed_at: datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None),
+                        DocumentSegment.completed_at: datetime.datetime.now(datetime.UTC).replace(tzinfo=None),
                     }
                 )
 
@@ -738,7 +738,7 @@ class IndexingRunner:
                 {
                     DocumentSegment.status: "completed",
                     DocumentSegment.enabled: True,
-                    DocumentSegment.completed_at: datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None),
+                    DocumentSegment.completed_at: datetime.datetime.now(datetime.UTC).replace(tzinfo=None),
                 }
             )
 
@@ -849,7 +849,7 @@ class IndexingRunner:
         doc_store.add_documents(documents)
 
         # update document status to indexing
-        cur_time = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+        cur_time = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
         self._update_document_index_status(
             document_id=dataset_document.id,
             after_indexing_status="indexing",
@@ -864,7 +864,7 @@ class IndexingRunner:
             dataset_document_id=dataset_document.id,
             update_params={
                 DocumentSegment.status: "indexing",
-                DocumentSegment.indexing_at: datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None),
+                DocumentSegment.indexing_at: datetime.datetime.now(datetime.UTC).replace(tzinfo=None),
             },
         )
         pass

api/core/llm_generator/output_parser/suggested_questions_after_answer.py

@@ -15,6 +15,5 @@ class SuggestedQuestionsAfterAnswerOutputParser:
             json_obj = json.loads(action_match.group(0).strip())
         else:
             json_obj = []
-            print(f"Could not parse LLM output: {text}")
 
         return json_obj

api/core/model_runtime/entities/message_entities.py

@@ -1,6 +1,6 @@
 from abc import ABC
 from collections.abc import Sequence
-from enum import Enum
+from enum import Enum, StrEnum
 from typing import Literal, Optional
 
 from pydantic import BaseModel, Field, field_validator
@@ -49,7 +49,7 @@ class PromptMessageFunction(BaseModel):
     function: PromptMessageTool
 
 
-class PromptMessageContentType(str, Enum):
+class PromptMessageContentType(StrEnum):
     """
     Enum class for prompt message content type.
     """
@@ -95,7 +95,7 @@ class ImagePromptMessageContent(PromptMessageContent):
     Model class for image prompt message content.
     """
 
-    class DETAIL(str, Enum):
+    class DETAIL(StrEnum):
         LOW = "low"
         HIGH = "high"
 

api/core/model_runtime/entities/model_entities.py

@@ -1,5 +1,5 @@
 from decimal import Decimal
-from enum import Enum
+from enum import Enum, StrEnum
 from typing import Any, Optional
 
 from pydantic import BaseModel, ConfigDict
@@ -92,7 +92,7 @@ class ModelFeature(Enum):
     AUDIO = "audio"
 
 
-class DefaultParameterName(str, Enum):
+class DefaultParameterName(StrEnum):
     """
     Enum class for parameter template variable.
     """

api/core/model_runtime/model_providers/anthropic/llm/llm.py

@@ -453,7 +453,7 @@ class AnthropicLargeLanguageModel(LargeLanguageModel):
 
         return credentials_kwargs
 
-    def _convert_prompt_messages(self, prompt_messages: list[PromptMessage]) -> tuple[str, list[dict]]:
+    def _convert_prompt_messages(self, prompt_messages: Sequence[PromptMessage]) -> tuple[str, list[dict]]:
         """
         Convert prompt messages to dict list and system
         """
@@ -461,7 +461,15 @@ class AnthropicLargeLanguageModel(LargeLanguageModel):
         first_loop = True
         for message in prompt_messages:
             if isinstance(message, SystemPromptMessage):
-                message.content = message.content.strip()
+                if isinstance(message.content, str):
+                    message.content = message.content.strip()
+                elif isinstance(message.content, list):
+                    # System prompt only support text
+                    message.content = "".join(
+                        c.data.strip() for c in message.content if isinstance(c, TextPromptMessageContent)
+                    )
+                else:
+                    raise ValueError(f"Unknown system prompt message content type {type(message.content)}")
                 if first_loop:
                     system = message.content
                     first_loop = False
@@ -475,6 +483,10 @@ class AnthropicLargeLanguageModel(LargeLanguageModel):
                 if isinstance(message, UserPromptMessage):
                     message = cast(UserPromptMessage, message)
                     if isinstance(message.content, str):
+                        # handle empty user prompt see #10013 #10520
+                        # responses, ignore user prompts containing only whitespace, the Claude API can't handle it.
+                        if not message.content.strip():
+                            continue
                         message_dict = {"role": "user", "content": message.content}
                         prompt_message_dicts.append(message_dict)
                     else:

api/core/model_runtime/model_providers/azure_openai/_constant.py

@@ -779,7 +779,7 @@ LLM_BASE_MODELS = [
                     name="frequency_penalty",
                     **PARAMETER_RULE_TEMPLATE[DefaultParameterName.FREQUENCY_PENALTY],
                 ),
-                _get_max_tokens(default=512, min_val=1, max_val=4096),
+                _get_max_tokens(default=512, min_val=1, max_val=16384),
                 ParameterRule(
                     name="seed",
                     label=I18nObject(zh_Hans="种子", en_US="Seed"),

api/core/model_runtime/model_providers/azure_openai/llm/llm.py

@@ -598,6 +598,9 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
             # message = cast(AssistantPromptMessage, message)
             message_dict = {"role": "assistant", "content": message.content}
             if message.tool_calls:
+                # fix azure when enable json schema cant process content = "" in assistant fix with None
+                if not message.content:
+                    message_dict["content"] = None
                 message_dict["tool_calls"] = [helper.dump_model(tool_call) for tool_call in message.tool_calls]
         elif isinstance(message, SystemPromptMessage):
             message = cast(SystemPromptMessage, message)

api/core/model_runtime/model_providers/azure_openai/tts/tts.py

@@ -14,7 +14,7 @@ from core.model_runtime.model_providers.azure_openai._constant import TTS_BASE_M
 
 class AzureOpenAIText2SpeechModel(_CommonAzureOpenAI, TTSModel):
     """
-    Model class for OpenAI Speech to text model.
+    Model class for OpenAI text2speech model.
     """
 
     def _invoke(

api/core/model_runtime/model_providers/bedrock/llm/us.anthropic.claude-3-5-haiku-v1.yaml

@@ -15,9 +15,9 @@ parameter_rules:
     use_template: max_tokens
     required: true
     type: int
-    default: 4096
+    default: 8192
     min: 1
-    max: 4096
+    max: 8192
     help:
       zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
       en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.

api/core/model_runtime/model_providers/bedrock/llm/us.anthropic.claude-3-sonnet-v2.yaml

@@ -16,9 +16,9 @@ parameter_rules:
     use_template: max_tokens
     required: true
     type: int
-    default: 4096
+    default: 8192
     min: 1
-    max: 4096
+    max: 8192
     help:
       zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
       en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.

api/core/model_runtime/model_providers/deepseek/llm/deepseek-chat.yaml

@@ -5,6 +5,7 @@ label:
 model_type: llm
 features:
   - agent-thought
+  - tool-call
   - multi-tool-call
   - stream-tool-call
 model_properties:
@@ -72,7 +73,7 @@ parameter_rules:
       - text
       - json_object
 pricing:
-  input: '1'
-  output: '2'
-  unit: '0.000001'
+  input: "1"
+  output: "2"
+  unit: "0.000001"
   currency: RMB

api/core/model_runtime/model_providers/deepseek/llm/deepseek-coder.yaml

@@ -5,6 +5,7 @@ label:
 model_type: llm
 features:
   - agent-thought
+  - tool-call
   - multi-tool-call
   - stream-tool-call
 model_properties:

api/core/model_runtime/model_providers/deepseek/llm/llm.py

@@ -1,18 +1,17 @@
 from collections.abc import Generator
 from typing import Optional, Union
-from urllib.parse import urlparse
 
-import tiktoken
+from yarl import URL
 
-from core.model_runtime.entities.llm_entities import LLMResult
+from core.model_runtime.entities.llm_entities import LLMMode, LLMResult
 from core.model_runtime.entities.message_entities import (
     PromptMessage,
     PromptMessageTool,
 )
-from core.model_runtime.model_providers.openai.llm.llm import OpenAILargeLanguageModel
+from core.model_runtime.model_providers.openai_api_compatible.llm.llm import OAIAPICompatLargeLanguageModel
 
 
-class DeepSeekLargeLanguageModel(OpenAILargeLanguageModel):
+class DeepseekLargeLanguageModel(OAIAPICompatLargeLanguageModel):
     def _invoke(
         self,
         model: str,
@@ -25,92 +24,15 @@ class DeepSeekLargeLanguageModel(OpenAILargeLanguageModel):
         user: Optional[str] = None,
     ) -> Union[LLMResult, Generator]:
         self._add_custom_parameters(credentials)
-
-        return super()._invoke(model, credentials, prompt_messages, model_parameters, tools, stop, stream, user)
+        return super()._invoke(model, credentials, prompt_messages, model_parameters, tools, stop, stream)
 
     def validate_credentials(self, model: str, credentials: dict) -> None:
         self._add_custom_parameters(credentials)
         super().validate_credentials(model, credentials)
 
-    # refactored from openai model runtime, use cl100k_base for calculate token number
-    def _num_tokens_from_string(self, model: str, text: str, tools: Optional[list[PromptMessageTool]] = None) -> int:
-        """
-        Calculate num tokens for text completion model with tiktoken package.
-
-        :param model: model name
-        :param text: prompt text
-        :param tools: tools for tool calling
-        :return: number of tokens
-        """
-        encoding = tiktoken.get_encoding("cl100k_base")
-        num_tokens = len(encoding.encode(text))
-
-        if tools:
-            num_tokens += self._num_tokens_for_tools(encoding, tools)
-
-        return num_tokens
-
-    # refactored from openai model runtime, use cl100k_base for calculate token number
-    def _num_tokens_from_messages(
-        self, model: str, messages: list[PromptMessage], tools: Optional[list[PromptMessageTool]] = None
-    ) -> int:
-        """Calculate num tokens for gpt-3.5-turbo and gpt-4 with tiktoken package.
-
-        Official documentation: https://github.com/openai/openai-cookbook/blob/
-        main/examples/How_to_format_inputs_to_ChatGPT_models.ipynb"""
-        encoding = tiktoken.get_encoding("cl100k_base")
-        tokens_per_message = 3
-        tokens_per_name = 1
-
-        num_tokens = 0
-        messages_dict = [self._convert_prompt_message_to_dict(m) for m in messages]
-        for message in messages_dict:
-            num_tokens += tokens_per_message
-            for key, value in message.items():
-                # Cast str(value) in case the message value is not a string
-                # This occurs with function messages
-                # TODO: The current token calculation method for the image type is not implemented,
-                #  which need to download the image and then get the resolution for calculation,
-                #  and will increase the request delay
-                if isinstance(value, list):
-                    text = ""
-                    for item in value:
-                        if isinstance(item, dict) and item["type"] == "text":
-                            text += item["text"]
-
-                    value = text
-
-                if key == "tool_calls":
-                    for tool_call in value:
-                        for t_key, t_value in tool_call.items():
-                            num_tokens += len(encoding.encode(t_key))
-                            if t_key == "function":
-                                for f_key, f_value in t_value.items():
-                                    num_tokens += len(encoding.encode(f_key))
-                                    num_tokens += len(encoding.encode(f_value))
-                            else:
-                                num_tokens += len(encoding.encode(t_key))
-                                num_tokens += len(encoding.encode(t_value))
-                else:
-                    num_tokens += len(encoding.encode(str(value)))
-
-                if key == "name":
-                    num_tokens += tokens_per_name
-
-        # every reply is primed with <im_start>assistant
-        num_tokens += 3
-
-        if tools:
-            num_tokens += self._num_tokens_for_tools(encoding, tools)
-
-        return num_tokens
-
     @staticmethod
-    def _add_custom_parameters(credentials: dict) -> None:
-        credentials["mode"] = "chat"
-        credentials["openai_api_key"] = credentials["api_key"]
-        if "endpoint_url" not in credentials or credentials["endpoint_url"] == "":
-            credentials["openai_api_base"] = "https://api.deepseek.com"
-        else:
-            parsed_url = urlparse(credentials["endpoint_url"])
-            credentials["openai_api_base"] = f"{parsed_url.scheme}://{parsed_url.netloc}"
+    def _add_custom_parameters(credentials) -> None:
+        credentials["endpoint_url"] = str(URL(credentials.get("endpoint_url", "https://api.deepseek.com")))
+        credentials["mode"] = LLMMode.CHAT.value
+        credentials["function_calling_type"] = "tool_call"
+        credentials["stream_function_calling"] = "support"

api/core/model_runtime/model_providers/fishaudio/fishaudio.py

@@ -18,7 +18,8 @@ class FishAudioProvider(ModelProvider):
         """
         try:
             model_instance = self.get_model_instance(ModelType.TTS)
-            model_instance.validate_credentials(credentials=credentials)
+            # FIXME fish tts do not have model for now, so set it to empty string instead
+            model_instance.validate_credentials(model="", credentials=credentials)
         except CredentialsValidateFailedError as ex:
             raise ex
         except Exception as ex:

api/core/model_runtime/model_providers/fishaudio/tts/tts.py

@@ -66,7 +66,7 @@ class FishAudioText2SpeechModel(TTSModel):
             voice=voice,
         )
 
-    def validate_credentials(self, credentials: dict, user: Optional[str] = None) -> None:
+    def validate_credentials(self, model: str, credentials: dict, user: Optional[str] = None) -> None:
         """
         Validate credentials for text2speech model
 
@@ -76,7 +76,7 @@ class FishAudioText2SpeechModel(TTSModel):
 
         try:
             self.get_tts_model_voices(
-                None,
+                "",
                 credentials={
                     "api_key": credentials["api_key"],
                     "api_base": credentials["api_base"],

api/core/model_runtime/model_providers/gitee_ai/llm/llm.py

@@ -32,12 +32,12 @@ class GiteeAILargeLanguageModel(OAIAPICompatLargeLanguageModel):
         return super()._invoke(model, credentials, prompt_messages, model_parameters, tools, stop, stream, user)
 
     def validate_credentials(self, model: str, credentials: dict) -> None:
-        self._add_custom_parameters(credentials, model, None)
+        self._add_custom_parameters(credentials, None)
         super().validate_credentials(model, credentials)
 
-    def _add_custom_parameters(self, credentials: dict, model: str, model_parameters: dict) -> None:
+    def _add_custom_parameters(self, credentials: dict, model: Optional[str]) -> None:
         if model is None:
-            model = "bge-large-zh-v1.5"
+            model = "Qwen2-72B-Instruct"
 
         model_identity = GiteeAILargeLanguageModel.MODEL_TO_IDENTITY.get(model, model)
         credentials["endpoint_url"] = f"https://ai.gitee.com/api/serverless/{model_identity}/"
@@ -47,5 +47,7 @@ class GiteeAILargeLanguageModel(OAIAPICompatLargeLanguageModel):
             credentials["mode"] = LLMMode.CHAT.value
 
         schema = self.get_model_schema(model, credentials)
+        assert schema is not None, f"Model schema not found for model {model}"
+        assert schema.features is not None, f"Model features not found for model {model}"
         if ModelFeature.TOOL_CALL in schema.features or ModelFeature.MULTI_TOOL_CALL in schema.features:
             credentials["function_calling_type"] = "tool_call"

api/core/model_runtime/model_providers/gitee_ai/rerank/rerank.py

@@ -122,7 +122,7 @@ class GiteeAIRerankModel(RerankModel):
             label=I18nObject(en_US=model),
             model_type=ModelType.RERANK,
             fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
-            model_properties={ModelPropertyKey.CONTEXT_SIZE: int(credentials.get("context_size"))},
+            model_properties={ModelPropertyKey.CONTEXT_SIZE: int(credentials.get("context_size", 512))},
         )
 
         return entity

api/core/model_runtime/model_providers/gitee_ai/tts/tts.py

@@ -10,7 +10,7 @@ from core.model_runtime.model_providers.gitee_ai._common import _CommonGiteeAI
 
 class GiteeAIText2SpeechModel(_CommonGiteeAI, TTSModel):
     """
-    Model class for OpenAI Speech to text model.
+    Model class for OpenAI text2speech model.
     """
 
     def _invoke(

api/core/model_runtime/model_providers/google/llm/llm.py

@@ -254,8 +254,12 @@ class GoogleLargeLanguageModel(LargeLanguageModel):
         assistant_prompt_message = AssistantPromptMessage(content=response.text)
 
         # calculate num tokens
-        prompt_tokens = self.get_num_tokens(model, credentials, prompt_messages)
-        completion_tokens = self.get_num_tokens(model, credentials, [assistant_prompt_message])
+        if response.usage_metadata:
+            prompt_tokens = response.usage_metadata.prompt_token_count
+            completion_tokens = response.usage_metadata.candidates_token_count
+        else:
+            prompt_tokens = self.get_num_tokens(model, credentials, prompt_messages)
+            completion_tokens = self.get_num_tokens(model, credentials, [assistant_prompt_message])
 
         # transform usage
         usage = self._calc_response_usage(model, credentials, prompt_tokens, completion_tokens)

api/core/model_runtime/model_providers/gpustack/rerank/rerank.py

@@ -140,7 +140,7 @@ class GPUStackRerankModel(RerankModel):
             label=I18nObject(en_US=model),
             model_type=ModelType.RERANK,
             fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
-            model_properties={ModelPropertyKey.CONTEXT_SIZE: int(credentials.get("context_size"))},
+            model_properties={ModelPropertyKey.CONTEXT_SIZE: int(credentials.get("context_size", 512))},
         )
 
         return entity

api/core/model_runtime/model_providers/huggingface_tei/huggingface_tei.yaml

@@ -34,3 +34,11 @@ model_credential_schema:
       placeholder:
         zh_Hans: 在此输入Text Embedding Inference的服务器地址，如 http://192.168.1.100:8080
         en_US: Enter the url of your Text Embedding Inference, e.g. http://192.168.1.100:8080
+    - variable: api_key
+      label:
+        en_US: API Key
+      type: secret-input
+      required: false
+      placeholder:
+        zh_Hans: 在此输入您的 API Key
+        en_US: Enter your API Key

api/core/model_runtime/model_providers/huggingface_tei/rerank/rerank.py

@@ -51,8 +51,13 @@ class HuggingfaceTeiRerankModel(RerankModel):
 
         server_url = server_url.removesuffix("/")
 
+        headers = {"Content-Type": "application/json"}
+        api_key = credentials.get("api_key")
+        if api_key:
+            headers["Authorization"] = f"Bearer {api_key}"
+
         try:
-            results = TeiHelper.invoke_rerank(server_url, query, docs)
+            results = TeiHelper.invoke_rerank(server_url, query, docs, headers)
 
             rerank_documents = []
             for result in results:
@@ -80,7 +85,11 @@ class HuggingfaceTeiRerankModel(RerankModel):
         """
         try:
             server_url = credentials["server_url"]
-            extra_args = TeiHelper.get_tei_extra_parameter(server_url, model)
+            headers = {"Content-Type": "application/json"}
+            api_key = credentials.get("api_key")
+            if api_key:
+                headers["Authorization"] = f"Bearer {api_key}"
+            extra_args = TeiHelper.get_tei_extra_parameter(server_url, model, headers)
             if extra_args.model_type != "reranker":
                 raise CredentialsValidateFailedError("Current model is not a rerank model")
 

api/core/model_runtime/model_providers/huggingface_tei/tei_helper.py

@@ -26,13 +26,15 @@ cache_lock = Lock()
 
 class TeiHelper:
     @staticmethod
-    def get_tei_extra_parameter(server_url: str, model_name: str) -> TeiModelExtraParameter:
+    def get_tei_extra_parameter(
+        server_url: str, model_name: str, headers: Optional[dict] = None
+    ) -> TeiModelExtraParameter:
         TeiHelper._clean_cache()
         with cache_lock:
             if model_name not in cache:
                 cache[model_name] = {
                     "expires": time() + 300,
-                    "value": TeiHelper._get_tei_extra_parameter(server_url),
+                    "value": TeiHelper._get_tei_extra_parameter(server_url, headers),
                 }
             return cache[model_name]["value"]
 
@@ -47,7 +49,7 @@ class TeiHelper:
             pass
 
     @staticmethod
-    def _get_tei_extra_parameter(server_url: str) -> TeiModelExtraParameter:
+    def _get_tei_extra_parameter(server_url: str, headers: Optional[dict] = None) -> TeiModelExtraParameter:
         """
         get tei model extra parameter like model_type, max_input_length, max_batch_requests
         """
@@ -61,7 +63,7 @@ class TeiHelper:
         session.mount("https://", HTTPAdapter(max_retries=3))
 
         try:
-            response = session.get(url, timeout=10)
+            response = session.get(url, headers=headers, timeout=10)
         except (MissingSchema, ConnectionError, Timeout) as e:
             raise RuntimeError(f"get tei model extra parameter failed, url: {url}, error: {e}")
         if response.status_code != 200:
@@ -86,7 +88,7 @@ class TeiHelper:
         )
 
     @staticmethod
-    def invoke_tokenize(server_url: str, texts: list[str]) -> list[list[dict]]:
+    def invoke_tokenize(server_url: str, texts: list[str], headers: Optional[dict] = None) -> list[list[dict]]:
         """
         Invoke tokenize endpoint
 
@@ -114,15 +116,15 @@ class TeiHelper:
         :param server_url: server url
         :param texts: texts to tokenize
         """
-        resp = httpx.post(
-            f"{server_url}/tokenize",
-            json={"inputs": texts},
-        )
+        url = f"{server_url}/tokenize"
+        json_data = {"inputs": texts}
+        resp = httpx.post(url, json=json_data, headers=headers)
+
         resp.raise_for_status()
         return resp.json()
 
     @staticmethod
-    def invoke_embeddings(server_url: str, texts: list[str]) -> dict:
+    def invoke_embeddings(server_url: str, texts: list[str], headers: Optional[dict] = None) -> dict:
         """
         Invoke embeddings endpoint
 
@@ -147,15 +149,14 @@ class TeiHelper:
         :param texts: texts to embed
         """
         # Use OpenAI compatible API here, which has usage tracking
-        resp = httpx.post(
-            f"{server_url}/v1/embeddings",
-            json={"input": texts},
-        )
+        url = f"{server_url}/v1/embeddings"
+        json_data = {"input": texts}
+        resp = httpx.post(url, json=json_data, headers=headers)
         resp.raise_for_status()
         return resp.json()
 
     @staticmethod
-    def invoke_rerank(server_url: str, query: str, docs: list[str]) -> list[dict]:
+    def invoke_rerank(server_url: str, query: str, docs: list[str], headers: Optional[dict] = None) -> list[dict]:
         """
         Invoke rerank endpoint
 
@@ -173,10 +174,7 @@ class TeiHelper:
         :param candidates: candidates to rerank
         """
         params = {"query": query, "texts": docs, "return_text": True}
-
-        response = httpx.post(
-            server_url + "/rerank",
-            json=params,
-        )
+        url = f"{server_url}/rerank"
+        response = httpx.post(url, json=params, headers=headers)
         response.raise_for_status()
         return response.json()

api/core/model_runtime/model_providers/huggingface_tei/text_embedding/text_embedding.py

@@ -51,6 +51,10 @@ class HuggingfaceTeiTextEmbeddingModel(TextEmbeddingModel):
 
         server_url = server_url.removesuffix("/")
 
+        headers = {"Content-Type": "application/json"}
+        api_key = credentials["api_key"]
+        if api_key:
+            headers["Authorization"] = f"Bearer {api_key}"
         # get model properties
         context_size = self._get_context_size(model, credentials)
         max_chunks = self._get_max_chunks(model, credentials)
@@ -60,7 +64,7 @@ class HuggingfaceTeiTextEmbeddingModel(TextEmbeddingModel):
         used_tokens = 0
 
         # get tokenized results from TEI
-        batched_tokenize_result = TeiHelper.invoke_tokenize(server_url, texts)
+        batched_tokenize_result = TeiHelper.invoke_tokenize(server_url, texts, headers)
 
         for i, (text, tokenize_result) in enumerate(zip(texts, batched_tokenize_result)):
             # Check if the number of tokens is larger than the context size
@@ -97,7 +101,7 @@ class HuggingfaceTeiTextEmbeddingModel(TextEmbeddingModel):
             used_tokens = 0
             for i in _iter:
                 iter_texts = inputs[i : i + max_chunks]
-                results = TeiHelper.invoke_embeddings(server_url, iter_texts)
+                results = TeiHelper.invoke_embeddings(server_url, iter_texts, headers)
                 embeddings = results["data"]
                 embeddings = [embedding["embedding"] for embedding in embeddings]
                 batched_embeddings.extend(embeddings)
@@ -127,7 +131,11 @@ class HuggingfaceTeiTextEmbeddingModel(TextEmbeddingModel):
 
         server_url = server_url.removesuffix("/")
 
-        batch_tokens = TeiHelper.invoke_tokenize(server_url, texts)
+        headers = {
+            "Authorization": f"Bearer {credentials.get('api_key')}",
+        }
+
+        batch_tokens = TeiHelper.invoke_tokenize(server_url, texts, headers)
         num_tokens = sum(len(tokens) for tokens in batch_tokens)
         return num_tokens
 
@@ -141,7 +149,14 @@ class HuggingfaceTeiTextEmbeddingModel(TextEmbeddingModel):
         """
         try:
             server_url = credentials["server_url"]
-            extra_args = TeiHelper.get_tei_extra_parameter(server_url, model)
+            headers = {"Content-Type": "application/json"}
+
+            api_key = credentials.get("api_key")
+
+            if api_key:
+                headers["Authorization"] = f"Bearer {api_key}"
+
+            extra_args = TeiHelper.get_tei_extra_parameter(server_url, model, headers)
             print(extra_args)
             if extra_args.model_type != "embedding":
                 raise CredentialsValidateFailedError("Current model is not a embedding model")

api/core/model_runtime/model_providers/jina/rerank/rerank.py

@@ -128,7 +128,7 @@ class JinaRerankModel(RerankModel):
             label=I18nObject(en_US=model),
             model_type=ModelType.RERANK,
             fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
-            model_properties={ModelPropertyKey.CONTEXT_SIZE: int(credentials.get("context_size"))},
+            model_properties={ModelPropertyKey.CONTEXT_SIZE: int(credentials.get("context_size", 8000))},
         )
 
         return entity

api/core/model_runtime/model_providers/jina/text_embedding/text_embedding.py

@@ -193,7 +193,7 @@ class JinaTextEmbeddingModel(TextEmbeddingModel):
             label=I18nObject(en_US=model),
             model_type=ModelType.TEXT_EMBEDDING,
             fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
-            model_properties={ModelPropertyKey.CONTEXT_SIZE: int(credentials.get("context_size"))},
+            model_properties={ModelPropertyKey.CONTEXT_SIZE: int(credentials.get("context_size", 8000))},
         )
 
         return entity

api/core/model_runtime/model_providers/ollama/text_embedding/text_embedding.py

@@ -139,7 +139,7 @@ class OllamaEmbeddingModel(TextEmbeddingModel):
             model_type=ModelType.TEXT_EMBEDDING,
             fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
             model_properties={
-                ModelPropertyKey.CONTEXT_SIZE: int(credentials.get("context_size")),
+                ModelPropertyKey.CONTEXT_SIZE: int(credentials.get("context_size", 512)),
                 ModelPropertyKey.MAX_CHUNKS: 1,
             },
             parameter_rules=[],