release/1.0.0 (#14478)

Signed-off-by: -LAN- <laipz8200@outlook.com>

.github/workflows/api-tests.yml

@@ -4,7 +4,6 @@ on:
   pull_request:
     branches:
       - main
-      - plugins/beta
     paths:
       - api/**
       - docker/**
@@ -27,6 +26,9 @@ jobs:
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false
 
       - name: Setup Poetry and Python ${{ matrix.python-version }}
         uses: ./.github/actions/setup-poetry

.github/workflows/build-push.yml

@@ -5,7 +5,6 @@ on:
     branches:
       - "main"
       - "deploy/dev"
-      - "plugins/beta"
   release:
     types: [published]
 
@@ -80,10 +79,12 @@ jobs:
           cache-to: type=gha,mode=max,scope=${{ matrix.service_name }}
 
       - name: Export digest
+        env:
+          DIGEST: ${{ steps.build.outputs.digest }}
         run: |
           mkdir -p /tmp/digests
-          digest="${{ steps.build.outputs.digest }}"
-          touch "/tmp/digests/${digest#sha256:}"
+          sanitized_digest=${DIGEST#sha256:}
+          touch "/tmp/digests/${sanitized_digest}"
 
       - name: Upload digest
         uses: actions/upload-artifact@v4
@@ -133,10 +134,15 @@ jobs:
 
       - name: Create manifest list and push
         working-directory: /tmp/digests
+        env:
+          IMAGE_NAME: ${{ env[matrix.image_name_env] }}
         run: |
           docker buildx imagetools create $(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "$DOCKER_METADATA_OUTPUT_JSON") \
-            $(printf '${{ env[matrix.image_name_env] }}@sha256:%s ' *)
+            $(printf "$IMAGE_NAME@sha256:%s " *)
 
       - name: Inspect image
+        env:
+          IMAGE_NAME: ${{ env[matrix.image_name_env] }}
+          IMAGE_VERSION: ${{ steps.meta.outputs.version }}
         run: |
-          docker buildx imagetools inspect ${{ env[matrix.image_name_env] }}:${{ steps.meta.outputs.version }}
+          docker buildx imagetools inspect "$IMAGE_NAME:$IMAGE_VERSION"

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

@@ -20,6 +20,9 @@ jobs:
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false
 
       - name: Setup Poetry and Python
         uses: ./.github/actions/setup-poetry

.github/workflows/expose_service_ports.sh

@@ -9,6 +9,6 @@ yq eval '.services["pgvecto-rs"].ports += ["5431:5432"]' -i docker/docker-compos
 yq eval '.services["elasticsearch"].ports += ["9200:9200"]' -i docker/docker-compose.yaml
 yq eval '.services.couchbase-server.ports += ["8091-8096:8091-8096"]' -i docker/docker-compose.yaml
 yq eval '.services.couchbase-server.ports += ["11210:11210"]' -i docker/docker-compose.yaml
-yq eval '.services.tidb.ports += ["4000:4000"]' -i docker/docker-compose.yaml
+yq eval '.services.tidb.ports += ["4000:4000"]' -i docker/tidb/docker-compose.yaml
 
 echo "Ports exposed for sandbox, weaviate, tidb, qdrant, chroma, milvus, pgvector, pgvecto-rs, elasticsearch, couchbase"

.github/workflows/style.yml

@@ -4,7 +4,6 @@ on:
   pull_request:
     branches:
       - main
-      - plugins/beta
 
 concurrency:
   group: style-${{ github.head_ref || github.run_id }}
@@ -18,6 +17,9 @@ jobs:
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false
 
       - name: Check changed files
         id: changed-files
@@ -60,6 +62,9 @@ jobs:
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false
 
       - name: Check changed files
         id: changed-files
@@ -87,7 +92,7 @@ jobs:
 
       - name: Web style check
         if: steps.changed-files.outputs.any_changed == 'true'
-        run: yarn run lint
+        run: pnpm run lint
 
   docker-compose-template:
     name: Docker Compose Template
@@ -96,6 +101,9 @@ jobs:
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false
 
       - name: Check changed files
         id: changed-files
@@ -124,6 +132,9 @@ jobs:
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false
 
       - name: Check changed files
         id: changed-files
@@ -141,7 +152,7 @@ jobs:
         if: steps.changed-files.outputs.any_changed == 'true'
         env:
           BASH_SEVERITY: warning
-          DEFAULT_BRANCH: plugins/beta
+          DEFAULT_BRANCH: main
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           IGNORE_GENERATED_FILES: true
           IGNORE_GITIGNORED_FILES: true

.github/workflows/tool-test-sdks.yaml

@@ -26,6 +26,9 @@ jobs:
 
     steps:
       - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false
 
       - name: Use Node.js ${{ matrix.node-version }}
         uses: actions/setup-node@v4
@@ -35,7 +38,7 @@ jobs:
           cache-dependency-path: 'pnpm-lock.yaml'
 
       - name: Install Dependencies
-        run: pnpm install
+        run: pnpm install --frozen-lockfile
 
       - name: Test
         run: pnpm test

.github/workflows/translate-i18n-base-on-english.yml

@@ -16,6 +16,7 @@ jobs:
       - uses: actions/checkout@v4
         with:
           fetch-depth: 2 # last 2 commits
+          persist-credentials: false
 
       - name: Check for file changes in i18n/en-US
         id: check_files

.github/workflows/vdb-tests.yml

@@ -28,6 +28,9 @@ jobs:
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false
 
       - name: Setup Poetry and Python ${{ matrix.python-version }}
         uses: ./.github/actions/setup-poetry
@@ -51,7 +54,15 @@ jobs:
       - name: Expose Service Ports
         run: sh .github/workflows/expose_service_ports.sh
 
-      - name: Set up Vector Stores (TiDB, Weaviate, Qdrant, PGVector, Milvus, PgVecto-RS, Chroma, MyScale, ElasticSearch, Couchbase)
+      - name: Set up Vector Store (TiDB)
+        uses: hoverkraft-tech/compose-action@v2.0.2
+        with:
+          compose-file: docker/tidb/docker-compose.yaml
+          services: |
+            tidb
+            tiflash
+
+      - name: Set up Vector Stores (Weaviate, Qdrant, PGVector, Milvus, PgVecto-RS, Chroma, MyScale, ElasticSearch, Couchbase)
         uses: hoverkraft-tech/compose-action@v2.0.2
         with:
           compose-file: |
@@ -67,7 +78,9 @@ jobs:
             pgvector
             chroma
             elasticsearch
-            tidb
+
+      - name: Check TiDB Ready
+        run: poetry run -P api python api/tests/integration_tests/vdb/tidb_vector/check_tiflash_ready.py
 
       - name: Test Vector Stores
         run: poetry run -P api bash dev/pytest/pytest_vdb.sh

.github/workflows/web-tests.yml

@@ -22,25 +22,34 @@ jobs:
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false
 
       - name: Check changed files
         id: changed-files
         uses: tj-actions/changed-files@v45
         with:
           files: web/**
+      # to run pnpm, should install package canvas, but it always install failed on amd64 under ubuntu-latest
+      # - name: Install pnpm
+      #   uses: pnpm/action-setup@v4
+      #   with:
+      #     version: 10
+      #     run_install: false
 
-      - name: Setup Node.js
-        uses: actions/setup-node@v4
-        if: steps.changed-files.outputs.any_changed == 'true'
-        with:
-          node-version: 20
-          cache: pnpm
-          cache-dependency-path: ./web/package.json
+      # - name: Setup Node.js
+      #   uses: actions/setup-node@v4
+      #   if: steps.changed-files.outputs.any_changed == 'true'
+      #   with:
+      #     node-version: 20
+      #     cache: pnpm
+      #     cache-dependency-path: ./web/package.json
 
-      - name: Install dependencies
-        if: steps.changed-files.outputs.any_changed == 'true'
-        run: pnpm install --frozen-lockfile
+      # - name: Install dependencies
+      #   if: steps.changed-files.outputs.any_changed == 'true'
+      #   run: pnpm install --frozen-lockfile
 
-      - name: Run tests
-        if: steps.changed-files.outputs.any_changed == 'true'
-        run: pnpm test
+      # - name: Run tests
+      #   if: steps.changed-files.outputs.any_changed == 'true'
+      #   run: pnpm test

.gitignore

@@ -163,6 +163,7 @@ docker/volumes/db/data/*
 docker/volumes/redis/data/*
 docker/volumes/weaviate/*
 docker/volumes/qdrant/*
+docker/tidb/volumes/*
 docker/volumes/etcd/*
 docker/volumes/minio/*
 docker/volumes/milvus/*

CONTRIBUTING.md

@@ -73,7 +73,7 @@ Dify requires the following dependencies to build, make sure they're installed o
 * [Docker](https://www.docker.com/)
 * [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/)
+* [pnpm](https://pnpm.io/)
 * [Python](https://www.python.org/) version 3.11.x or 3.12.x
 
 ### 4. Installations

CONTRIBUTING_CN.md

@@ -70,7 +70,7 @@ Dify 依赖以下工具和库：
 - [Docker](https://www.docker.com/)
 - [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/)
+- [pnpm](https://pnpm.io/)
 - [Python](https://www.python.org/) version 3.11.x or 3.12.x
 
 ### 4. 安装

CONTRIBUTING_JA.md

@@ -73,7 +73,7 @@ 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](https://www.docker.com/)
 - [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/)
+- [pnpm](https://pnpm.io/)
 - [Python](https://www.python.org/) version 3.11.x or 3.12.x
 
 ### 4. インストール

CONTRIBUTING_VI.md

@@ -72,7 +72,7 @@ Dify yêu cầu các phụ thuộc sau để build, hãy đảm bảo chúng đ
 - [Docker](https://www.docker.com/)
 - [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/)
+- [pnpm](https://pnpm.io/)
 - [Python](https://www.python.org/) phiên bản 3.11.x hoặc 3.12.x
 
 ### 4. Cài đặt

LICENSE

@@ -1,12 +1,12 @@
 # Open Source License
 
-Dify is licensed under the Apache License 2.0, with the following additional conditions:
+Dify is licensed under a modified version of the Apache License 2.0, with the following additional conditions:
 
 1. Dify may be utilized commercially, including as a backend service for other applications or as an application development platform for enterprises. Should the conditions below be met, a commercial license must be obtained from the producer:
 
-a. Multi-tenant service: Unless explicitly authorized by Dify in writing, you may not use the Dify source code to operate a multi-tenant environment. 
+a. Multi-tenant service: Unless explicitly authorized by Dify in writing, you may not use the Dify source code to operate a multi-tenant environment.
     - Tenant Definition: Within the context of Dify, one tenant corresponds to one workspace. The workspace provides a separated area for each tenant's data and configurations.
-    
+
 b. LOGO and copyright information: In the process of using Dify's frontend, you may not remove or modify the LOGO or copyright information in the Dify console or applications. This restriction is inapplicable to uses of Dify that do not involve its frontend.
     - Frontend Definition: For the purposes of this license, the "frontend" of Dify includes all components located in the `web/` directory when running Dify from the raw source code, or the "web" image when running Dify with Docker.
 
@@ -21,19 +21,4 @@ Apart from the specific conditions mentioned above, all other rights and restric
 
 The interactive design of this product is protected by appearance patent.
 
-© 2024 LangGenius, Inc.
-
-
-----------
-
-Licensed under the Apache License, Version 2.0 (the "License");
-you may not use this file except in compliance with the License.
-You may obtain a copy of the License at
-
-    http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software
-distributed under the License is distributed on an "AS IS" BASIS,
-WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-See the License for the specific language governing permissions and
-limitations under the License.
+© 2025 LangGenius, Inc.

README.md

@@ -108,6 +108,72 @@ Please refer to our [FAQ](https://docs.dify.ai/getting-started/install-self-host
 **7. Backend-as-a-Service**: 
   All of Dify's offerings come with corresponding APIs, so you could effortlessly integrate Dify into your own business logic.
 
+## Feature Comparison
+<table style="width: 100%;">
+  <tr>
+    <th align="center">Feature</th>
+    <th align="center">Dify.AI</th>
+    <th align="center">LangChain</th>
+    <th align="center">Flowise</th>
+    <th align="center">OpenAI Assistants API</th>
+  </tr>
+  <tr>
+    <td align="center">Programming Approach</td>
+    <td align="center">API + App-oriented</td>
+    <td align="center">Python Code</td>
+    <td align="center">App-oriented</td>
+    <td align="center">API-oriented</td>
+  </tr>
+  <tr>
+    <td align="center">Supported LLMs</td>
+    <td align="center">Rich Variety</td>
+    <td align="center">Rich Variety</td>
+    <td align="center">Rich Variety</td>
+    <td align="center">OpenAI-only</td>
+  </tr>
+  <tr>
+    <td align="center">RAG Engine</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+  </tr>
+  <tr>
+    <td align="center">Agent</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">✅</td>
+  </tr>
+  <tr>
+    <td align="center">Workflow</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">Observability</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">Enterprise Feature (SSO/Access control)</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">Local Deployment</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+  </tr>
+</table>
 
 ## Using Dify
 

README_FR.md

@@ -55,7 +55,7 @@
 Dify est une plateforme de développement d'applications LLM open source. Son interface intuitive combine un flux de travail d'IA, un pipeline RAG, des capacités d'agent, une gestion de modèles, des fonctionnalités d'observabilité, et plus encore, vous permettant de passer rapidement du prototype à la production. Voici une liste des fonctionnalités principales:
 </br> </br>
 
-**1. Flux de travail**: 
+**1. Flux de travail** : 
   Construisez et testez des flux de travail d'IA puissants sur un canevas visuel, en utilisant toutes les fonctionnalités suivantes et plus encore.
 
 
@@ -63,27 +63,25 @@ Dify est une plateforme de développement d'applications LLM open source. Son in
 
 
 
-**2. Prise en charge complète des modèles**: 
+**2. Prise en charge complète des modèles** : 
   Intégration transparente avec des centaines de LLM propriétaires / open source provenant de dizaines de fournisseurs d'inférence et de solutions auto-hébergées, couvrant GPT, Mistral, Llama3, et tous les modèles compatibles avec l'API OpenAI. Une liste complète des fournisseurs de modèles pris en charge se trouve [ici](https://docs.dify.ai/getting-started/readme/model-providers).
 
 ![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3)
 
 
-**3. IDE de prompt**: 
+**3. IDE de prompt** : 
   Interface intuitive pour créer des prompts, comparer les performances des modèles et ajouter des fonctionnalités supplémentaires telles que la synthèse vocale à une application basée sur des chats. 
 
-**4. Pipeline RAG**: 
+**4. Pipeline RAG** : 
   Des capacités RAG étendues qui couvrent tout, de l'ingestion de documents à la récupération, avec un support prêt à l'emploi pour l'extraction de texte à partir de PDF, PPT et autres formats de document courants.
 
-**5. Capac
-
-ités d'agent**: 
+**5. Capacités d'agent** : 
   Vous pouvez définir des agents basés sur l'appel de fonction LLM ou ReAct, et ajouter des outils pré-construits ou personnalisés pour l'agent. Dify fournit plus de 50 outils intégrés pour les agents d'IA, tels que la recherche Google, DALL·E, Stable Diffusion et WolframAlpha.
 
-**6. LLMOps**: 
+**6. LLMOps** : 
   Surveillez et analysez les journaux d'application et les performances au fil du temps. Vous pouvez continuellement améliorer les prompts, les ensembles de données et les modèles en fonction des données de production et des annotations.
 
-**7. Backend-as-a-Service**: 
+**7. Backend-as-a-Service** : 
   Toutes les offres de Dify sont accompagnées d'API correspondantes, vous permettant d'intégrer facilement Dify dans votre propre logique métier.
 
 

README_JA.md

@@ -164,7 +164,7 @@ DifyはオープンソースのLLMアプリケーション開発プラットフ
 
 - **企業/組織向けのDify</br>**
 企業中心の機能を提供しています。[メールを送信](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry)して企業のニーズについて相談してください。 </br>
-  > AWSを使用しているスタートアップ企業や中小企業の場合は、[AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6)のDify Premiumをチェックして、ワンクリックで自分のAWS VPCにデプロイできます。さらに、手頃な価格のAMIオファリングどして、ロゴやブランディングをカスタマイズしてアプリケーションを作成するオプションがあります。
+  > AWSを使用しているスタートアップ企業や中小企業の場合は、[AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t23mebxzwjhu6)のDify Premiumをチェックして、ワンクリックで自分のAWS VPCにデプロイできます。さらに、手頃な価格のAMIオファリングとして、ロゴやブランディングをカスタマイズしてアプリケーションを作成するオプションがあります。
 
 
 ## 最新の情報を入手

README_KL.md

@@ -87,9 +87,7 @@ Dify is an open-source LLM app development platform. Its intuitive interface com
 
 ## Feature Comparison
 <table style="width: 100%;">
-  <tr
-
->
+  <tr>
     <th align="center">Feature</th>
     <th align="center">Dify.AI</th>
     <th align="center">LangChain</th>

README_SI.md

@@ -106,6 +106,73 @@ Prosimo, glejte naša pogosta vprašanja [FAQ](https://docs.dify.ai/getting-star
 **7. Backend-as-a-Service**: 
   AVse ponudbe Difyja so opremljene z ustreznimi API-ji, tako da lahko Dify brez težav integrirate v svojo poslovno logiko.
 
+## Primerjava Funkcij
+
+<table style="width: 100%;">
+  <tr>
+    <th align="center">Funkcija</th>
+    <th align="center">Dify.AI</th>
+    <th align="center">LangChain</th>
+    <th align="center">Flowise</th>
+    <th align="center">OpenAI Assistants API</th>
+  </tr>
+  <tr>
+    <td align="center">Programski pristop</td>
+    <td align="center">API + usmerjeno v aplikacije</td>
+    <td align="center">Python koda</td>
+    <td align="center">Usmerjeno v aplikacije</td>
+    <td align="center">Usmerjeno v API</td>
+  </tr>
+  <tr>
+    <td align="center">Podprti LLM-ji</td>
+    <td align="center">Bogata izbira</td>
+    <td align="center">Bogata izbira</td>
+    <td align="center">Bogata izbira</td>
+    <td align="center">Samo OpenAI</td>
+  </tr>
+  <tr>
+    <td align="center">RAG pogon</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+  </tr>
+  <tr>
+    <td align="center">Agent</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">✅</td>
+  </tr>
+  <tr>
+    <td align="center">Potek dela</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">Spremljanje</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">Funkcija za podjetja (SSO/nadzor dostopa)</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">Lokalna namestitev</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+  </tr>
+</table>
 
 ## Uporaba Dify
 
@@ -187,4 +254,4 @@ Zaradi zaščite vaše zasebnosti se izogibajte objavljanju varnostnih vprašanj
 
 ## Licenca
 
-To skladišče je na voljo pod [odprtokodno licenco Dify](LICENSE) , ki je v bistvu Apache 2.0 z nekaj dodatnimi omejitvami.
+To skladišče je na voljo pod [odprtokodno licenco Dify](LICENSE) , ki je v bistvu Apache 2.0 z nekaj dodatnimi omejitvami.

api/Dockerfile

@@ -55,9 +55,11 @@ RUN \
         # basic environment
         curl nodejs libgmp-dev libmpfr-dev libmpc-dev \
         # For Security
-        # expat libldap-2.5-0 perl libsqlite3-0 zlib1g \
+        expat libldap-2.5-0 perl libsqlite3-0 zlib1g \
         # install a chinese font to support the use of tools like matplotlib
         fonts-noto-cjk \
+        # install a package to improve the accuracy of guessing mime type and file extension
+        media-types \
         # install libmagic to support the use of python-magic guess MIMETYPE
         libmagic1 \
     && apt-get autoremove -y \

api/README.md

@@ -37,7 +37,13 @@
 
 4. Create environment.
 
-   Dify API service uses [Poetry](https://python-poetry.org/docs/) to manage dependencies. You can execute `poetry shell` to activate the environment.
+   Dify API service uses [Poetry](https://python-poetry.org/docs/) to manage dependencies. First, you need to add the poetry shell plugin, if you don't have it already, in order to run in a virtual environment. [Note: Poetry shell is no longer a native command so you need to install the poetry plugin beforehand]
+
+   ```bash
+   poetry self add poetry-plugin-shell
+   ```
+   
+   Then, You can execute `poetry shell` to activate the environment.
 
 5. Install dependencies
 

api/app_factory.py

@@ -2,6 +2,7 @@ import logging
 import time
 
 from configs import dify_config
+from contexts.wrapper import RecyclableContextVar
 from dify_app import DifyApp
 
 
@@ -16,6 +17,12 @@ def create_flask_app_with_configs() -> DifyApp:
     dify_app = DifyApp(__name__)
     dify_app.config.from_mapping(dify_config.model_dump())
 
+    # add before request hook
+    @dify_app.before_request
+    def before_request():
+        # add an unique identifier to each request
+        RecyclableContextVar.increment_thread_recycles()
+
     return dify_app
 
 

api/commands.py

@@ -707,12 +707,13 @@ def extract_unique_plugins(output_file: str, input_file: str):
 @click.option(
     "--output_file", prompt=True, help="The file to store the installed plugins.", default="installed_plugins.jsonl"
 )
-def install_plugins(input_file: str, output_file: str):
+@click.option("--workers", prompt=True, help="The number of workers to install plugins.", default=100)
+def install_plugins(input_file: str, output_file: str, workers: int):
     """
     Install plugins.
     """
     click.echo(click.style("Starting install plugins.", fg="white"))
 
-    PluginMigration.install_plugins(input_file, output_file)
+    PluginMigration.install_plugins(input_file, output_file, workers)
 
     click.echo(click.style("Install plugins completed.", fg="green"))

api/configs/feature/__init__.py

@@ -373,8 +373,8 @@ class HttpConfig(BaseSettings):
     )
 
     RESPECT_XFORWARD_HEADERS_ENABLED: bool = Field(
-        description="Enable or disable the X-Forwarded-For Proxy Fix middleware from Werkzeug"
-        " to respect X-* headers to redirect clients",
+        description="Enable handling of X-Forwarded-For, X-Forwarded-Proto, and X-Forwarded-Port headers"
+        " when the app is behind a single trusted reverse proxy.",
         default=False,
     )
 

api/configs/middleware/__init__.py

@@ -1,3 +1,4 @@
+import os
 from typing import Any, Literal, Optional
 from urllib.parse import quote_plus
 
@@ -166,6 +167,11 @@ class DatabaseConfig(BaseSettings):
         default=False,
     )
 
+    RETRIEVAL_SERVICE_EXECUTORS: NonNegativeInt = Field(
+        description="Number of processes for the retrieval service, default to CPU cores.",
+        default=os.cpu_count(),
+    )
+
     @computed_field
     def SQLALCHEMY_ENGINE_OPTIONS(self) -> dict[str, Any]:
         return {

api/constants/__init__.py

@@ -15,7 +15,7 @@ AUDIO_EXTENSIONS.extend([ext.upper() for ext in AUDIO_EXTENSIONS])
 
 if dify_config.ETL_TYPE == "Unstructured":
     DOCUMENT_EXTENSIONS = ["txt", "markdown", "md", "mdx", "pdf", "html", "htm", "xlsx", "xls"]
-    DOCUMENT_EXTENSIONS.extend(("docx", "csv", "eml", "msg", "pptx", "xml", "epub"))
+    DOCUMENT_EXTENSIONS.extend(("doc", "docx", "csv", "eml", "msg", "pptx", "xml", "epub"))
     if dify_config.UNSTRUCTURED_API_URL:
         DOCUMENT_EXTENSIONS.append("ppt")
     DOCUMENT_EXTENSIONS.extend([ext.upper() for ext in DOCUMENT_EXTENSIONS])

api/contexts/__init__.py

@@ -2,6 +2,8 @@ from contextvars import ContextVar
 from threading import Lock
 from typing import TYPE_CHECKING
 
+from contexts.wrapper import RecyclableContextVar
+
 if TYPE_CHECKING:
     from core.plugin.entities.plugin_daemon import PluginModelProviderEntity
     from core.tools.plugin_tool.provider import PluginToolProviderController
@@ -12,8 +14,17 @@ tenant_id: ContextVar[str] = ContextVar("tenant_id")
 
 workflow_variable_pool: ContextVar["VariablePool"] = ContextVar("workflow_variable_pool")
 
-plugin_tool_providers: ContextVar[dict[str, "PluginToolProviderController"]] = ContextVar("plugin_tool_providers")
-plugin_tool_providers_lock: ContextVar[Lock] = ContextVar("plugin_tool_providers_lock")
+"""
+To avoid race-conditions caused by gunicorn thread recycling, using RecyclableContextVar to replace with
+"""
+plugin_tool_providers: RecyclableContextVar[dict[str, "PluginToolProviderController"]] = RecyclableContextVar(
+    ContextVar("plugin_tool_providers")
+)
+plugin_tool_providers_lock: RecyclableContextVar[Lock] = RecyclableContextVar(ContextVar("plugin_tool_providers_lock"))
 
-plugin_model_providers: ContextVar[list["PluginModelProviderEntity"] | None] = ContextVar("plugin_model_providers")
-plugin_model_providers_lock: ContextVar[Lock] = ContextVar("plugin_model_providers_lock")
+plugin_model_providers: RecyclableContextVar[list["PluginModelProviderEntity"] | None] = RecyclableContextVar(
+    ContextVar("plugin_model_providers")
+)
+plugin_model_providers_lock: RecyclableContextVar[Lock] = RecyclableContextVar(
+    ContextVar("plugin_model_providers_lock")
+)

api/contexts/wrapper.py

@@ -0,0 +1,65 @@
+from contextvars import ContextVar
+from typing import Generic, TypeVar
+
+T = TypeVar("T")
+
+
+class HiddenValue:
+    pass
+
+
+_default = HiddenValue()
+
+
+class RecyclableContextVar(Generic[T]):
+    """
+    RecyclableContextVar is a wrapper around ContextVar
+    It's safe to use in gunicorn with thread recycling, but features like `reset` are not available for now
+
+    NOTE: you need to call `increment_thread_recycles` before requests
+    """
+
+    _thread_recycles: ContextVar[int] = ContextVar("thread_recycles")
+
+    @classmethod
+    def increment_thread_recycles(cls):
+        try:
+            recycles = cls._thread_recycles.get()
+            cls._thread_recycles.set(recycles + 1)
+        except LookupError:
+            cls._thread_recycles.set(0)
+
+    def __init__(self, context_var: ContextVar[T]):
+        self._context_var = context_var
+        self._updates = ContextVar[int](context_var.name + "_updates", default=0)
+
+    def get(self, default: T | HiddenValue = _default) -> T:
+        thread_recycles = self._thread_recycles.get(0)
+        self_updates = self._updates.get()
+        if thread_recycles > self_updates:
+            self._updates.set(thread_recycles)
+
+        # check if thread is recycled and should be updated
+        if thread_recycles < self_updates:
+            return self._context_var.get()
+        else:
+            # thread_recycles >= self_updates, means current context is invalid
+            if isinstance(default, HiddenValue) or default is _default:
+                raise LookupError
+            else:
+                return default
+
+    def set(self, value: T):
+        # it leads to a situation that self.updates is less than cls.thread_recycles if `set` was never called before
+        # increase it manually
+        thread_recycles = self._thread_recycles.get(0)
+        self_updates = self._updates.get()
+        if thread_recycles > self_updates:
+            self._updates.set(thread_recycles)
+
+        if self._updates.get() == self._thread_recycles.get(0):
+            # after increment,
+            self._updates.set(self._updates.get() + 1)
+
+        # set the context
+        self._context_var.set(value)

api/controllers/console/datasets/datasets.py

@@ -623,7 +623,6 @@ class DatasetRetrievalSettingApi(Resource):
         match vector_type:
             case (
                 VectorType.RELYT
-                | VectorType.PGVECTOR
                 | VectorType.TIDB_VECTOR
                 | VectorType.CHROMA
                 | VectorType.TENCENT

api/controllers/files/image_preview.py

@@ -1,3 +1,5 @@
+from urllib.parse import quote
+
 from flask import Response, request
 from flask_restful import Resource, reqparse  # type: ignore
 from werkzeug.exceptions import NotFound
@@ -71,7 +73,8 @@ class FilePreviewApi(Resource):
         if upload_file.size > 0:
             response.headers["Content-Length"] = str(upload_file.size)
         if args["as_attachment"]:
-            response.headers["Content-Disposition"] = f"attachment; filename={upload_file.name}"
+            encoded_filename = quote(upload_file.name)
+            response.headers["Content-Disposition"] = f"attachment; filename*=UTF-8''{encoded_filename}"
 
         return response
 

api/controllers/inner_api/workspace/workspace.py

@@ -50,8 +50,8 @@ class EnterpriseWorkspaceNoOwnerEmail(Resource):
             "plan": tenant.plan,
             "status": tenant.status,
             "custom_config": json.loads(tenant.custom_config) if tenant.custom_config else {},
-            "created_at": tenant.created_at.isoformat() if tenant.created_at else None,
-            "updated_at": tenant.updated_at.isoformat() if tenant.updated_at else None,
+            "created_at": tenant.created_at.isoformat() + "Z" if tenant.created_at else None,
+            "updated_at": tenant.updated_at.isoformat() + "Z" if tenant.updated_at else None,
         }
 
         return {

api/controllers/service_api/app/message.py

@@ -10,6 +10,7 @@ from controllers.service_api.app.error import NotChatAppError
 from controllers.service_api.wraps import FetchUserArg, WhereisUserArg, validate_app_token
 from core.app.entities.app_invoke_entities import InvokeFrom
 from fields.conversation_fields import message_file_fields
+from fields.message_fields import feedback_fields, retriever_resource_fields
 from fields.raws import FilesContainedField
 from libs.helper import TimestampField, uuid_value
 from models.model import App, AppMode, EndUser
@@ -18,26 +19,6 @@ from services.message_service import MessageService
 
 
 class MessageListApi(Resource):
-    feedback_fields = {"rating": fields.String}
-    retriever_resource_fields = {
-        "id": fields.String,
-        "message_id": fields.String,
-        "position": fields.Integer,
-        "dataset_id": fields.String,
-        "dataset_name": fields.String,
-        "document_id": fields.String,
-        "document_name": fields.String,
-        "data_source_type": fields.String,
-        "segment_id": fields.String,
-        "score": fields.Float,
-        "hit_count": fields.Integer,
-        "word_count": fields.Integer,
-        "segment_position": fields.Integer,
-        "index_node_hash": fields.String,
-        "content": fields.String,
-        "created_at": TimestampField,
-    }
-
     agent_thought_fields = {
         "id": fields.String,
         "chain_id": fields.String,
@@ -89,7 +70,7 @@ class MessageListApi(Resource):
 
         try:
             return MessageService.pagination_by_first_id(
-                app_model, end_user, args["conversation_id"], args["first_id"], args["limit"]
+                app_model, end_user, args["conversation_id"], args["first_id"], args["limit"], "desc"
             )
         except services.errors.conversation.ConversationNotExistsError:
             raise NotFound("Conversation Not Exists.")

api/controllers/service_api/dataset/document.py

@@ -336,6 +336,10 @@ class DocumentUpdateByFileApi(DatasetApiResource):
 
         if not dataset:
             raise ValueError("Dataset is not exist.")
+
+        # indexing_technique is already set in dataset since this is an update
+        args["indexing_technique"] = dataset.indexing_technique
+
         if "file" in request.files:
             # save file info
             file = request.files["file"]

api/controllers/service_api/wraps.py

@@ -154,7 +154,7 @@ def validate_dataset_token(view=None):
             )  # TODO: only owner information is required, so only one is returned.
             if tenant_account_join:
                 tenant, ta = tenant_account_join
-                account = Account.query.filter_by(id=ta.account_id).first()
+                account = db.session.query(Account).filter(Account.id == ta.account_id).first()
                 # Login admin
                 if account:
                     account.current_tenant = tenant

api/controllers/web/message.py

@@ -21,7 +21,7 @@ from core.app.entities.app_invoke_entities import InvokeFrom
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
 from core.model_runtime.errors.invoke import InvokeError
 from fields.conversation_fields import message_file_fields
-from fields.message_fields import agent_thought_fields
+from fields.message_fields import agent_thought_fields, feedback_fields, retriever_resource_fields
 from fields.raws import FilesContainedField
 from libs import helper
 from libs.helper import TimestampField, uuid_value
@@ -34,27 +34,6 @@ from services.message_service import MessageService
 
 
 class MessageListApi(WebApiResource):
-    feedback_fields = {"rating": fields.String}
-
-    retriever_resource_fields = {
-        "id": fields.String,
-        "message_id": fields.String,
-        "position": fields.Integer,
-        "dataset_id": fields.String,
-        "dataset_name": fields.String,
-        "document_id": fields.String,
-        "document_name": fields.String,
-        "data_source_type": fields.String,
-        "segment_id": fields.String,
-        "score": fields.Float,
-        "hit_count": fields.Integer,
-        "word_count": fields.Integer,
-        "segment_position": fields.Integer,
-        "index_node_hash": fields.String,
-        "content": fields.String,
-        "created_at": TimestampField,
-    }
-
     message_fields = {
         "id": fields.String,
         "conversation_id": fields.String,

api/core/agent/entities.py

@@ -1,7 +1,7 @@
 from enum import StrEnum
 from typing import Any, Optional, Union
 
-from pydantic import BaseModel
+from pydantic import BaseModel, Field
 
 from core.tools.entities.tool_entities import ToolInvokeMessage, ToolProviderType
 
@@ -14,7 +14,7 @@ class AgentToolEntity(BaseModel):
     provider_type: ToolProviderType
     provider_id: str
     tool_name: str
-    tool_parameters: dict[str, Any] = {}
+    tool_parameters: dict[str, Any] = Field(default_factory=dict)
     plugin_unique_identifier: str | None = None
 
 

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

@@ -2,9 +2,9 @@ from collections.abc import Mapping
 from typing import Any
 
 from core.app.app_config.entities import ModelConfigEntity
-from core.entities import DEFAULT_PLUGIN_ID
 from core.model_runtime.entities.model_entities import ModelPropertyKey, ModelType
 from core.model_runtime.model_providers.model_provider_factory import ModelProviderFactory
+from core.plugin.entities.plugin import ModelProviderID
 from core.provider_manager import ProviderManager
 
 
@@ -61,9 +61,7 @@ class ModelConfigManager:
             raise ValueError(f"model.provider is required and must be in {str(model_provider_names)}")
 
         if "/" not in config["model"]["provider"]:
-            config["model"]["provider"] = (
-                f"{DEFAULT_PLUGIN_ID}/{config['model']['provider']}/{config['model']['provider']}"
-            )
+            config["model"]["provider"] = str(ModelProviderID(config["model"]["provider"]))
 
         if config["model"]["provider"] not in model_provider_names:
             raise ValueError(f"model.provider is required and must be in {str(model_provider_names)}")

api/core/app/app_config/entities.py

@@ -17,8 +17,8 @@ class ModelConfigEntity(BaseModel):
     provider: str
     model: str
     mode: Optional[str] = None
-    parameters: dict[str, Any] = {}
-    stop: list[str] = []
+    parameters: dict[str, Any] = Field(default_factory=dict)
+    stop: list[str] = Field(default_factory=list)
 
 
 class AdvancedChatMessageEntity(BaseModel):
@@ -132,7 +132,7 @@ class ExternalDataVariableEntity(BaseModel):
 
     variable: str
     type: str
-    config: dict[str, Any] = {}
+    config: dict[str, Any] = Field(default_factory=dict)
 
 
 class DatasetRetrieveConfigEntity(BaseModel):
@@ -188,7 +188,7 @@ class SensitiveWordAvoidanceEntity(BaseModel):
     """
 
     type: str
-    config: dict[str, Any] = {}
+    config: dict[str, Any] = Field(default_factory=dict)
 
 
 class TextToSpeechEntity(BaseModel):

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

@@ -140,9 +140,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
             app_config=app_config,
             file_upload_config=file_extra_config,
             conversation_id=conversation.id if conversation else None,
-            inputs=conversation.inputs
-            if conversation
-            else self._prepare_user_inputs(
+            inputs=self._prepare_user_inputs(
                 user_inputs=inputs, variables=app_config.variables, tenant_id=app_model.tenant_id
             ),
             query=query,

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

@@ -149,9 +149,7 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
             model_conf=ModelConfigConverter.convert(app_config),
             file_upload_config=file_extra_config,
             conversation_id=conversation.id if conversation else None,
-            inputs=conversation.inputs
-            if conversation
-            else self._prepare_user_inputs(
+            inputs=self._prepare_user_inputs(
                 user_inputs=inputs, variables=app_config.variables, tenant_id=app_model.tenant_id
             ),
             query=query,

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

@@ -141,9 +141,7 @@ class ChatAppGenerator(MessageBasedAppGenerator):
             model_conf=ModelConfigConverter.convert(app_config),
             file_upload_config=file_extra_config,
             conversation_id=conversation.id if conversation else None,
-            inputs=conversation.inputs
-            if conversation
-            else self._prepare_user_inputs(
+            inputs=self._prepare_user_inputs(
                 user_inputs=inputs, variables=app_config.variables, tenant_id=app_model.tenant_id
             ),
             query=query,

api/core/app/apps/message_based_app_generator.py

@@ -42,7 +42,6 @@ class MessageBasedAppGenerator(BaseAppGenerator):
             ChatAppGenerateEntity,
             CompletionAppGenerateEntity,
             AgentChatAppGenerateEntity,
-            AgentChatAppGenerateEntity,
         ],
         queue_manager: AppQueueManager,
         conversation: Conversation,

api/core/app/entities/app_invoke_entities.py

@@ -63,9 +63,9 @@ class ModelConfigWithCredentialsEntity(BaseModel):
     model_schema: AIModelEntity
     mode: str
     provider_model_bundle: ProviderModelBundle
-    credentials: dict[str, Any] = {}
-    parameters: dict[str, Any] = {}
-    stop: list[str] = []
+    credentials: dict[str, Any] = Field(default_factory=dict)
+    parameters: dict[str, Any] = Field(default_factory=dict)
+    stop: list[str] = Field(default_factory=list)
 
     # pydantic configs
     model_config = ConfigDict(protected_namespaces=())
@@ -94,7 +94,7 @@ class AppGenerateEntity(BaseModel):
     call_depth: int = 0
 
     # extra parameters, like: auto_generate_conversation_name
-    extras: dict[str, Any] = {}
+    extras: dict[str, Any] = Field(default_factory=dict)
 
     # tracing instance
     trace_manager: Optional[TraceQueueManager] = None

api/core/app/task_pipeline/workflow_cycle_manage.py

@@ -844,7 +844,7 @@ class WorkflowCycleManage:
         if node_execution_id not in self._workflow_node_executions:
             raise ValueError(f"Workflow node execution not found: {node_execution_id}")
         cached_workflow_node_execution = self._workflow_node_executions[node_execution_id]
-        return cached_workflow_node_execution
+        return session.merge(cached_workflow_node_execution)
 
     def _handle_agent_log(self, task_id: str, event: QueueAgentLogEvent) -> AgentLogStreamResponse:
         """

api/core/entities/provider_configuration.py

@@ -6,10 +6,10 @@ from collections.abc import Iterator, Sequence
 from json import JSONDecodeError
 from typing import Optional
 
-from pydantic import BaseModel, ConfigDict
+from pydantic import BaseModel, ConfigDict, Field
+from sqlalchemy import or_
 
 from constants import HIDDEN_VALUE
-from core.entities import DEFAULT_PLUGIN_ID
 from core.entities.model_entities import ModelStatus, ModelWithProviderEntity, SimpleModelProviderEntity
 from core.entities.provider_entities import (
     CustomConfiguration,
@@ -28,6 +28,7 @@ from core.model_runtime.entities.provider_entities import (
 )
 from core.model_runtime.model_providers.__base.ai_model import AIModel
 from core.model_runtime.model_providers.model_provider_factory import ModelProviderFactory
+from core.plugin.entities.plugin import ModelProviderID
 from extensions.ext_database import db
 from models.provider import (
     LoadBalancingModelConfig,
@@ -190,8 +191,11 @@ class ProviderConfiguration(BaseModel):
             db.session.query(Provider)
             .filter(
                 Provider.tenant_id == self.tenant_id,
-                Provider.provider_name == self.provider.provider,
                 Provider.provider_type == ProviderType.CUSTOM.value,
+                or_(
+                    Provider.provider_name == ModelProviderID(self.provider.provider).plugin_name,
+                    Provider.provider_name == self.provider.provider,
+                ),
             )
             .first()
         )
@@ -279,7 +283,10 @@ class ProviderConfiguration(BaseModel):
             db.session.query(Provider)
             .filter(
                 Provider.tenant_id == self.tenant_id,
-                Provider.provider_name == self.provider.provider,
+                or_(
+                    Provider.provider_name == ModelProviderID(self.provider.provider).plugin_name,
+                    Provider.provider_name == self.provider.provider,
+                ),
                 Provider.provider_type == ProviderType.CUSTOM.value,
             )
             .first()
@@ -996,7 +1003,7 @@ class ProviderConfigurations(BaseModel):
     """
 
     tenant_id: str
-    configurations: dict[str, ProviderConfiguration] = {}
+    configurations: dict[str, ProviderConfiguration] = Field(default_factory=dict)
 
     def __init__(self, tenant_id: str):
         super().__init__(tenant_id=tenant_id)
@@ -1052,7 +1059,7 @@ class ProviderConfigurations(BaseModel):
 
     def __getitem__(self, key):
         if "/" not in key:
-            key = f"{DEFAULT_PLUGIN_ID}/{key}/{key}"
+            key = str(ModelProviderID(key))
 
         return self.configurations[key]
 
@@ -1067,7 +1074,7 @@ class ProviderConfigurations(BaseModel):
 
     def get(self, key, default=None) -> ProviderConfiguration | None:
         if "/" not in key:
-            key = f"{DEFAULT_PLUGIN_ID}/{key}/{key}"
+            key = str(ModelProviderID(key))
 
         return self.configurations.get(key, default)  # type: ignore
 

api/core/hosting_configuration.py

@@ -41,9 +41,13 @@ class HostedModerationConfig(BaseModel):
 
 
 class HostingConfiguration:
-    provider_map: dict[str, HostingProvider] = {}
+    provider_map: dict[str, HostingProvider]
     moderation_config: Optional[HostedModerationConfig] = None
 
+    def __init__(self) -> None:
+        self.provider_map = {}
+        self.moderation_config = None
+
     def init_app(self, app: Flask) -> None:
         if dify_config.EDITION != "CLOUD":
             return

api/core/model_runtime/model_providers/__base/large_language_model.py

@@ -228,7 +228,7 @@ class LargeLanguageModel(AIModel):
         :return: result generator
         """
         callbacks = callbacks or []
-        prompt_message = AssistantPromptMessage(content="")
+        assistant_message = AssistantPromptMessage(content="")
         usage = None
         system_fingerprint = None
         real_model = model
@@ -250,7 +250,7 @@ class LargeLanguageModel(AIModel):
                     callbacks=callbacks,
                 )
 
-                prompt_message.content += chunk.delta.message.content
+                assistant_message.content += chunk.delta.message.content
                 real_model = chunk.model
                 if chunk.delta.usage:
                     usage = chunk.delta.usage
@@ -265,7 +265,7 @@ class LargeLanguageModel(AIModel):
             result=LLMResult(
                 model=real_model,
                 prompt_messages=prompt_messages,
-                message=prompt_message,
+                message=assistant_message,
                 usage=usage or LLMUsage.empty_usage(),
                 system_fingerprint=system_fingerprint,
             ),

api/core/model_runtime/model_providers/model_provider_factory.py

@@ -7,7 +7,6 @@ from typing import Optional
 from pydantic import BaseModel
 
 import contexts
-from core.entities import DEFAULT_PLUGIN_ID
 from core.helper.position_helper import get_provider_position_map, sort_to_dict_by_position_map
 from core.model_runtime.entities.model_entities import AIModelEntity, ModelType
 from core.model_runtime.entities.provider_entities import ProviderConfig, ProviderEntity, SimpleProviderEntity
@@ -34,9 +33,11 @@ class ModelProviderExtension(BaseModel):
 
 
 class ModelProviderFactory:
-    provider_position_map: dict[str, int] = {}
+    provider_position_map: dict[str, int]
 
     def __init__(self, tenant_id: str) -> None:
+        self.provider_position_map = {}
+
         self.tenant_id = tenant_id
         self.plugin_model_manager = PluginModelManager()
 
@@ -360,11 +361,5 @@ class ModelProviderFactory:
         :param provider: provider name
         :return: plugin id and provider name
         """
-        plugin_id = DEFAULT_PLUGIN_ID
-        provider_name = provider
-        if "/" in provider:
-            # get the plugin_id before provider
-            plugin_id = "/".join(provider.split("/")[:-1])
-            provider_name = provider.split("/")[-1]
-
-        return str(plugin_id), provider_name
+        provider_id = ModelProviderID(provider)
+        return provider_id.plugin_id, provider_id.provider_name

api/core/model_runtime/model_providers/vertex_ai/llm/_position.yaml

@@ -0,0 +1,22 @@
+- claude-3-haiku@20240307
+- claude-3-opus@20240229
+- claude-3-sonnet@20240229
+- claude-3-5-sonnet-v2@20241022
+- claude-3-5-sonnet@20240620
+- gemini-1.0-pro-vision-001
+- gemini-1.0-pro-002
+- gemini-1.5-flash-001
+- gemini-1.5-flash-002
+- gemini-1.5-pro-001
+- gemini-1.5-pro-002
+- gemini-2.0-flash-001
+- gemini-2.0-flash-exp
+- gemini-2.0-flash-lite-preview-02-05
+- gemini-2.0-flash-thinking-exp-01-21
+- gemini-2.0-flash-thinking-exp-1219
+- gemini-2.0-pro-exp-02-05
+- gemini-exp-1114
+- gemini-exp-1121
+- gemini-exp-1206
+- gemini-flash-experimental
+- gemini-pro-experimental

api/core/plugin/entities/plugin.py

@@ -159,7 +159,7 @@ class GenericProviderID:
             if re.match(r"^[a-z0-9_-]+$", value):
                 value = f"langgenius/{value}/{value}"
             else:
-                raise ValueError("Invalid plugin id")
+                raise ValueError(f"Invalid plugin id {value}")
 
         self.organization, self.plugin_name, self.provider_name = value.split("/")
         self.is_hardcoded = is_hardcoded
@@ -180,7 +180,7 @@ class ToolProviderID(GenericProviderID):
     def __init__(self, value: str, is_hardcoded: bool = False) -> None:
         super().__init__(value, is_hardcoded)
         if self.organization == "langgenius":
-            if self.provider_name in ["jina", "siliconflow"]:
+            if self.provider_name in ["jina", "siliconflow", "stepfun", "gitee_ai"]:
                 self.plugin_name = f"{self.provider_name}_tool"
 
 
@@ -212,3 +212,9 @@ class PluginDependency(BaseModel):
 
     type: Type
     value: Github | Marketplace | Package
+    current_identifier: Optional[str] = None
+
+
+class MissingPluginDependency(BaseModel):
+    plugin_unique_identifier: str
+    current_identifier: Optional[str] = None

api/core/plugin/manager/plugin.py

@@ -3,6 +3,7 @@ from collections.abc import Sequence
 from core.plugin.entities.bundle import PluginBundleDependency
 from core.plugin.entities.plugin import (
     GenericProviderID,
+    MissingPluginDependency,
     PluginDeclaration,
     PluginEntity,
     PluginInstallation,
@@ -175,14 +176,16 @@ class PluginInstallationManager(BasePluginManager):
             headers={"Content-Type": "application/json"},
         )
 
-    def fetch_missing_dependencies(self, tenant_id: str, plugin_unique_identifiers: list[str]) -> list[str]:
+    def fetch_missing_dependencies(
+        self, tenant_id: str, plugin_unique_identifiers: list[str]
+    ) -> list[MissingPluginDependency]:
         """
         Fetch missing dependencies
         """
         return self._request_with_plugin_daemon_response(
             "POST",
             f"plugin/{tenant_id}/management/installation/missing",
-            list[str],
+            list[MissingPluginDependency],
             data={"plugin_unique_identifiers": plugin_unique_identifiers},
             headers={"Content-Type": "application/json"},
         )

api/core/plugin/manager/tool.py

@@ -3,7 +3,7 @@ from typing import Any, Optional
 
 from pydantic import BaseModel
 
-from core.plugin.entities.plugin import GenericProviderID
+from core.plugin.entities.plugin import GenericProviderID, ToolProviderID
 from core.plugin.entities.plugin_daemon import PluginBasicBooleanResponse, PluginToolProviderEntity
 from core.plugin.manager.base import BasePluginManager
 from core.tools.entities.tool_entities import ToolInvokeMessage, ToolParameter
@@ -45,7 +45,7 @@ class PluginToolManager(BasePluginManager):
         """
         Fetch tool provider for the given tenant and plugin.
         """
-        tool_provider_id = GenericProviderID(provider)
+        tool_provider_id = ToolProviderID(provider)
 
         def transformer(json_response: dict[str, Any]) -> dict:
             data = json_response.get("data")

api/core/provider_manager.py

@@ -100,8 +100,23 @@ class ProviderManager:
             tenant_id, provider_name_to_provider_records_dict
         )
 
+        # append providers with langgenius/openai/openai
+        provider_name_list = list(provider_name_to_provider_records_dict.keys())
+        for provider_name in provider_name_list:
+            provider_id = ModelProviderID(provider_name)
+            if str(provider_id) not in provider_name_list:
+                provider_name_to_provider_records_dict[str(provider_id)] = provider_name_to_provider_records_dict[
+                    provider_name
+                ]
+
         # Get all provider model records of the workspace
         provider_name_to_provider_model_records_dict = self._get_all_provider_models(tenant_id)
+        for provider_name in list(provider_name_to_provider_model_records_dict.keys()):
+            provider_id = ModelProviderID(provider_name)
+            if str(provider_id) not in provider_name_to_provider_model_records_dict:
+                provider_name_to_provider_model_records_dict[str(provider_id)] = (
+                    provider_name_to_provider_model_records_dict[provider_name]
+                )
 
         # Get all provider entities
         model_provider_factory = ModelProviderFactory(tenant_id)
@@ -360,7 +375,8 @@ class ProviderManager:
 
         provider_name_to_provider_records_dict = defaultdict(list)
         for provider in providers:
-            provider_name_to_provider_records_dict[provider.provider_name].append(provider)
+            # TODO: Use provider name with prefix after the data migration
+            provider_name_to_provider_records_dict[str(ModelProviderID(provider.provider_name))].append(provider)
 
         return provider_name_to_provider_records_dict
 
@@ -454,11 +470,9 @@ class ProviderManager:
 
         provider_name_to_provider_load_balancing_model_configs_dict = defaultdict(list)
         for provider_load_balancing_config in provider_load_balancing_configs:
-            (
-                provider_name_to_provider_load_balancing_model_configs_dict[
-                    provider_load_balancing_config.provider_name
-                ].append(provider_load_balancing_config)
-            )
+            provider_name_to_provider_load_balancing_model_configs_dict[
+                provider_load_balancing_config.provider_name
+            ].append(provider_load_balancing_config)
 
         return provider_name_to_provider_load_balancing_model_configs_dict
 
@@ -501,7 +515,8 @@ class ProviderManager:
                             # FIXME ignore the type errork, onyl TrialHostingQuota has limit need to change the logic
                             provider_record = Provider(
                                 tenant_id=tenant_id,
-                                provider_name=provider_name,
+                                # TODO: Use provider name with prefix after the data migration.
+                                provider_name=ModelProviderID(provider_name).provider_name,
                                 provider_type=ProviderType.SYSTEM.value,
                                 quota_type=ProviderQuotaType.TRIAL.value,
                                 quota_limit=quota.quota_limit,  # type: ignore
@@ -516,13 +531,12 @@ class ProviderManager:
                                 db.session.query(Provider)
                                 .filter(
                                     Provider.tenant_id == tenant_id,
-                                    Provider.provider_name == provider_name,
+                                    Provider.provider_name == ModelProviderID(provider_name).provider_name,
                                     Provider.provider_type == ProviderType.SYSTEM.value,
                                     Provider.quota_type == ProviderQuotaType.TRIAL.value,
                                 )
                                 .first()
                             )
-
                             if provider_record and not provider_record.is_valid:
                                 provider_record.is_valid = True
                                 db.session.commit()

api/core/rag/datasource/retrieval_service.py

@@ -1,8 +1,12 @@
-import threading
+import concurrent.futures
+import json
+from concurrent.futures import ThreadPoolExecutor
 from typing import Optional
 
 from flask import Flask, current_app
+from sqlalchemy.orm import load_only
 
+from configs import dify_config
 from core.rag.data_post_processor.data_post_processor import DataPostProcessor
 from core.rag.datasource.keyword.keyword_factory import Keyword
 from core.rag.datasource.vdb.vector_factory import Vector
@@ -26,6 +30,7 @@ default_retrieval_model = {
 
 
 class RetrievalService:
+    # Cache precompiled regular expressions to avoid repeated compilation
     @classmethod
     def retrieve(
         cls,
@@ -40,74 +45,62 @@ class RetrievalService:
     ):
         if not query:
             return []
-        dataset = db.session.query(Dataset).filter(Dataset.id == dataset_id).first()
-        if not dataset:
-            return []
-
+        dataset = cls._get_dataset(dataset_id)
         if not dataset or dataset.available_document_count == 0 or dataset.available_segment_count == 0:
             return []
+
         all_documents: list[Document] = []
-        threads: list[threading.Thread] = []
         exceptions: list[str] = []
-        # retrieval_model source with keyword
-        if retrieval_method == "keyword_search":
-            keyword_thread = threading.Thread(
-                target=RetrievalService.keyword_search,
-                kwargs={
-                    "flask_app": current_app._get_current_object(),  # type: ignore
-                    "dataset_id": dataset_id,
-                    "query": query,
-                    "top_k": top_k,
-                    "all_documents": all_documents,
-                    "exceptions": exceptions,
-                },
-            )
-            threads.append(keyword_thread)
-            keyword_thread.start()
-        # retrieval_model source with semantic
-        if RetrievalMethod.is_support_semantic_search(retrieval_method):
-            embedding_thread = threading.Thread(
-                target=RetrievalService.embedding_search,
-                kwargs={
-                    "flask_app": current_app._get_current_object(),  # type: ignore
-                    "dataset_id": dataset_id,
-                    "query": query,
-                    "top_k": top_k,
-                    "score_threshold": score_threshold,
-                    "reranking_model": reranking_model,
-                    "all_documents": all_documents,
-                    "retrieval_method": retrieval_method,
-                    "exceptions": exceptions,
-                },
-            )
-            threads.append(embedding_thread)
-            embedding_thread.start()
 
-        # retrieval source with full text
-        if RetrievalMethod.is_support_fulltext_search(retrieval_method):
-            full_text_index_thread = threading.Thread(
-                target=RetrievalService.full_text_index_search,
-                kwargs={
-                    "flask_app": current_app._get_current_object(),  # type: ignore
-                    "dataset_id": dataset_id,
-                    "query": query,
-                    "retrieval_method": retrieval_method,
-                    "score_threshold": score_threshold,
-                    "top_k": top_k,
-                    "reranking_model": reranking_model,
-                    "all_documents": all_documents,
-                    "exceptions": exceptions,
-                },
-            )
-            threads.append(full_text_index_thread)
-            full_text_index_thread.start()
-
-        for thread in threads:
-            thread.join()
+        # Optimize multithreading with thread pools
+        with ThreadPoolExecutor(max_workers=dify_config.RETRIEVAL_SERVICE_EXECUTORS) as executor:  # type: ignore
+            futures = []
+            if retrieval_method == "keyword_search":
+                futures.append(
+                    executor.submit(
+                        cls.keyword_search,
+                        flask_app=current_app._get_current_object(),  # type: ignore
+                        dataset_id=dataset_id,
+                        query=query,
+                        top_k=top_k,
+                        all_documents=all_documents,
+                        exceptions=exceptions,
+                    )
+                )
+            if RetrievalMethod.is_support_semantic_search(retrieval_method):
+                futures.append(
+                    executor.submit(
+                        cls.embedding_search,
+                        flask_app=current_app._get_current_object(),  # type: ignore
+                        dataset_id=dataset_id,
+                        query=query,
+                        top_k=top_k,
+                        score_threshold=score_threshold,
+                        reranking_model=reranking_model,
+                        all_documents=all_documents,
+                        retrieval_method=retrieval_method,
+                        exceptions=exceptions,
+                    )
+                )
+            if RetrievalMethod.is_support_fulltext_search(retrieval_method):
+                futures.append(
+                    executor.submit(
+                        cls.full_text_index_search,
+                        flask_app=current_app._get_current_object(),  # type: ignore
+                        dataset_id=dataset_id,
+                        query=query,
+                        top_k=top_k,
+                        score_threshold=score_threshold,
+                        reranking_model=reranking_model,
+                        all_documents=all_documents,
+                        retrieval_method=retrieval_method,
+                        exceptions=exceptions,
+                    )
+                )
+            concurrent.futures.wait(futures, timeout=30, return_when=concurrent.futures.ALL_COMPLETED)
 
         if exceptions:
-            exception_message = ";\n".join(exceptions)
-            raise ValueError(exception_message)
+            raise ValueError(";\n".join(exceptions))
 
         if retrieval_method == RetrievalMethod.HYBRID_SEARCH.value:
             data_post_processor = DataPostProcessor(
@@ -132,18 +125,21 @@ class RetrievalService:
         )
         return all_documents
 
+    @classmethod
+    def _get_dataset(cls, dataset_id: str) -> Optional[Dataset]:
+        return db.session.query(Dataset).filter(Dataset.id == dataset_id).first()
+
     @classmethod
     def keyword_search(
         cls, flask_app: Flask, dataset_id: str, query: str, top_k: int, all_documents: list, exceptions: list
     ):
         with flask_app.app_context():
             try:
-                dataset = db.session.query(Dataset).filter(Dataset.id == dataset_id).first()
+                dataset = cls._get_dataset(dataset_id)
                 if not dataset:
                     raise ValueError("dataset not found")
 
                 keyword = Keyword(dataset=dataset)
-
                 documents = keyword.search(cls.escape_query_for_search(query), top_k=top_k)
                 all_documents.extend(documents)
             except Exception as e:
@@ -164,14 +160,13 @@ class RetrievalService:
     ):
         with flask_app.app_context():
             try:
-                dataset = db.session.query(Dataset).filter(Dataset.id == dataset_id).first()
+                dataset = cls._get_dataset(dataset_id)
                 if not dataset:
                     raise ValueError("dataset not found")
 
                 vector = Vector(dataset=dataset)
-
                 documents = vector.search_by_vector(
-                    cls.escape_query_for_search(query),
+                    query,
                     search_type="similarity_score_threshold",
                     top_k=top_k,
                     score_threshold=score_threshold,
@@ -186,7 +181,7 @@ class RetrievalService:
                         and retrieval_method == RetrievalMethod.SEMANTIC_SEARCH.value
                     ):
                         data_post_processor = DataPostProcessor(
-                            str(dataset.tenant_id), RerankMode.RERANKING_MODEL.value, reranking_model, None, False
+                            str(dataset.tenant_id), str(RerankMode.RERANKING_MODEL.value), reranking_model, None, False
                         )
                         all_documents.extend(
                             data_post_processor.invoke(
@@ -216,13 +211,11 @@ class RetrievalService:
     ):
         with flask_app.app_context():
             try:
-                dataset = db.session.query(Dataset).filter(Dataset.id == dataset_id).first()
+                dataset = cls._get_dataset(dataset_id)
                 if not dataset:
                     raise ValueError("dataset not found")
 
-                vector_processor = Vector(
-                    dataset=dataset,
-                )
+                vector_processor = Vector(dataset=dataset)
 
                 documents = vector_processor.search_by_full_text(cls.escape_query_for_search(query), top_k=top_k)
                 if documents:
@@ -233,7 +226,7 @@ class RetrievalService:
                         and retrieval_method == RetrievalMethod.FULL_TEXT_SEARCH.value
                     ):
                         data_post_processor = DataPostProcessor(
-                            str(dataset.tenant_id), RerankMode.RERANKING_MODEL.value, reranking_model, None, False
+                            str(dataset.tenant_id), str(RerankMode.RERANKING_MODEL.value), reranking_model, None, False
                         )
                         all_documents.extend(
                             data_post_processor.invoke(
@@ -250,66 +243,106 @@ class RetrievalService:
 
     @staticmethod
     def escape_query_for_search(query: str) -> str:
-        return query.replace('"', '\\"')
+        return json.dumps(query).strip('"')
+
+    @classmethod
+    def format_retrieval_documents(cls, documents: list[Document]) -> list[RetrievalSegments]:
+        """Format retrieval documents with optimized batch processing"""
+        if not documents:
+            return []
+
+        try:
+            # Collect document IDs
+            document_ids = {doc.metadata.get("document_id") for doc in documents if "document_id" in doc.metadata}
+            if not document_ids:
+                return []
+
+            # Batch query dataset documents
+            dataset_documents = {
+                doc.id: doc
+                for doc in db.session.query(DatasetDocument)
+                .filter(DatasetDocument.id.in_(document_ids))
+                .options(load_only(DatasetDocument.id, DatasetDocument.doc_form, DatasetDocument.dataset_id))
+                .all()
+            }
+
+            records = []
+            include_segment_ids = set()
+            segment_child_map = {}
+
+            # Process documents
+            for document in documents:
+                document_id = document.metadata.get("document_id")
+                if document_id not in dataset_documents:
+                    continue
+
+                dataset_document = dataset_documents[document_id]
 
-    @staticmethod
-    def format_retrieval_documents(documents: list[Document]) -> list[RetrievalSegments]:
-        records = []
-        include_segment_ids = []
-        segment_child_map = {}
-        for document in documents:
-            document_id = document.metadata.get("document_id")
-            dataset_document = db.session.query(DatasetDocument).filter(DatasetDocument.id == document_id).first()
-            if dataset_document:
                 if dataset_document.doc_form == IndexType.PARENT_CHILD_INDEX:
+                    # Handle parent-child documents
                     child_index_node_id = document.metadata.get("doc_id")
-                    result = (
-                        db.session.query(ChildChunk, DocumentSegment)
-                        .join(DocumentSegment, ChildChunk.segment_id == DocumentSegment.id)
+
+                    child_chunk = (
+                        db.session.query(ChildChunk).filter(ChildChunk.index_node_id == child_index_node_id).first()
+                    )
+
+                    if not child_chunk:
+                        continue
+
+                    segment = (
+                        db.session.query(DocumentSegment)
                         .filter(
-                            ChildChunk.index_node_id == child_index_node_id,
                             DocumentSegment.dataset_id == dataset_document.dataset_id,
                             DocumentSegment.enabled == True,
                             DocumentSegment.status == "completed",
+                            DocumentSegment.id == child_chunk.segment_id,
+                        )
+                        .options(
+                            load_only(
+                                DocumentSegment.id,
+                                DocumentSegment.content,
+                                DocumentSegment.answer,
+                            )
                         )
                         .first()
                     )
-                    if result:
-                        child_chunk, segment = result
-                        if not segment:
-                            continue
-                        if segment.id not in include_segment_ids:
-                            include_segment_ids.append(segment.id)
-                            child_chunk_detail = {
-                                "id": child_chunk.id,
-                                "content": child_chunk.content,
-                                "position": child_chunk.position,
-                                "score": document.metadata.get("score", 0.0),
-                            }
-                            map_detail = {
-                                "max_score": document.metadata.get("score", 0.0),
-                                "child_chunks": [child_chunk_detail],
-                            }
-                            segment_child_map[segment.id] = map_detail
-                            record = {
-                                "segment": segment,
-                            }
-                            records.append(record)
-                        else:
-                            child_chunk_detail = {
-                                "id": child_chunk.id,
-                                "content": child_chunk.content,
-                                "position": child_chunk.position,
-                                "score": document.metadata.get("score", 0.0),
-                            }
-                            segment_child_map[segment.id]["child_chunks"].append(child_chunk_detail)
-                            segment_child_map[segment.id]["max_score"] = max(
-                                segment_child_map[segment.id]["max_score"], document.metadata.get("score", 0.0)
-                            )
-                    else:
+
+                    if not segment:
                         continue
+
+                    if segment.id not in include_segment_ids:
+                        include_segment_ids.add(segment.id)
+                        child_chunk_detail = {
+                            "id": child_chunk.id,
+                            "content": child_chunk.content,
+                            "position": child_chunk.position,
+                            "score": document.metadata.get("score", 0.0),
+                        }
+                        map_detail = {
+                            "max_score": document.metadata.get("score", 0.0),
+                            "child_chunks": [child_chunk_detail],
+                        }
+                        segment_child_map[segment.id] = map_detail
+                        record = {
+                            "segment": segment,
+                        }
+                        records.append(record)
+                    else:
+                        child_chunk_detail = {
+                            "id": child_chunk.id,
+                            "content": child_chunk.content,
+                            "position": child_chunk.position,
+                            "score": document.metadata.get("score", 0.0),
+                        }
+                        segment_child_map[segment.id]["child_chunks"].append(child_chunk_detail)
+                        segment_child_map[segment.id]["max_score"] = max(
+                            segment_child_map[segment.id]["max_score"], document.metadata.get("score", 0.0)
+                        )
                 else:
-                    index_node_id = document.metadata["doc_id"]
+                    # Handle normal documents
+                    index_node_id = document.metadata.get("doc_id")
+                    if not index_node_id:
+                        continue
 
                     segment = (
                         db.session.query(DocumentSegment)
@@ -324,16 +357,21 @@ class RetrievalService:
 
                     if not segment:
                         continue
-                    include_segment_ids.append(segment.id)
+
+                    include_segment_ids.add(segment.id)
                     record = {
                         "segment": segment,
-                        "score": document.metadata.get("score", None),
+                        "score": document.metadata.get("score"),  # type: ignore
                     }
-
                     records.append(record)
+
+            # Add child chunks information to records
             for record in records:
                 if record["segment"].id in segment_child_map:
-                    record["child_chunks"] = segment_child_map[record["segment"].id].get("child_chunks", None)
+                    record["child_chunks"] = segment_child_map[record["segment"].id].get("child_chunks")  # type: ignore
                     record["score"] = segment_child_map[record["segment"].id]["max_score"]
 
-        return [RetrievalSegments(**record) for record in records]
+            return [RetrievalSegments(**record) for record in records]
+        except Exception as e:
+            db.session.rollback()
+            raise e

api/core/rag/datasource/vdb/chroma/chroma_vector.py

@@ -111,8 +111,9 @@ class ChromaVector(BaseVector):
         for index in range(len(ids)):
             distance = distances[index]
             metadata = dict(metadatas[index])
-            if distance >= score_threshold:
-                metadata["score"] = distance
+            score = 1 - distance
+            if score > score_threshold:
+                metadata["score"] = score
                 doc = Document(
                     page_content=documents[index],
                     metadata=metadata,

api/core/rag/datasource/vdb/tidb_vector/tidb_vector.py

@@ -9,6 +9,7 @@ from sqlalchemy import text as sql_text
 from sqlalchemy.orm import Session, declarative_base
 
 from configs import dify_config
+from core.rag.datasource.vdb.field import Field
 from core.rag.datasource.vdb.vector_base import BaseVector
 from core.rag.datasource.vdb.vector_factory import AbstractVectorFactory
 from core.rag.datasource.vdb.vector_type import VectorType
@@ -54,14 +55,13 @@ class TiDBVector(BaseVector):
         return Table(
             self._collection_name,
             self._orm_base.metadata,
-            Column("id", String(36), primary_key=True, nullable=False),
+            Column(Field.PRIMARY_KEY.value, String(36), primary_key=True, nullable=False),
             Column(
-                "vector",
+                Field.VECTOR.value,
                 VectorType(dim),
                 nullable=False,
-                comment="" if self._distance_func is None else f"hnsw(distance={self._distance_func})",
             ),
-            Column("text", TEXT, nullable=False),
+            Column(Field.TEXT_KEY.value, TEXT, nullable=False),
             Column("meta", JSON, nullable=False),
             Column("create_time", DateTime, server_default=sqlalchemy.text("CURRENT_TIMESTAMP")),
             Column(
@@ -96,6 +96,7 @@ class TiDBVector(BaseVector):
             collection_exist_cache_key = "vector_indexing_{}".format(self._collection_name)
             if redis_client.get(collection_exist_cache_key):
                 return
+            tidb_dist_func = self._get_distance_func()
             with Session(self._engine) as session:
                 session.begin()
                 create_statement = sql_text(f"""
@@ -104,14 +105,14 @@ class TiDBVector(BaseVector):
                         text TEXT NOT NULL,
                         meta JSON NOT NULL,
                         doc_id VARCHAR(64) AS (JSON_UNQUOTE(JSON_EXTRACT(meta, '$.doc_id'))) STORED,
-                        KEY (doc_id),
-                        vector VECTOR<FLOAT>({dimension}) NOT NULL COMMENT "hnsw(distance={self._distance_func})",
+                        vector VECTOR<FLOAT>({dimension}) NOT NULL,
                         create_time DATETIME DEFAULT CURRENT_TIMESTAMP,
-                        update_time DATETIME DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP
+                        update_time DATETIME DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP,
+                        KEY (doc_id),
+                        VECTOR INDEX idx_vector (({tidb_dist_func}(vector))) USING HNSW
                     );
                 """)
                 session.execute(create_statement)
-                # tidb vector not support 'CREATE/ADD INDEX' now
                 session.commit()
             redis_client.set(collection_exist_cache_key, 1, ex=3600)
 
@@ -194,23 +195,30 @@ class TiDBVector(BaseVector):
         )
 
         docs = []
-        if self._distance_func == "l2":
-            tidb_func = "Vec_l2_distance"
-        elif self._distance_func == "cosine":
-            tidb_func = "Vec_Cosine_distance"
-        else:
-            tidb_func = "Vec_Cosine_distance"
+        tidb_dist_func = self._get_distance_func()
 
         with Session(self._engine) as session:
-            select_statement = sql_text(
-                f"""SELECT meta, text, distance FROM (
-                        SELECT meta, text, {tidb_func}(vector, "{query_vector_str}")  as distance
-                        FROM {self._collection_name}
-                        ORDER BY distance
-                        LIMIT {top_k}
-                    ) t WHERE distance < {distance};"""
+            select_statement = sql_text(f"""
+                SELECT meta, text, distance 
+                FROM (
+                  SELECT 
+                    meta,
+                    text,
+                    {tidb_dist_func}(vector, :query_vector_str) AS distance
+                  FROM {self._collection_name}
+                  ORDER BY distance ASC
+                  LIMIT :top_k
+                ) t
+                WHERE distance <= :distance
+                """)
+            res = session.execute(
+                select_statement,
+                params={
+                    "query_vector_str": query_vector_str,
+                    "distance": distance,
+                    "top_k": top_k,
+                },
             )
-            res = session.execute(select_statement)
             results = [(row[0], row[1], row[2]) for row in res]
             for meta, text, distance in results:
                 metadata = json.loads(meta)
@@ -227,6 +235,16 @@ class TiDBVector(BaseVector):
             session.execute(sql_text(f"""DROP TABLE IF EXISTS {self._collection_name};"""))
             session.commit()
 
+    def _get_distance_func(self) -> str:
+        match self._distance_func:
+            case "l2":
+                tidb_dist_func = "VEC_L2_DISTANCE"
+            case "cosine":
+                tidb_dist_func = "VEC_COSINE_DISTANCE"
+            case _:
+                tidb_dist_func = "VEC_COSINE_DISTANCE"
+        return tidb_dist_func
+
 
 class TiDBVectorFactory(AbstractVectorFactory):
     def init_vector(self, dataset: Dataset, attributes: list, embeddings: Embeddings) -> TiDBVector:

api/core/rag/retrieval/dataset_retrieval.py

@@ -203,6 +203,7 @@ class DatasetRetrieval:
                                 "segment_id": segment.id,
                                 "retriever_from": invoke_from.to_source(),
                                 "score": record.score or 0.0,
+                                "doc_metadata": document.doc_metadata,
                             }
 
                             if invoke_from.to_source() == "dev":

api/core/tools/custom_tool/tool.py

@@ -105,10 +105,10 @@ class ApiTool(Tool):
         needed_parameters = [parameter for parameter in (self.api_bundle.parameters or []) if parameter.required]
         for parameter in needed_parameters:
             if parameter.required and parameter.name not in parameters:
-                raise ToolParameterValidationError(f"Missing required parameter {parameter.name}")
-
-            if parameter.default is not None and parameter.name not in parameters:
-                parameters[parameter.name] = parameter.default
+                if parameter.default is not None:
+                    parameters[parameter.name] = parameter.default
+                else:
+                    raise ToolParameterValidationError(f"Missing required parameter {parameter.name}")
 
         return headers
 

api/core/tools/entities/tool_entities.py

@@ -185,7 +185,7 @@ class ToolInvokeMessage(BaseModel):
     """
         plain text, image url or link url
     """
-    message: JsonMessage | TextMessage | BlobMessage | VariableMessage | FileMessage | LogMessage | None
+    message: JsonMessage | TextMessage | BlobMessage | LogMessage | FileMessage | None | VariableMessage
     meta: dict[str, Any] | None = None
 
     @field_validator("message", mode="before")

api/core/tools/tool_engine.py

@@ -246,10 +246,11 @@ class ToolEngine:
                     + "you do not need to create it, just tell the user to check it now."
                 )
             elif response.type == ToolInvokeMessage.MessageType.JSON:
-                text = json.dumps(cast(ToolInvokeMessage.JsonMessage, response.message).json_object, ensure_ascii=False)
-                result += f"tool response: {text}."
+                result = json.dumps(
+                    cast(ToolInvokeMessage.JsonMessage, response.message).json_object, ensure_ascii=False
+                )
             else:
-                result += f"tool response: {response.message!r}."
+                result += str(response.message)
 
         return result
 

api/core/tools/tool_manager.py

@@ -9,7 +9,7 @@ from typing import TYPE_CHECKING, Any, Union, cast
 from yarl import URL
 
 import contexts
-from core.plugin.entities.plugin import GenericProviderID
+from core.plugin.entities.plugin import ToolProviderID
 from core.plugin.manager.tool import PluginToolManager
 from core.tools.__base.tool_provider import ToolProviderController
 from core.tools.__base.tool_runtime import ToolRuntime
@@ -188,13 +188,13 @@ class ToolManager:
                 )
 
             if isinstance(provider_controller, PluginToolProviderController):
-                provider_id_entity = GenericProviderID(provider_id)
+                provider_id_entity = ToolProviderID(provider_id)
                 # get credentials
                 builtin_provider: BuiltinToolProvider | None = (
                     db.session.query(BuiltinToolProvider)
                     .filter(
                         BuiltinToolProvider.tenant_id == tenant_id,
-                        (BuiltinToolProvider.provider == provider_id)
+                        (BuiltinToolProvider.provider == str(provider_id_entity))
                         | (BuiltinToolProvider.provider == provider_id_entity.provider_name),
                     )
                     .first()
@@ -572,95 +572,96 @@ class ToolManager:
         else:
             filters.append(typ)
 
-        if "builtin" in filters:
-            # get builtin providers
-            builtin_providers = cls.list_builtin_providers(tenant_id)
+        with db.session.no_autoflush:
+            if "builtin" in filters:
+                # get builtin providers
+                builtin_providers = cls.list_builtin_providers(tenant_id)
 
-            # get db builtin providers
-            db_builtin_providers: list[BuiltinToolProvider] = (
-                db.session.query(BuiltinToolProvider).filter(BuiltinToolProvider.tenant_id == tenant_id).all()
-            )
-
-            # rewrite db_builtin_providers
-            for db_provider in db_builtin_providers:
-                tool_provider_id = GenericProviderID(db_provider.provider)
-                db_provider.provider = tool_provider_id.to_string()
-
-            def find_db_builtin_provider(provider):
-                return next((x for x in db_builtin_providers if x.provider == provider), None)
-
-            # append builtin providers
-            for provider in builtin_providers:
-                # handle include, exclude
-                if is_filtered(
-                    include_set=cast(set[str], dify_config.POSITION_TOOL_INCLUDES_SET),
-                    exclude_set=cast(set[str], dify_config.POSITION_TOOL_EXCLUDES_SET),
-                    data=provider,
-                    name_func=lambda x: x.identity.name,
-                ):
-                    continue
-
-                user_provider = ToolTransformService.builtin_provider_to_user_provider(
-                    provider_controller=provider,
-                    db_provider=find_db_builtin_provider(provider.entity.identity.name),
-                    decrypt_credentials=False,
+                # get db builtin providers
+                db_builtin_providers: list[BuiltinToolProvider] = (
+                    db.session.query(BuiltinToolProvider).filter(BuiltinToolProvider.tenant_id == tenant_id).all()
                 )
 
-                if isinstance(provider, PluginToolProviderController):
-                    result_providers[f"plugin_provider.{user_provider.name}"] = user_provider
-                else:
-                    result_providers[f"builtin_provider.{user_provider.name}"] = user_provider
+                # rewrite db_builtin_providers
+                for db_provider in db_builtin_providers:
+                    tool_provider_id = str(ToolProviderID(db_provider.provider))
+                    db_provider.provider = tool_provider_id
 
-        # get db api providers
+                def find_db_builtin_provider(provider):
+                    return next((x for x in db_builtin_providers if x.provider == provider), None)
 
-        if "api" in filters:
-            db_api_providers: list[ApiToolProvider] = (
-                db.session.query(ApiToolProvider).filter(ApiToolProvider.tenant_id == tenant_id).all()
-            )
+                # append builtin providers
+                for provider in builtin_providers:
+                    # handle include, exclude
+                    if is_filtered(
+                        include_set=cast(set[str], dify_config.POSITION_TOOL_INCLUDES_SET),
+                        exclude_set=cast(set[str], dify_config.POSITION_TOOL_EXCLUDES_SET),
+                        data=provider,
+                        name_func=lambda x: x.identity.name,
+                    ):
+                        continue
 
-            api_provider_controllers: list[dict[str, Any]] = [
-                {"provider": provider, "controller": ToolTransformService.api_provider_to_controller(provider)}
-                for provider in db_api_providers
-            ]
-
-            # get labels
-            labels = ToolLabelManager.get_tools_labels([x["controller"] for x in api_provider_controllers])
-
-            for api_provider_controller in api_provider_controllers:
-                user_provider = ToolTransformService.api_provider_to_user_provider(
-                    provider_controller=api_provider_controller["controller"],
-                    db_provider=api_provider_controller["provider"],
-                    decrypt_credentials=False,
-                    labels=labels.get(api_provider_controller["controller"].provider_id, []),
-                )
-                result_providers[f"api_provider.{user_provider.name}"] = user_provider
-
-        if "workflow" in filters:
-            # get workflow providers
-            workflow_providers: list[WorkflowToolProvider] = (
-                db.session.query(WorkflowToolProvider).filter(WorkflowToolProvider.tenant_id == tenant_id).all()
-            )
-
-            workflow_provider_controllers: list[WorkflowToolProviderController] = []
-            for provider in workflow_providers:
-                try:
-                    workflow_provider_controllers.append(
-                        ToolTransformService.workflow_provider_to_controller(db_provider=provider)
+                    user_provider = ToolTransformService.builtin_provider_to_user_provider(
+                        provider_controller=provider,
+                        db_provider=find_db_builtin_provider(provider.entity.identity.name),
+                        decrypt_credentials=False,
                     )
-                except Exception:
-                    # app has been deleted
-                    pass
 
-            labels = ToolLabelManager.get_tools_labels(
-                [cast(ToolProviderController, controller) for controller in workflow_provider_controllers]
-            )
+                    if isinstance(provider, PluginToolProviderController):
+                        result_providers[f"plugin_provider.{user_provider.name}"] = user_provider
+                    else:
+                        result_providers[f"builtin_provider.{user_provider.name}"] = user_provider
 
-            for provider_controller in workflow_provider_controllers:
-                user_provider = ToolTransformService.workflow_provider_to_user_provider(
-                    provider_controller=provider_controller,
-                    labels=labels.get(provider_controller.provider_id, []),
+            # get db api providers
+
+            if "api" in filters:
+                db_api_providers: list[ApiToolProvider] = (
+                    db.session.query(ApiToolProvider).filter(ApiToolProvider.tenant_id == tenant_id).all()
                 )
-                result_providers[f"workflow_provider.{user_provider.name}"] = user_provider
+
+                api_provider_controllers: list[dict[str, Any]] = [
+                    {"provider": provider, "controller": ToolTransformService.api_provider_to_controller(provider)}
+                    for provider in db_api_providers
+                ]
+
+                # get labels
+                labels = ToolLabelManager.get_tools_labels([x["controller"] for x in api_provider_controllers])
+
+                for api_provider_controller in api_provider_controllers:
+                    user_provider = ToolTransformService.api_provider_to_user_provider(
+                        provider_controller=api_provider_controller["controller"],
+                        db_provider=api_provider_controller["provider"],
+                        decrypt_credentials=False,
+                        labels=labels.get(api_provider_controller["controller"].provider_id, []),
+                    )
+                    result_providers[f"api_provider.{user_provider.name}"] = user_provider
+
+            if "workflow" in filters:
+                # get workflow providers
+                workflow_providers: list[WorkflowToolProvider] = (
+                    db.session.query(WorkflowToolProvider).filter(WorkflowToolProvider.tenant_id == tenant_id).all()
+                )
+
+                workflow_provider_controllers: list[WorkflowToolProviderController] = []
+                for provider in workflow_providers:
+                    try:
+                        workflow_provider_controllers.append(
+                            ToolTransformService.workflow_provider_to_controller(db_provider=provider)
+                        )
+                    except Exception:
+                        # app has been deleted
+                        pass
+
+                labels = ToolLabelManager.get_tools_labels(
+                    [cast(ToolProviderController, controller) for controller in workflow_provider_controllers]
+                )
+
+                for provider_controller in workflow_provider_controllers:
+                    user_provider = ToolTransformService.workflow_provider_to_user_provider(
+                        provider_controller=provider_controller,
+                        labels=labels.get(provider_controller.provider_id, []),
+                    )
+                    result_providers[f"workflow_provider.{user_provider.name}"] = user_provider
 
         return BuiltinToolProviderSort.sort(list(result_providers.values()))
 

api/core/tools/utils/dataset_retriever/dataset_multi_retriever_tool.py

@@ -123,6 +123,7 @@ class DatasetMultiRetrieverTool(DatasetRetrieverBaseTool):
                             "segment_id": segment.id,
                             "retriever_from": self.retriever_from,
                             "score": document_score_list.get(segment.index_node_id, None),
+                            "doc_metadata": document.doc_metadata,
                         }
 
                         if self.retriever_from == "dev":

api/core/tools/utils/dataset_retriever/dataset_retriever_tool.py

@@ -3,11 +3,13 @@ from typing import Any
 from pydantic import BaseModel, Field
 
 from core.rag.datasource.retrieval_service import RetrievalService
+from core.rag.entities.context_entities import DocumentContext
 from core.rag.models.document import Document as RetrievalDocument
 from core.rag.retrieval.retrieval_methods import RetrievalMethod
 from core.tools.utils.dataset_retriever.dataset_retriever_base_tool import DatasetRetrieverBaseTool
 from extensions.ext_database import db
-from models.dataset import Dataset, Document, DocumentSegment
+from models.dataset import Dataset
+from models.dataset import Document as DatasetDocument
 from services.external_knowledge_service import ExternalDatasetService
 
 default_retrieval_model = {
@@ -54,7 +56,6 @@ class DatasetRetrieverTool(DatasetRetrieverBaseTool):
 
         if not dataset:
             return ""
-
         for hit_callback in self.hit_callbacks:
             hit_callback.on_query(query, dataset.id)
         if dataset.provider == "external":
@@ -125,7 +126,6 @@ class DatasetRetrieverTool(DatasetRetrieverBaseTool):
                     )
                 else:
                     documents = []
-
                 for hit_callback in self.hit_callbacks:
                     hit_callback.on_tool_end(documents)
                 document_score_list = {}
@@ -134,50 +134,47 @@ class DatasetRetrieverTool(DatasetRetrieverBaseTool):
                         if item.metadata is not None and item.metadata.get("score"):
                             document_score_list[item.metadata["doc_id"]] = item.metadata["score"]
                 document_context_list = []
-                index_node_ids = [document.metadata["doc_id"] for document in documents]
-                segments = DocumentSegment.query.filter(
-                    DocumentSegment.dataset_id == self.dataset_id,
-                    DocumentSegment.completed_at.isnot(None),
-                    DocumentSegment.status == "completed",
-                    DocumentSegment.enabled == True,
-                    DocumentSegment.index_node_id.in_(index_node_ids),
-                ).all()
-
-                if segments:
-                    index_node_id_to_position = {id: position for position, id in enumerate(index_node_ids)}
-                    sorted_segments = sorted(
-                        segments, key=lambda segment: index_node_id_to_position.get(segment.index_node_id, float("inf"))
-                    )
-                    for segment in sorted_segments:
+                records = RetrievalService.format_retrieval_documents(documents)
+                if records:
+                    for record in records:
+                        segment = record.segment
                         if segment.answer:
                             document_context_list.append(
-                                f"question:{segment.get_sign_content()} answer:{segment.answer}"
+                                DocumentContext(
+                                    content=f"question:{segment.get_sign_content()} answer:{segment.answer}",
+                                    score=record.score,
+                                )
                             )
                         else:
-                            document_context_list.append(segment.get_sign_content())
+                            document_context_list.append(
+                                DocumentContext(
+                                    content=segment.get_sign_content(),
+                                    score=record.score,
+                                )
+                            )
+                    retrieval_resource_list = []
                     if self.return_resource:
-                        context_list = []
-                        resource_number = 1
-                        for segment in sorted_segments:
-                            document_segment = Document.query.filter(
-                                Document.id == segment.document_id,
-                                Document.enabled == True,
-                                Document.archived == False,
+                        for record in records:
+                            segment = record.segment
+                            dataset = Dataset.query.filter_by(id=segment.dataset_id).first()
+                            document = DatasetDocument.query.filter(
+                                DatasetDocument.id == segment.document_id,
+                                DatasetDocument.enabled == True,
+                                DatasetDocument.archived == False,
                             ).first()
-                            if not document_segment:
-                                continue
-                            if dataset and document_segment:
+                            if dataset and document:
                                 source = {
-                                    "position": resource_number,
                                     "dataset_id": dataset.id,
                                     "dataset_name": dataset.name,
-                                    "document_id": document_segment.id,
-                                    "document_name": document_segment.name,
-                                    "data_source_type": document_segment.data_source_type,
+                                    "document_id": document.id,  # type: ignore
+                                    "document_name": document.name,  # type: ignore
+                                    "data_source_type": document.data_source_type,  # type: ignore
                                     "segment_id": segment.id,
                                     "retriever_from": self.retriever_from,
-                                    "score": document_score_list.get(segment.index_node_id, None),
+                                    "score": record.score or 0.0,
+                                    "doc_metadata": document.doc_metadat,  # type: ignore
                                 }
+
                                 if self.retriever_from == "dev":
                                     source["hit_count"] = segment.hit_count
                                     source["word_count"] = segment.word_count
@@ -187,10 +184,19 @@ class DatasetRetrieverTool(DatasetRetrieverBaseTool):
                                     source["content"] = f"question:{segment.content} \nanswer:{segment.answer}"
                                 else:
                                     source["content"] = segment.content
-                                context_list.append(source)
-                            resource_number += 1
+                                retrieval_resource_list.append(source)
 
-                        for hit_callback in self.hit_callbacks:
-                            hit_callback.return_retriever_resource_info(context_list)
-
-                return str("\n".join(document_context_list))
+            if self.return_resource and retrieval_resource_list:
+                retrieval_resource_list = sorted(
+                    retrieval_resource_list,
+                    key=lambda x: x.get("score") or 0.0,
+                    reverse=True,
+                )
+                for position, item in enumerate(retrieval_resource_list, start=1):  # type: ignore
+                    item["position"] = position  # type: ignore
+                for hit_callback in self.hit_callbacks:
+                    hit_callback.return_retriever_resource_info(retrieval_resource_list)
+            if document_context_list:
+                document_context_list = sorted(document_context_list, key=lambda x: x.score or 0.0, reverse=True)
+                return str("\n".join([document_context.content for document_context in document_context_list]))
+            return ""

api/core/workflow/graph_engine/graph_engine.py

@@ -665,7 +665,7 @@ class GraphEngine:
                                     retries += 1
                                     route_node_state.node_run_result = run_result
                                     yield NodeRunRetryEvent(
-                                        id=node_instance.id,
+                                        id=str(uuid.uuid4()),
                                         node_id=node_instance.node_id,
                                         node_type=node_instance.node_type,
                                         node_data=node_instance.node_data,
@@ -680,7 +680,7 @@ class GraphEngine:
                                         start_at=retry_start_at,
                                     )
                                     time.sleep(retry_interval)
-                                    continue
+                                    break
                             route_node_state.set_finished(run_result=run_result)
 
                             if run_result.status == WorkflowNodeExecutionStatus.FAILED:

api/core/workflow/nodes/agent/agent_node.py

@@ -8,12 +8,12 @@ from core.model_manager import ModelManager
 from core.model_runtime.entities.model_entities import ModelType
 from core.plugin.manager.exc import PluginDaemonClientSideError
 from core.plugin.manager.plugin import PluginInstallationManager
-from core.tools.entities.tool_entities import ToolProviderType
+from core.tools.entities.tool_entities import ToolParameter, ToolProviderType
 from core.tools.tool_manager import ToolManager
 from core.workflow.entities.node_entities import NodeRunResult
 from core.workflow.entities.variable_pool import VariablePool
 from core.workflow.enums import SystemVariableKey
-from core.workflow.nodes.agent.entities import AgentNodeData
+from core.workflow.nodes.agent.entities import AgentNodeData, ParamsAutoGenerated
 from core.workflow.nodes.base.entities import BaseNodeData
 from core.workflow.nodes.enums import NodeType
 from core.workflow.nodes.event.event import RunCompletedEvent
@@ -156,16 +156,38 @@ class AgentNode(ToolNode):
                 value = cast(list[dict[str, Any]], value)
                 value = [tool for tool in value if tool.get("enabled", False)]
 
+                for tool in value:
+                    if "schemas" in tool:
+                        tool.pop("schemas")
+                    parameters = tool.get("parameters", {})
+                    if all(isinstance(v, dict) for _, v in parameters.items()):
+                        params = {}
+                        for key, param in parameters.items():
+                            if param.get("auto", ParamsAutoGenerated.OPEN.value) == ParamsAutoGenerated.CLOSE.value:
+                                value_param = param.get("value", {})
+                                params[key] = value_param.get("value", "") if value_param is not None else None
+                            else:
+                                params[key] = None
+                        parameters = params
+                    tool["settings"] = {k: v.get("value", None) for k, v in tool.get("settings", {}).items()}
+                    tool["parameters"] = parameters
+
             if not for_log:
                 if parameter.type == "array[tools]":
                     value = cast(list[dict[str, Any]], value)
                     tool_value = []
                     for tool in value:
+                        provider_type = ToolProviderType(tool.get("type", ToolProviderType.BUILT_IN.value))
+                        setting_params = tool.get("settings", {})
+                        parameters = tool.get("parameters", {})
+                        manual_input_params = [key for key, value in parameters.items() if value is not None]
+
+                        parameters = {**parameters, **setting_params}
                         entity = AgentToolEntity(
                             provider_id=tool.get("provider_name", ""),
-                            provider_type=ToolProviderType.BUILT_IN,
+                            provider_type=provider_type,
                             tool_name=tool.get("tool_name", ""),
-                            tool_parameters=tool.get("parameters", {}),
+                            tool_parameters=parameters,
                             plugin_unique_identifier=tool.get("plugin_unique_identifier", None),
                         )
 
@@ -178,11 +200,26 @@ class AgentNode(ToolNode):
                             tool_runtime.entity.description.llm = (
                                 extra.get("descrption", "") or tool_runtime.entity.description.llm
                             )
-
+                        for tool_runtime_params in tool_runtime.entity.parameters:
+                            tool_runtime_params.form = (
+                                ToolParameter.ToolParameterForm.FORM
+                                if tool_runtime_params.name in manual_input_params
+                                else tool_runtime_params.form
+                            )
+                        manual_input_value = {}
+                        if tool_runtime.entity.parameters:
+                            manual_input_value = {
+                                key: value for key, value in parameters.items() if key in manual_input_params
+                            }
+                        runtime_parameters = {
+                            **tool_runtime.runtime.runtime_parameters,
+                            **manual_input_value,
+                        }
                         tool_value.append(
                             {
                                 **tool_runtime.entity.model_dump(mode="json"),
-                                "runtime_parameters": tool_runtime.runtime.runtime_parameters,
+                                "runtime_parameters": runtime_parameters,
+                                "provider_type": provider_type.value,
                             }
                         )
                     value = tool_value

api/core/workflow/nodes/agent/entities.py

@@ -1,3 +1,4 @@
+from enum import Enum
 from typing import Any, Literal, Union
 
 from pydantic import BaseModel
@@ -16,3 +17,8 @@ class AgentNodeData(BaseNodeData):
         type: Literal["mixed", "variable", "constant"]
 
     agent_parameters: dict[str, AgentInput]
+
+
+class ParamsAutoGenerated(Enum):
+    CLOSE = 0
+    OPEN = 1

api/core/workflow/nodes/document_extractor/node.py

@@ -107,8 +107,10 @@ def _extract_text_by_mime_type(*, file_content: bytes, mime_type: str) -> str:
             return _extract_text_from_plain_text(file_content)
         case "application/pdf":
             return _extract_text_from_pdf(file_content)
-        case "application/vnd.openxmlformats-officedocument.wordprocessingml.document" | "application/msword":
+        case "application/msword":
             return _extract_text_from_doc(file_content)
+        case "application/vnd.openxmlformats-officedocument.wordprocessingml.document":
+            return _extract_text_from_docx(file_content)
         case "text/csv":
             return _extract_text_from_csv(file_content)
         case "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet" | "application/vnd.ms-excel":
@@ -142,8 +144,10 @@ def _extract_text_by_file_extension(*, file_content: bytes, file_extension: str)
             return _extract_text_from_yaml(file_content)
         case ".pdf":
             return _extract_text_from_pdf(file_content)
-        case ".doc" | ".docx":
+        case ".doc":
             return _extract_text_from_doc(file_content)
+        case ".docx":
+            return _extract_text_from_docx(file_content)
         case ".csv":
             return _extract_text_from_csv(file_content)
         case ".xls" | ".xlsx":
@@ -203,7 +207,33 @@ def _extract_text_from_pdf(file_content: bytes) -> str:
 
 def _extract_text_from_doc(file_content: bytes) -> str:
     """
-    Extract text from a DOC/DOCX file.
+    Extract text from a DOC file.
+    """
+    from unstructured.partition.api import partition_via_api
+
+    if not (dify_config.UNSTRUCTURED_API_URL and dify_config.UNSTRUCTURED_API_KEY):
+        raise TextExtractionError("UNSTRUCTURED_API_URL and UNSTRUCTURED_API_KEY must be set")
+
+    try:
+        with tempfile.NamedTemporaryFile(suffix=".doc", delete=False) as temp_file:
+            temp_file.write(file_content)
+            temp_file.flush()
+            with open(temp_file.name, "rb") as file:
+                elements = partition_via_api(
+                    file=file,
+                    metadata_filename=temp_file.name,
+                    api_url=dify_config.UNSTRUCTURED_API_URL,
+                    api_key=dify_config.UNSTRUCTURED_API_KEY,
+                )
+            os.unlink(temp_file.name)
+        return "\n".join([getattr(element, "text", "") for element in elements])
+    except Exception as e:
+        raise TextExtractionError(f"Failed to extract text from DOC: {str(e)}") from e
+
+
+def _extract_text_from_docx(file_content: bytes) -> str:
+    """
+    Extract text from a DOCX file.
     For now support only paragraph and table add more if needed
     """
     try:
@@ -255,13 +285,13 @@ def _extract_text_from_doc(file_content: bytes) -> str:
 
                         text.append(markdown_table)
                 except Exception as e:
-                    logger.warning(f"Failed to extract table from DOC/DOCX: {e}")
+                    logger.warning(f"Failed to extract table from DOC: {e}")
                     continue
 
         return "\n".join(text)
 
     except Exception as e:
-        raise TextExtractionError(f"Failed to extract text from DOC/DOCX: {str(e)}") from e
+        raise TextExtractionError(f"Failed to extract text from DOCX: {str(e)}") from e
 
 
 def _download_file_content(file: File) -> bytes:
@@ -329,14 +359,29 @@ def _extract_text_from_excel(file_content: bytes) -> str:
 
 
 def _extract_text_from_ppt(file_content: bytes) -> str:
+    from unstructured.partition.api import partition_via_api
     from unstructured.partition.ppt import partition_ppt
 
     try:
-        with io.BytesIO(file_content) as file:
-            elements = partition_ppt(file=file)
+        if dify_config.UNSTRUCTURED_API_URL and dify_config.UNSTRUCTURED_API_KEY:
+            with tempfile.NamedTemporaryFile(suffix=".ppt", delete=False) as temp_file:
+                temp_file.write(file_content)
+                temp_file.flush()
+                with open(temp_file.name, "rb") as file:
+                    elements = partition_via_api(
+                        file=file,
+                        metadata_filename=temp_file.name,
+                        api_url=dify_config.UNSTRUCTURED_API_URL,
+                        api_key=dify_config.UNSTRUCTURED_API_KEY,
+                    )
+                os.unlink(temp_file.name)
+        else:
+            with io.BytesIO(file_content) as file:
+                elements = partition_ppt(file=file)
         return "\n".join([getattr(element, "text", "") for element in elements])
+
     except Exception as e:
-        raise TextExtractionError(f"Failed to extract text from PPT: {str(e)}") from e
+        raise TextExtractionError(f"Failed to extract text from PPTX: {str(e)}") from e
 
 
 def _extract_text_from_pptx(file_content: bytes) -> str:

api/core/workflow/nodes/end/end_node.py

@@ -1,6 +1,3 @@
-from collections.abc import Mapping, Sequence
-from typing import Any
-
 from core.workflow.entities.node_entities import NodeRunResult
 from core.workflow.nodes.base import BaseNode
 from core.workflow.nodes.end.entities import EndNodeData
@@ -30,20 +27,3 @@ class EndNode(BaseNode[EndNodeData]):
             inputs=outputs,
             outputs=outputs,
         )
-
-    @classmethod
-    def _extract_variable_selector_to_variable_mapping(
-        cls,
-        *,
-        graph_config: Mapping[str, Any],
-        node_id: str,
-        node_data: EndNodeData,
-    ) -> Mapping[str, Sequence[str]]:
-        """
-        Extract variable selector to variable mapping
-        :param graph_config: graph config
-        :param node_id: node id
-        :param node_data: node data
-        :return:
-        """
-        return {}

api/core/workflow/nodes/if_else/if_else_node.py

@@ -1,5 +1,4 @@
-from collections.abc import Mapping, Sequence
-from typing import Any, Literal
+from typing import Literal
 
 from typing_extensions import deprecated
 
@@ -88,23 +87,6 @@ class IfElseNode(BaseNode[IfElseNodeData]):
 
         return data
 
-    @classmethod
-    def _extract_variable_selector_to_variable_mapping(
-        cls,
-        *,
-        graph_config: Mapping[str, Any],
-        node_id: str,
-        node_data: IfElseNodeData,
-    ) -> Mapping[str, Sequence[str]]:
-        """
-        Extract variable selector to variable mapping
-        :param graph_config: graph config
-        :param node_id: node id
-        :param node_data: node data
-        :return:
-        """
-        return {}
-
 
 @deprecated("This function is deprecated. You should use the new cases structure.")
 def _should_not_use_old_function(

api/core/workflow/nodes/iteration/iteration_node.py

@@ -590,6 +590,7 @@ class IterationNode(BaseNode[IterationNodeData]):
         with flask_app.app_context():
             parallel_mode_run_id = uuid.uuid4().hex
             graph_engine_copy = graph_engine.create_copy()
+            graph_engine_copy.graph_runtime_state.total_tokens = 0
             variable_pool_copy = graph_engine_copy.graph_runtime_state.variable_pool
             variable_pool_copy.add([self.node_id, "index"], index)
             variable_pool_copy.add([self.node_id, "item"], item)

api/core/workflow/nodes/iteration/iteration_start_node.py

@@ -1,10 +1,7 @@
-from collections.abc import Mapping, Sequence
-from typing import Any
-
 from core.workflow.entities.node_entities import NodeRunResult
 from core.workflow.nodes.base import BaseNode
 from core.workflow.nodes.enums import NodeType
-from core.workflow.nodes.iteration.entities import IterationNodeData, IterationStartNodeData
+from core.workflow.nodes.iteration.entities import IterationStartNodeData
 from models.workflow import WorkflowNodeExecutionStatus
 
 
@@ -21,16 +18,3 @@ class IterationStartNode(BaseNode):
         Run the node.
         """
         return NodeRunResult(status=WorkflowNodeExecutionStatus.SUCCEEDED)
-
-    @classmethod
-    def _extract_variable_selector_to_variable_mapping(
-        cls, graph_config: Mapping[str, Any], node_id: str, node_data: IterationNodeData
-    ) -> Mapping[str, Sequence[str]]:
-        """
-        Extract variable selector to variable mapping
-        :param graph_config: graph config
-        :param node_id: node id
-        :param node_data: node data
-        :return:
-        """
-        return {}

api/core/workflow/nodes/knowledge_retrieval/knowledge_retrieval_node.py

@@ -240,6 +240,7 @@ class KnowledgeRetrievalNode(BaseNode[KnowledgeRetrievalNodeData]):
                                 "segment_word_count": segment.word_count,
                                 "segment_position": segment.position,
                                 "segment_index_node_hash": segment.index_node_hash,
+                                "doc_metadata": document.doc_metadata,
                             },
                             "title": document.name,
                         }

api/core/workflow/nodes/llm/node.py

@@ -1,6 +1,7 @@
 import json
 import logging
 from collections.abc import Generator, Mapping, Sequence
+from datetime import UTC, datetime
 from typing import TYPE_CHECKING, Any, Optional, cast
 
 from configs import dify_config
@@ -29,6 +30,7 @@ from core.model_runtime.entities.message_entities import (
 from core.model_runtime.entities.model_entities import ModelFeature, ModelPropertyKey, ModelType
 from core.model_runtime.model_providers.__base.large_language_model import LargeLanguageModel
 from core.model_runtime.utils.encoders import jsonable_encoder
+from core.plugin.entities.plugin import ModelProviderID
 from core.prompt.entities.advanced_prompt_entities import CompletionModelPromptTemplate, MemoryConfig
 from core.prompt.utils.prompt_message_util import PromptMessageUtil
 from core.variables import (
@@ -247,6 +249,24 @@ class LLMNode(BaseNode[LLMNodeData]):
 
     def _handle_invoke_result(self, invoke_result: LLMResult | Generator) -> Generator[NodeEvent, None, None]:
         if isinstance(invoke_result, LLMResult):
+            content = invoke_result.message.content
+            if content is None:
+                message_text = ""
+            elif isinstance(content, str):
+                message_text = content
+            elif isinstance(content, list):
+                # Assuming the list contains PromptMessageContent objects with a "data" attribute
+                message_text = "".join(
+                    item.data if hasattr(item, "data") and isinstance(item.data, str) else str(item) for item in content
+                )
+            else:
+                message_text = str(content)
+
+            yield ModelInvokeCompletedEvent(
+                text=message_text,
+                usage=invoke_result.usage,
+                finish_reason=None,
+            )
             return
 
         model = None
@@ -439,6 +459,7 @@ class LLMNode(BaseNode[LLMNodeData]):
                 "index_node_hash": metadata.get("segment_index_node_hash"),
                 "content": context_dict.get("content"),
                 "page": metadata.get("page"),
+                "doc_metadata": metadata.get("doc_metadata"),
             }
 
             return source
@@ -740,11 +761,17 @@ class LLMNode(BaseNode[LLMNodeData]):
         if used_quota is not None and system_configuration.current_quota_type is not None:
             db.session.query(Provider).filter(
                 Provider.tenant_id == tenant_id,
-                Provider.provider_name == model_instance.provider,
+                # TODO: Use provider name with prefix after the data migration.
+                Provider.provider_name == ModelProviderID(model_instance.provider).provider_name,
                 Provider.provider_type == ProviderType.SYSTEM.value,
                 Provider.quota_type == system_configuration.current_quota_type.value,
                 Provider.quota_limit > Provider.quota_used,
-            ).update({"quota_used": Provider.quota_used + used_quota})
+            ).update(
+                {
+                    "quota_used": Provider.quota_used + used_quota,
+                    "last_used": datetime.now(tz=UTC).replace(tzinfo=None),
+                }
+            )
             db.session.commit()
 
     @classmethod

api/core/workflow/nodes/start/start_node.py

@@ -1,6 +1,3 @@
-from collections.abc import Mapping, Sequence
-from typing import Any
-
 from core.workflow.constants import SYSTEM_VARIABLE_NODE_ID
 from core.workflow.entities.node_entities import NodeRunResult
 from core.workflow.nodes.base import BaseNode
@@ -23,13 +20,3 @@ class StartNode(BaseNode[StartNodeData]):
             node_inputs[SYSTEM_VARIABLE_NODE_ID + "." + var] = system_inputs[var]
 
         return NodeRunResult(status=WorkflowNodeExecutionStatus.SUCCEEDED, inputs=node_inputs, outputs=node_inputs)
-
-    @classmethod
-    def _extract_variable_selector_to_variable_mapping(
-        cls,
-        *,
-        graph_config: Mapping[str, Any],
-        node_id: str,
-        node_data: StartNodeData,
-    ) -> Mapping[str, Sequence[str]]:
-        return {}

api/core/workflow/nodes/variable_aggregator/variable_aggregator_node.py

@@ -1,6 +1,3 @@
-from collections.abc import Mapping, Sequence
-from typing import Any
-
 from core.workflow.entities.node_entities import NodeRunResult
 from core.workflow.nodes.base import BaseNode
 from core.workflow.nodes.enums import NodeType
@@ -36,16 +33,3 @@ class VariableAggregatorNode(BaseNode[VariableAssignerNodeData]):
                         break
 
         return NodeRunResult(status=WorkflowNodeExecutionStatus.SUCCEEDED, outputs=outputs, inputs=inputs)
-
-    @classmethod
-    def _extract_variable_selector_to_variable_mapping(
-        cls, *, graph_config: Mapping[str, Any], node_id: str, node_data: VariableAssignerNodeData
-    ) -> Mapping[str, Sequence[str]]:
-        """
-        Extract variable selector to variable mapping
-        :param graph_config: graph config
-        :param node_id: node id
-        :param node_data: node data
-        :return:
-        """
-        return {}

api/core/workflow/utils/condition/processor.py

@@ -64,6 +64,10 @@ class ConditionProcessor:
                     expected=expected_value,
                 )
             group_results.append(result)
+            # Implemented short-circuit evaluation for logical conditions
+            if (operator == "and" and not result) or (operator == "or" and result):
+                final_result = result
+                return input_conditions, group_results, final_result
 
         final_result = all(group_results) if operator == "and" else any(group_results)
         return input_conditions, group_results, final_result

api/events/event_handlers/deduct_quota_when_message_created.py

@@ -1,6 +1,9 @@
+from datetime import UTC, datetime
+
 from configs import dify_config
 from core.app.entities.app_invoke_entities import AgentChatAppGenerateEntity, ChatAppGenerateEntity
 from core.entities.provider_entities import QuotaUnit
+from core.plugin.entities.plugin import ModelProviderID
 from events.message_event import message_was_created
 from extensions.ext_database import db
 from models.provider import Provider, ProviderType
@@ -48,9 +51,15 @@ def handle(sender, **kwargs):
     if used_quota is not None and system_configuration.current_quota_type is not None:
         db.session.query(Provider).filter(
             Provider.tenant_id == application_generate_entity.app_config.tenant_id,
-            Provider.provider_name == model_config.provider,
+            # TODO: Use provider name with prefix after the data migration.
+            Provider.provider_name == ModelProviderID(model_config.provider).provider_name,
             Provider.provider_type == ProviderType.SYSTEM.value,
             Provider.quota_type == system_configuration.current_quota_type.value,
             Provider.quota_limit > Provider.quota_used,
-        ).update({"quota_used": Provider.quota_used + used_quota})
+        ).update(
+            {
+                "quota_used": Provider.quota_used + used_quota,
+                "last_used": datetime.now(tz=UTC).replace(tzinfo=None),
+            }
+        )
         db.session.commit()

api/extensions/ext_proxy_fix.py

@@ -6,4 +6,4 @@ def init_app(app: DifyApp):
     if dify_config.RESPECT_XFORWARD_HEADERS_ENABLED:
         from werkzeug.middleware.proxy_fix import ProxyFix
 
-        app.wsgi_app = ProxyFix(app.wsgi_app)  # type: ignore
+        app.wsgi_app = ProxyFix(app.wsgi_app, x_port=1)  # type: ignore

api/fields/app_fields.py

@@ -198,7 +198,7 @@ app_site_fields = {
     "use_icon_as_answer_icon": fields.Boolean,
 }
 
-leaked_dependency_fields = {"type": fields.String, "value": fields.Raw}
+leaked_dependency_fields = {"type": fields.String, "value": fields.Raw, "current_identifier": fields.String}
 
 app_import_fields = {
     "id": fields.String,

api/fields/conversation_fields.py

@@ -95,10 +95,6 @@ model_config_fields = {
     "agent_mode": fields.Raw,
 }
 
-simple_configs_fields = {
-    "prompt_template": fields.String,
-}
-
 simple_model_config_fields = {
     "model": fields.Raw(attribute="model_dict"),
     "pre_prompt": fields.String,
@@ -212,14 +208,3 @@ conversation_infinite_scroll_pagination_fields = {
     "has_more": fields.Boolean,
     "data": fields.List(fields.Nested(simple_conversation_fields)),
 }
-
-conversation_with_model_config_fields = {
-    **simple_conversation_fields,
-    "model_config": fields.Raw,
-}
-
-conversation_with_model_config_infinite_scroll_pagination_fields = {
-    "limit": fields.Integer,
-    "has_more": fields.Boolean,
-    "data": fields.List(fields.Nested(conversation_with_model_config_fields)),
-}

api/fields/hit_testing_fields.py

@@ -7,6 +7,7 @@ document_fields = {
     "data_source_type": fields.String,
     "name": fields.String,
     "doc_type": fields.String,
+    "doc_metadata": fields.Raw,
 }
 
 segment_fields = {

api/fields/message_fields.py

@@ -7,27 +7,6 @@ from .raws import FilesContainedField
 
 feedback_fields = {"rating": fields.String}
 
-retriever_resource_fields = {
-    "id": fields.String,
-    "message_id": fields.String,
-    "position": fields.Integer,
-    "dataset_id": fields.String,
-    "dataset_name": fields.String,
-    "document_id": fields.String,
-    "document_name": fields.String,
-    "data_source_type": fields.String,
-    "segment_id": fields.String,
-    "score": fields.Float,
-    "hit_count": fields.Integer,
-    "word_count": fields.Integer,
-    "segment_position": fields.Integer,
-    "index_node_hash": fields.String,
-    "content": fields.String,
-    "created_at": TimestampField,
-}
-
-feedback_fields = {"rating": fields.String}
-
 agent_thought_fields = {
     "id": fields.String,
     "chain_id": fields.String,

api/models/model.py

@@ -604,7 +604,7 @@ class InstalledApp(Base):
         return tenant
 
 
-class Conversation(Base):
+class Conversation(db.Model):  # type: ignore[name-defined]
     __tablename__ = "conversations"
     __table_args__ = (
         db.PrimaryKeyConstraint("id", name="conversation_pkey"),
@@ -839,7 +839,7 @@ class Conversation(Base):
         return self.override_model_configs is not None
 
 
-class Message(Base):
+class Message(db.Model):  # type: ignore[name-defined]
     __tablename__ = "messages"
     __table_args__ = (
         PrimaryKeyConstraint("id", name="message_pkey"),
@@ -1190,7 +1190,7 @@ class Message(Base):
         )
 
 
-class MessageFeedback(Base):
+class MessageFeedback(db.Model):  # type: ignore[name-defined]
     __tablename__ = "message_feedbacks"
     __table_args__ = (
         db.PrimaryKeyConstraint("id", name="message_feedback_pkey"),
@@ -1217,7 +1217,7 @@ class MessageFeedback(Base):
         return account
 
 
-class MessageFile(Base):
+class MessageFile(db.Model):  # type: ignore[name-defined]
     __tablename__ = "message_files"
     __table_args__ = (
         db.PrimaryKeyConstraint("id", name="message_file_pkey"),
@@ -1258,7 +1258,7 @@ class MessageFile(Base):
     created_at: Mapped[datetime] = db.Column(db.DateTime, nullable=False, server_default=func.current_timestamp())
 
 
-class MessageAnnotation(Base):
+class MessageAnnotation(db.Model):  # type: ignore[name-defined]
     __tablename__ = "message_annotations"
     __table_args__ = (
         db.PrimaryKeyConstraint("id", name="message_annotation_pkey"),
@@ -1289,7 +1289,7 @@ class MessageAnnotation(Base):
         return account
 
 
-class AppAnnotationHitHistory(Base):
+class AppAnnotationHitHistory(db.Model):  # type: ignore[name-defined]
     __tablename__ = "app_annotation_hit_histories"
     __table_args__ = (
         db.PrimaryKeyConstraint("id", name="app_annotation_hit_histories_pkey"),
@@ -1327,7 +1327,7 @@ class AppAnnotationHitHistory(Base):
         return account
 
 
-class AppAnnotationSetting(Base):
+class AppAnnotationSetting(db.Model):  # type: ignore[name-defined]
     __tablename__ = "app_annotation_settings"
     __table_args__ = (
         db.PrimaryKeyConstraint("id", name="app_annotation_settings_pkey"),

api/poetry.lock

@@ -644,15 +644,15 @@ files = [
 
 [[package]]
 name = "bce-python-sdk"
-version = "0.9.25"
+version = "0.9.29"
 description = "BCE SDK for python"
 optional = false
 python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,<4,>=2.7"
 groups = ["storage"]
 markers = "python_version == \"3.11\" or python_version >= \"3.12\""
 files = [
-    {file = "bce_python_sdk-0.9.25-py3-none-any.whl", hash = "sha256:cd1ab4c887e163adba6bfb3cd40465a365e5f4255705a015b0cdbe768e649877"},
-    {file = "bce_python_sdk-0.9.25.tar.gz", hash = "sha256:93a0623fbb1bf3a58b4f2d7bdbd799a3b342a538f0c72950c77168e431470e86"},
+    {file = "bce_python_sdk-0.9.29-py3-none-any.whl", hash = "sha256:6518dc0ada422acd1841eeabcb7f89cfc07e3bb1a4be3c75945cab953907b555"},
+    {file = "bce_python_sdk-0.9.29.tar.gz", hash = "sha256:326fbd50d57bf6d2fc21d58f589b069e0e84fc0a8733be9575c109293ab08cc4"},
 ]
 
 [package.dependencies]
@@ -748,19 +748,19 @@ files = [
 
 [[package]]
 name = "boto3"
-version = "1.36.12"
+version = "1.37.1"
 description = "The AWS SDK for Python"
 optional = false
 python-versions = ">=3.8"
 groups = ["main"]
 markers = "python_version == \"3.11\" or python_version >= \"3.12\""
 files = [
-    {file = "boto3-1.36.12-py3-none-any.whl", hash = "sha256:32cdf0967287f3ec25a9dc09df0d29cb86b8900c3e0546a63d672775d8127abf"},
-    {file = "boto3-1.36.12.tar.gz", hash = "sha256:287d84f49bba3255a17b374578127d42b6251e72f55914a62e0ad9ca78c0954b"},
+    {file = "boto3-1.37.1-py3-none-any.whl", hash = "sha256:4320441f904435a1b85e6ecb81793192e522c737cc9ed6566014e29f0a11cb22"},
+    {file = "boto3-1.37.1.tar.gz", hash = "sha256:96d18f7feb0c1fcb95f8837b74b6c8880e1b4e35ce5f8a8f8cb243a090c278ed"},
 ]
 
 [package.dependencies]
-botocore = ">=1.36.12,<1.37.0"
+botocore = ">=1.37.1,<1.38.0"
 jmespath = ">=0.7.1,<2.0.0"
 s3transfer = ">=0.11.0,<0.12.0"
 
@@ -769,15 +769,15 @@ crt = ["botocore[crt] (>=1.21.0,<2.0a0)"]
 
 [[package]]
 name = "botocore"
-version = "1.36.16"
+version = "1.37.1"
 description = "Low-level, data-driven core of boto 3."
 optional = false
 python-versions = ">=3.8"
 groups = ["main"]
 markers = "python_version == \"3.11\" or python_version >= \"3.12\""
 files = [
-    {file = "botocore-1.36.16-py3-none-any.whl", hash = "sha256:aca0348ccd730332082489b6817fdf89e1526049adcf6e9c8c11c96dd9f42c03"},
-    {file = "botocore-1.36.16.tar.gz", hash = "sha256:10c6aa386ba1a9a0faef6bb5dbfc58fc2563a3c6b95352e86a583cd5f14b11f3"},
+    {file = "botocore-1.37.1-py3-none-any.whl", hash = "sha256:c1db1bfc5d8c6b3b6d1ca6794f605294b4264e82a7e727b88e0fef9c2b9fbb9c"},
+    {file = "botocore-1.37.1.tar.gz", hash = "sha256:b194db8fb2a0ffba53568c364ae26166e7eec0445496b2ac86a6e142f3dd982f"},
 ]
 
 [package.dependencies]
@@ -1820,40 +1820,44 @@ files = [
 
 [[package]]
 name = "cryptography"
-version = "44.0.0"
+version = "44.0.1"
 description = "cryptography is a package which provides cryptographic recipes and primitives to Python developers."
 optional = false
 python-versions = "!=3.9.0,!=3.9.1,>=3.7"
 groups = ["main", "storage", "vdb"]
 markers = "python_version == \"3.11\" or python_version >= \"3.12\""
 files = [
-    {file = "cryptography-44.0.0-cp37-abi3-macosx_10_9_universal2.whl", hash = "sha256:84111ad4ff3f6253820e6d3e58be2cc2a00adb29335d4cacb5ab4d4d34f2a123"},
-    {file = "cryptography-44.0.0-cp37-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b15492a11f9e1b62ba9d73c210e2416724633167de94607ec6069ef724fad092"},
-    {file = "cryptography-44.0.0-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:831c3c4d0774e488fdc83a1923b49b9957d33287de923d58ebd3cec47a0ae43f"},
-    {file = "cryptography-44.0.0-cp37-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:761817a3377ef15ac23cd7834715081791d4ec77f9297ee694ca1ee9c2c7e5eb"},
-    {file = "cryptography-44.0.0-cp37-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:3c672a53c0fb4725a29c303be906d3c1fa99c32f58abe008a82705f9ee96f40b"},
-    {file = "cryptography-44.0.0-cp37-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:4ac4c9f37eba52cb6fbeaf5b59c152ea976726b865bd4cf87883a7e7006cc543"},
-    {file = "cryptography-44.0.0-cp37-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:ed3534eb1090483c96178fcb0f8893719d96d5274dfde98aa6add34614e97c8e"},
-    {file = "cryptography-44.0.0-cp37-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:f3f6fdfa89ee2d9d496e2c087cebef9d4fcbb0ad63c40e821b39f74bf48d9c5e"},
-    {file = "cryptography-44.0.0-cp37-abi3-win32.whl", hash = "sha256:eb33480f1bad5b78233b0ad3e1b0be21e8ef1da745d8d2aecbb20671658b9053"},
-    {file = "cryptography-44.0.0-cp37-abi3-win_amd64.whl", hash = "sha256:abc998e0c0eee3c8a1904221d3f67dcfa76422b23620173e28c11d3e626c21bd"},
-    {file = "cryptography-44.0.0-cp39-abi3-macosx_10_9_universal2.whl", hash = "sha256:660cb7312a08bc38be15b696462fa7cc7cd85c3ed9c576e81f4dc4d8b2b31591"},
-    {file = "cryptography-44.0.0-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1923cb251c04be85eec9fda837661c67c1049063305d6be5721643c22dd4e2b7"},
-    {file = "cryptography-44.0.0-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:404fdc66ee5f83a1388be54300ae978b2efd538018de18556dde92575e05defc"},
-    {file = "cryptography-44.0.0-cp39-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:c5eb858beed7835e5ad1faba59e865109f3e52b3783b9ac21e7e47dc5554e289"},
-    {file = "cryptography-44.0.0-cp39-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:f53c2c87e0fb4b0c00fa9571082a057e37690a8f12233306161c8f4b819960b7"},
-    {file = "cryptography-44.0.0-cp39-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:9e6fc8a08e116fb7c7dd1f040074c9d7b51d74a8ea40d4df2fc7aa08b76b9e6c"},
-    {file = "cryptography-44.0.0-cp39-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:d2436114e46b36d00f8b72ff57e598978b37399d2786fd39793c36c6d5cb1c64"},
-    {file = "cryptography-44.0.0-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:a01956ddfa0a6790d594f5b34fc1bfa6098aca434696a03cfdbe469b8ed79285"},
-    {file = "cryptography-44.0.0-cp39-abi3-win32.whl", hash = "sha256:eca27345e1214d1b9f9490d200f9db5a874479be914199194e746c893788d417"},
-    {file = "cryptography-44.0.0-cp39-abi3-win_amd64.whl", hash = "sha256:708ee5f1bafe76d041b53a4f95eb28cdeb8d18da17e597d46d7833ee59b97ede"},
-    {file = "cryptography-44.0.0-pp310-pypy310_pp73-macosx_10_9_x86_64.whl", hash = "sha256:37d76e6863da3774cd9db5b409a9ecfd2c71c981c38788d3fcfaf177f447b731"},
-    {file = "cryptography-44.0.0-pp310-pypy310_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:f677e1268c4e23420c3acade68fac427fffcb8d19d7df95ed7ad17cdef8404f4"},
-    {file = "cryptography-44.0.0-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:f5e7cb1e5e56ca0933b4873c0220a78b773b24d40d186b6738080b73d3d0a756"},
-    {file = "cryptography-44.0.0-pp310-pypy310_pp73-manylinux_2_34_aarch64.whl", hash = "sha256:8b3e6eae66cf54701ee7d9c83c30ac0a1e3fa17be486033000f2a73a12ab507c"},
-    {file = "cryptography-44.0.0-pp310-pypy310_pp73-manylinux_2_34_x86_64.whl", hash = "sha256:be4ce505894d15d5c5037167ffb7f0ae90b7be6f2a98f9a5c3442395501c32fa"},
-    {file = "cryptography-44.0.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:62901fb618f74d7d81bf408c8719e9ec14d863086efe4185afd07c352aee1d2c"},
-    {file = "cryptography-44.0.0.tar.gz", hash = "sha256:cd4e834f340b4293430701e772ec543b0fbe6c2dea510a5286fe0acabe153a02"},
+    {file = "cryptography-44.0.1-cp37-abi3-macosx_10_9_universal2.whl", hash = "sha256:bf688f615c29bfe9dfc44312ca470989279f0e94bb9f631f85e3459af8efc009"},
+    {file = "cryptography-44.0.1-cp37-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:dd7c7e2d71d908dc0f8d2027e1604102140d84b155e658c20e8ad1304317691f"},
+    {file = "cryptography-44.0.1-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:887143b9ff6bad2b7570da75a7fe8bbf5f65276365ac259a5d2d5147a73775f2"},
+    {file = "cryptography-44.0.1-cp37-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:322eb03ecc62784536bc173f1483e76747aafeb69c8728df48537eb431cd1911"},
+    {file = "cryptography-44.0.1-cp37-abi3-manylinux_2_28_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:21377472ca4ada2906bc313168c9dc7b1d7ca417b63c1c3011d0c74b7de9ae69"},
+    {file = "cryptography-44.0.1-cp37-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:df978682c1504fc93b3209de21aeabf2375cb1571d4e61907b3e7a2540e83026"},
+    {file = "cryptography-44.0.1-cp37-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:eb3889330f2a4a148abead555399ec9a32b13b7c8ba969b72d8e500eb7ef84cd"},
+    {file = "cryptography-44.0.1-cp37-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:8e6a85a93d0642bd774460a86513c5d9d80b5c002ca9693e63f6e540f1815ed0"},
+    {file = "cryptography-44.0.1-cp37-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:6f76fdd6fd048576a04c5210d53aa04ca34d2ed63336d4abd306d0cbe298fddf"},
+    {file = "cryptography-44.0.1-cp37-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:6c8acf6f3d1f47acb2248ec3ea261171a671f3d9428e34ad0357148d492c7864"},
+    {file = "cryptography-44.0.1-cp37-abi3-win32.whl", hash = "sha256:24979e9f2040c953a94bf3c6782e67795a4c260734e5264dceea65c8f4bae64a"},
+    {file = "cryptography-44.0.1-cp37-abi3-win_amd64.whl", hash = "sha256:fd0ee90072861e276b0ff08bd627abec29e32a53b2be44e41dbcdf87cbee2b00"},
+    {file = "cryptography-44.0.1-cp39-abi3-macosx_10_9_universal2.whl", hash = "sha256:a2d8a7045e1ab9b9f803f0d9531ead85f90c5f2859e653b61497228b18452008"},
+    {file = "cryptography-44.0.1-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b8272f257cf1cbd3f2e120f14c68bff2b6bdfcc157fafdee84a1b795efd72862"},
+    {file = "cryptography-44.0.1-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1e8d181e90a777b63f3f0caa836844a1182f1f265687fac2115fcf245f5fbec3"},
+    {file = "cryptography-44.0.1-cp39-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:436df4f203482f41aad60ed1813811ac4ab102765ecae7a2bbb1dbb66dcff5a7"},
+    {file = "cryptography-44.0.1-cp39-abi3-manylinux_2_28_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:4f422e8c6a28cf8b7f883eb790695d6d45b0c385a2583073f3cec434cc705e1a"},
+    {file = "cryptography-44.0.1-cp39-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:72198e2b5925155497a5a3e8c216c7fb3e64c16ccee11f0e7da272fa93b35c4c"},
+    {file = "cryptography-44.0.1-cp39-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:2a46a89ad3e6176223b632056f321bc7de36b9f9b93b2cc1cccf935a3849dc62"},
+    {file = "cryptography-44.0.1-cp39-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:53f23339864b617a3dfc2b0ac8d5c432625c80014c25caac9082314e9de56f41"},
+    {file = "cryptography-44.0.1-cp39-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:888fcc3fce0c888785a4876ca55f9f43787f4c5c1cc1e2e0da71ad481ff82c5b"},
+    {file = "cryptography-44.0.1-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:00918d859aa4e57db8299607086f793fa7813ae2ff5a4637e318a25ef82730f7"},
+    {file = "cryptography-44.0.1-cp39-abi3-win32.whl", hash = "sha256:9b336599e2cb77b1008cb2ac264b290803ec5e8e89d618a5e978ff5eb6f715d9"},
+    {file = "cryptography-44.0.1-cp39-abi3-win_amd64.whl", hash = "sha256:e403f7f766ded778ecdb790da786b418a9f2394f36e8cc8b796cc056ab05f44f"},
+    {file = "cryptography-44.0.1-pp310-pypy310_pp73-macosx_10_9_x86_64.whl", hash = "sha256:1f9a92144fa0c877117e9748c74501bea842f93d21ee00b0cf922846d9d0b183"},
+    {file = "cryptography-44.0.1-pp310-pypy310_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:610a83540765a8d8ce0f351ce42e26e53e1f774a6efb71eb1b41eb01d01c3d12"},
+    {file = "cryptography-44.0.1-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:5fed5cd6102bb4eb843e3315d2bf25fede494509bddadb81e03a859c1bc17b83"},
+    {file = "cryptography-44.0.1-pp310-pypy310_pp73-manylinux_2_34_aarch64.whl", hash = "sha256:f4daefc971c2d1f82f03097dc6f216744a6cd2ac0f04c68fb935ea2ba2a0d420"},
+    {file = "cryptography-44.0.1-pp310-pypy310_pp73-manylinux_2_34_x86_64.whl", hash = "sha256:94f99f2b943b354a5b6307d7e8d19f5c423a794462bde2bf310c770ba052b1c4"},
+    {file = "cryptography-44.0.1-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:d9c5b9f698a83c8bd71e0f4d3f9f839ef244798e5ffe96febfa9714717db7af7"},
+    {file = "cryptography-44.0.1.tar.gz", hash = "sha256:f51f5705ab27898afda1aaa430f34ad90dc117421057782022edf0600bec5f14"},
 ]
 
 [package.dependencies]
@@ -1866,7 +1870,7 @@ nox = ["nox (>=2024.4.15)", "nox[uv] (>=2024.3.2)"]
 pep8test = ["check-sdist", "click (>=8.0.1)", "mypy (>=1.4)", "ruff (>=0.3.6)"]
 sdist = ["build (>=1.0.0)"]
 ssh = ["bcrypt (>=3.1.5)"]
-test = ["certifi (>=2024)", "cryptography-vectors (==44.0.0)", "pretend (>=0.7)", "pytest (>=7.4.0)", "pytest-benchmark (>=4.0)", "pytest-cov (>=2.10.1)", "pytest-xdist (>=3.5.0)"]
+test = ["certifi (>=2024)", "cryptography-vectors (==44.0.1)", "pretend (>=0.7)", "pytest (>=7.4.0)", "pytest-benchmark (>=4.0)", "pytest-cov (>=2.10.1)", "pytest-xdist (>=3.5.0)"]
 test-randomorder = ["pytest-randomly"]
 
 [[package]]
@@ -2316,15 +2320,15 @@ sqlalchemy = ">=2.0.16"
 
 [[package]]
 name = "flatbuffers"
-version = "25.1.24"
+version = "25.2.10"
 description = "The FlatBuffers serialization format for Python"
 optional = false
 python-versions = "*"
 groups = ["vdb"]
 markers = "python_version == \"3.11\" or python_version >= \"3.12\""
 files = [
-    {file = "flatbuffers-25.1.24-py2.py3-none-any.whl", hash = "sha256:1abfebaf4083117225d0723087ea909896a34e3fec933beedb490d595ba24145"},
-    {file = "flatbuffers-25.1.24.tar.gz", hash = "sha256:e0f7b7d806c0abdf166275492663130af40c11f89445045fbef0aa3c9a8643ad"},
+    {file = "flatbuffers-25.2.10-py2.py3-none-any.whl", hash = "sha256:ebba5f4d5ea615af3f7fd70fc310636fbb2bbd1f566ac0a23d98dd412de50051"},
+    {file = "flatbuffers-25.2.10.tar.gz", hash = "sha256:97e451377a41262f8d9bd4295cc836133415cc03d8cb966410a4af92eb00d26e"},
 ]
 
 [[package]]
@@ -4166,15 +4170,15 @@ rapidfuzz = ">=3.9.0,<4.0.0"
 
 [[package]]
 name = "litellm"
-version = "1.60.8"
+version = "1.61.6"
 description = "Library to easily interface with LLM API providers"
 optional = false
 python-versions = "!=2.7.*,!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,!=3.7.*,>=3.8"
 groups = ["main"]
 markers = "python_version == \"3.11\" or python_version >= \"3.12\""
 files = [
-    {file = "litellm-1.60.8-py3-none-any.whl", hash = "sha256:260bdcc9749c769f1a84dc927abe7c91f6294a97da05abc6b513c5dd2dcf17a1"},
-    {file = "litellm-1.60.8.tar.gz", hash = "sha256:4a0aca9bd226d727ca4a41aaf8722f825fc10cf33f37a177a3cceb4ee2c442d8"},
+    {file = "litellm-1.61.6-py3-none-any.whl", hash = "sha256:eef4c4a84a2c93de4c6d5a05a785f9b0cc61f63bafb3b3dc83d977db649e1b13"},
+    {file = "litellm-1.61.6.tar.gz", hash = "sha256:2c613823f86ce2aa7956e2458857ab6aa62258dc7da9816bfdac90735be270be"},
 ]
 
 [package.dependencies]
@@ -4228,159 +4232,159 @@ files = [
 
 [[package]]
 name = "lxml"
-version = "5.3.0"
+version = "5.3.1"
 description = "Powerful and Pythonic XML processing library combining libxml2/libxslt with the ElementTree API."
 optional = false
 python-versions = ">=3.6"
 groups = ["main"]
 markers = "python_version == \"3.11\" or python_version >= \"3.12\""
 files = [
-    {file = "lxml-5.3.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:dd36439be765e2dde7660212b5275641edbc813e7b24668831a5c8ac91180656"},
-    {file = "lxml-5.3.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:ae5fe5c4b525aa82b8076c1a59d642c17b6e8739ecf852522c6321852178119d"},
-    {file = "lxml-5.3.0-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:501d0d7e26b4d261fca8132854d845e4988097611ba2531408ec91cf3fd9d20a"},
-    {file = "lxml-5.3.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fb66442c2546446944437df74379e9cf9e9db353e61301d1a0e26482f43f0dd8"},
-    {file = "lxml-5.3.0-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:9e41506fec7a7f9405b14aa2d5c8abbb4dbbd09d88f9496958b6d00cb4d45330"},
-    {file = "lxml-5.3.0-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f7d4a670107d75dfe5ad080bed6c341d18c4442f9378c9f58e5851e86eb79965"},
-    {file = "lxml-5.3.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:41ce1f1e2c7755abfc7e759dc34d7d05fd221723ff822947132dc934d122fe22"},
-    {file = "lxml-5.3.0-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:44264ecae91b30e5633013fb66f6ddd05c006d3e0e884f75ce0b4755b3e3847b"},
-    {file = "lxml-5.3.0-cp310-cp310-manylinux_2_28_ppc64le.whl", hash = "sha256:3c174dc350d3ec52deb77f2faf05c439331d6ed5e702fc247ccb4e6b62d884b7"},
-    {file = "lxml-5.3.0-cp310-cp310-manylinux_2_28_s390x.whl", hash = "sha256:2dfab5fa6a28a0b60a20638dc48e6343c02ea9933e3279ccb132f555a62323d8"},
-    {file = "lxml-5.3.0-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:b1c8c20847b9f34e98080da785bb2336ea982e7f913eed5809e5a3c872900f32"},
-    {file = "lxml-5.3.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:2c86bf781b12ba417f64f3422cfc302523ac9cd1d8ae8c0f92a1c66e56ef2e86"},
-    {file = "lxml-5.3.0-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:c162b216070f280fa7da844531169be0baf9ccb17263cf5a8bf876fcd3117fa5"},
-    {file = "lxml-5.3.0-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:36aef61a1678cb778097b4a6eeae96a69875d51d1e8f4d4b491ab3cfb54b5a03"},
-    {file = "lxml-5.3.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:f65e5120863c2b266dbcc927b306c5b78e502c71edf3295dfcb9501ec96e5fc7"},
-    {file = "lxml-5.3.0-cp310-cp310-win32.whl", hash = "sha256:ef0c1fe22171dd7c7c27147f2e9c3e86f8bdf473fed75f16b0c2e84a5030ce80"},
-    {file = "lxml-5.3.0-cp310-cp310-win_amd64.whl", hash = "sha256:052d99051e77a4f3e8482c65014cf6372e61b0a6f4fe9edb98503bb5364cfee3"},
-    {file = "lxml-5.3.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:74bcb423462233bc5d6066e4e98b0264e7c1bed7541fff2f4e34fe6b21563c8b"},
-    {file = "lxml-5.3.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:a3d819eb6f9b8677f57f9664265d0a10dd6551d227afb4af2b9cd7bdc2ccbf18"},
-    {file = "lxml-5.3.0-cp311-cp311-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:5b8f5db71b28b8c404956ddf79575ea77aa8b1538e8b2ef9ec877945b3f46442"},
-    {file = "lxml-5.3.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2c3406b63232fc7e9b8783ab0b765d7c59e7c59ff96759d8ef9632fca27c7ee4"},
-    {file = "lxml-5.3.0-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:2ecdd78ab768f844c7a1d4a03595038c166b609f6395e25af9b0f3f26ae1230f"},
-    {file = "lxml-5.3.0-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:168f2dfcfdedf611eb285efac1516c8454c8c99caf271dccda8943576b67552e"},
-    {file = "lxml-5.3.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:aa617107a410245b8660028a7483b68e7914304a6d4882b5ff3d2d3eb5948d8c"},
-    {file = "lxml-5.3.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:69959bd3167b993e6e710b99051265654133a98f20cec1d9b493b931942e9c16"},
-    {file = "lxml-5.3.0-cp311-cp311-manylinux_2_28_ppc64le.whl", hash = "sha256:bd96517ef76c8654446fc3db9242d019a1bb5fe8b751ba414765d59f99210b79"},
-    {file = "lxml-5.3.0-cp311-cp311-manylinux_2_28_s390x.whl", hash = "sha256:ab6dd83b970dc97c2d10bc71aa925b84788c7c05de30241b9e96f9b6d9ea3080"},
-    {file = "lxml-5.3.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:eec1bb8cdbba2925bedc887bc0609a80e599c75b12d87ae42ac23fd199445654"},
-    {file = "lxml-5.3.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:6a7095eeec6f89111d03dabfe5883a1fd54da319c94e0fb104ee8f23616b572d"},
-    {file = "lxml-5.3.0-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:6f651ebd0b21ec65dfca93aa629610a0dbc13dbc13554f19b0113da2e61a4763"},
-    {file = "lxml-5.3.0-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:f422a209d2455c56849442ae42f25dbaaba1c6c3f501d58761c619c7836642ec"},
-    {file = "lxml-5.3.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:62f7fdb0d1ed2065451f086519865b4c90aa19aed51081979ecd05a21eb4d1be"},
-    {file = "lxml-5.3.0-cp311-cp311-win32.whl", hash = "sha256:c6379f35350b655fd817cd0d6cbeef7f265f3ae5fedb1caae2eb442bbeae9ab9"},
-    {file = "lxml-5.3.0-cp311-cp311-win_amd64.whl", hash = "sha256:9c52100e2c2dbb0649b90467935c4b0de5528833c76a35ea1a2691ec9f1ee7a1"},
-    {file = "lxml-5.3.0-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:e99f5507401436fdcc85036a2e7dc2e28d962550afe1cbfc07c40e454256a859"},
-    {file = "lxml-5.3.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:384aacddf2e5813a36495233b64cb96b1949da72bef933918ba5c84e06af8f0e"},
-    {file = "lxml-5.3.0-cp312-cp312-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:874a216bf6afaf97c263b56371434e47e2c652d215788396f60477540298218f"},
-    {file = "lxml-5.3.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:65ab5685d56914b9a2a34d67dd5488b83213d680b0c5d10b47f81da5a16b0b0e"},
-    {file = "lxml-5.3.0-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:aac0bbd3e8dd2d9c45ceb82249e8bdd3ac99131a32b4d35c8af3cc9db1657179"},
-    {file = "lxml-5.3.0-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b369d3db3c22ed14c75ccd5af429086f166a19627e84a8fdade3f8f31426e52a"},
-    {file = "lxml-5.3.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c24037349665434f375645fa9d1f5304800cec574d0310f618490c871fd902b3"},
-    {file = "lxml-5.3.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:62d172f358f33a26d6b41b28c170c63886742f5b6772a42b59b4f0fa10526cb1"},
-    {file = "lxml-5.3.0-cp312-cp312-manylinux_2_28_ppc64le.whl", hash = "sha256:c1f794c02903c2824fccce5b20c339a1a14b114e83b306ff11b597c5f71a1c8d"},
-    {file = "lxml-5.3.0-cp312-cp312-manylinux_2_28_s390x.whl", hash = "sha256:5d6a6972b93c426ace71e0be9a6f4b2cfae9b1baed2eed2006076a746692288c"},
-    {file = "lxml-5.3.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:3879cc6ce938ff4eb4900d901ed63555c778731a96365e53fadb36437a131a99"},
-    {file = "lxml-5.3.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:74068c601baff6ff021c70f0935b0c7bc528baa8ea210c202e03757c68c5a4ff"},
-    {file = "lxml-5.3.0-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:ecd4ad8453ac17bc7ba3868371bffb46f628161ad0eefbd0a855d2c8c32dd81a"},
-    {file = "lxml-5.3.0-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:7e2f58095acc211eb9d8b5771bf04df9ff37d6b87618d1cbf85f92399c98dae8"},
-    {file = "lxml-5.3.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:e63601ad5cd8f860aa99d109889b5ac34de571c7ee902d6812d5d9ddcc77fa7d"},
-    {file = "lxml-5.3.0-cp312-cp312-win32.whl", hash = "sha256:17e8d968d04a37c50ad9c456a286b525d78c4a1c15dd53aa46c1d8e06bf6fa30"},
-    {file = "lxml-5.3.0-cp312-cp312-win_amd64.whl", hash = "sha256:c1a69e58a6bb2de65902051d57fde951febad631a20a64572677a1052690482f"},
-    {file = "lxml-5.3.0-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:8c72e9563347c7395910de6a3100a4840a75a6f60e05af5e58566868d5eb2d6a"},
-    {file = "lxml-5.3.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:e92ce66cd919d18d14b3856906a61d3f6b6a8500e0794142338da644260595cd"},
-    {file = "lxml-5.3.0-cp313-cp313-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1d04f064bebdfef9240478f7a779e8c5dc32b8b7b0b2fc6a62e39b928d428e51"},
-    {file = "lxml-5.3.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5c2fb570d7823c2bbaf8b419ba6e5662137f8166e364a8b2b91051a1fb40ab8b"},
-    {file = "lxml-5.3.0-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:0c120f43553ec759f8de1fee2f4794452b0946773299d44c36bfe18e83caf002"},
-    {file = "lxml-5.3.0-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:562e7494778a69086f0312ec9689f6b6ac1c6b65670ed7d0267e49f57ffa08c4"},
-    {file = "lxml-5.3.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:423b121f7e6fa514ba0c7918e56955a1d4470ed35faa03e3d9f0e3baa4c7e492"},
-    {file = "lxml-5.3.0-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:c00f323cc00576df6165cc9d21a4c21285fa6b9989c5c39830c3903dc4303ef3"},
-    {file = "lxml-5.3.0-cp313-cp313-manylinux_2_28_ppc64le.whl", hash = "sha256:1fdc9fae8dd4c763e8a31e7630afef517eab9f5d5d31a278df087f307bf601f4"},
-    {file = "lxml-5.3.0-cp313-cp313-manylinux_2_28_s390x.whl", hash = "sha256:658f2aa69d31e09699705949b5fc4719cbecbd4a97f9656a232e7d6c7be1a367"},
-    {file = "lxml-5.3.0-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:1473427aff3d66a3fa2199004c3e601e6c4500ab86696edffdbc84954c72d832"},
-    {file = "lxml-5.3.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:a87de7dd873bf9a792bf1e58b1c3887b9264036629a5bf2d2e6579fe8e73edff"},
-    {file = "lxml-5.3.0-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:0d7b36afa46c97875303a94e8f3ad932bf78bace9e18e603f2085b652422edcd"},
-    {file = "lxml-5.3.0-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:cf120cce539453ae086eacc0130a324e7026113510efa83ab42ef3fcfccac7fb"},
-    {file = "lxml-5.3.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:df5c7333167b9674aa8ae1d4008fa4bc17a313cc490b2cca27838bbdcc6bb15b"},
-    {file = "lxml-5.3.0-cp313-cp313-win32.whl", hash = "sha256:c802e1c2ed9f0c06a65bc4ed0189d000ada8049312cfeab6ca635e39c9608957"},
-    {file = "lxml-5.3.0-cp313-cp313-win_amd64.whl", hash = "sha256:406246b96d552e0503e17a1006fd27edac678b3fcc9f1be71a2f94b4ff61528d"},
-    {file = "lxml-5.3.0-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:8f0de2d390af441fe8b2c12626d103540b5d850d585b18fcada58d972b74a74e"},
-    {file = "lxml-5.3.0-cp36-cp36m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1afe0a8c353746e610bd9031a630a95bcfb1a720684c3f2b36c4710a0a96528f"},
-    {file = "lxml-5.3.0-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:56b9861a71575f5795bde89256e7467ece3d339c9b43141dbdd54544566b3b94"},
-    {file = "lxml-5.3.0-cp36-cp36m-manylinux_2_28_x86_64.whl", hash = "sha256:9fb81d2824dff4f2e297a276297e9031f46d2682cafc484f49de182aa5e5df99"},
-    {file = "lxml-5.3.0-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:2c226a06ecb8cdef28845ae976da407917542c5e6e75dcac7cc33eb04aaeb237"},
-    {file = "lxml-5.3.0-cp36-cp36m-musllinux_1_2_x86_64.whl", hash = "sha256:7d3d1ca42870cdb6d0d29939630dbe48fa511c203724820fc0fd507b2fb46577"},
-    {file = "lxml-5.3.0-cp36-cp36m-win32.whl", hash = "sha256:094cb601ba9f55296774c2d57ad68730daa0b13dc260e1f941b4d13678239e70"},
-    {file = "lxml-5.3.0-cp36-cp36m-win_amd64.whl", hash = "sha256:eafa2c8658f4e560b098fe9fc54539f86528651f61849b22111a9b107d18910c"},
-    {file = "lxml-5.3.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:cb83f8a875b3d9b458cada4f880fa498646874ba4011dc974e071a0a84a1b033"},
-    {file = "lxml-5.3.0-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:25f1b69d41656b05885aa185f5fdf822cb01a586d1b32739633679699f220391"},
-    {file = "lxml-5.3.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:23e0553b8055600b3bf4a00b255ec5c92e1e4aebf8c2c09334f8368e8bd174d6"},
-    {file = "lxml-5.3.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9ada35dd21dc6c039259596b358caab6b13f4db4d4a7f8665764d616daf9cc1d"},
-    {file = "lxml-5.3.0-cp37-cp37m-manylinux_2_28_aarch64.whl", hash = "sha256:81b4e48da4c69313192d8c8d4311e5d818b8be1afe68ee20f6385d0e96fc9512"},
-    {file = "lxml-5.3.0-cp37-cp37m-manylinux_2_28_x86_64.whl", hash = "sha256:2bc9fd5ca4729af796f9f59cd8ff160fe06a474da40aca03fcc79655ddee1a8b"},
-    {file = "lxml-5.3.0-cp37-cp37m-musllinux_1_2_aarch64.whl", hash = "sha256:07da23d7ee08577760f0a71d67a861019103e4812c87e2fab26b039054594cc5"},
-    {file = "lxml-5.3.0-cp37-cp37m-musllinux_1_2_x86_64.whl", hash = "sha256:ea2e2f6f801696ad7de8aec061044d6c8c0dd4037608c7cab38a9a4d316bfb11"},
-    {file = "lxml-5.3.0-cp37-cp37m-win32.whl", hash = "sha256:5c54afdcbb0182d06836cc3d1be921e540be3ebdf8b8a51ee3ef987537455f84"},
-    {file = "lxml-5.3.0-cp37-cp37m-win_amd64.whl", hash = "sha256:f2901429da1e645ce548bf9171784c0f74f0718c3f6150ce166be39e4dd66c3e"},
-    {file = "lxml-5.3.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:c56a1d43b2f9ee4786e4658c7903f05da35b923fb53c11025712562d5cc02753"},
-    {file = "lxml-5.3.0-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6ee8c39582d2652dcd516d1b879451500f8db3fe3607ce45d7c5957ab2596040"},
-    {file = "lxml-5.3.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0fdf3a3059611f7585a78ee10399a15566356116a4288380921a4b598d807a22"},
-    {file = "lxml-5.3.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:146173654d79eb1fc97498b4280c1d3e1e5d58c398fa530905c9ea50ea849b22"},
-    {file = "lxml-5.3.0-cp38-cp38-manylinux_2_28_aarch64.whl", hash = "sha256:0a7056921edbdd7560746f4221dca89bb7a3fe457d3d74267995253f46343f15"},
-    {file = "lxml-5.3.0-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:9e4b47ac0f5e749cfc618efdf4726269441014ae1d5583e047b452a32e221920"},
-    {file = "lxml-5.3.0-cp38-cp38-musllinux_1_2_aarch64.whl", hash = "sha256:f914c03e6a31deb632e2daa881fe198461f4d06e57ac3d0e05bbcab8eae01945"},
-    {file = "lxml-5.3.0-cp38-cp38-musllinux_1_2_x86_64.whl", hash = "sha256:213261f168c5e1d9b7535a67e68b1f59f92398dd17a56d934550837143f79c42"},
-    {file = "lxml-5.3.0-cp38-cp38-win32.whl", hash = "sha256:218c1b2e17a710e363855594230f44060e2025b05c80d1f0661258142b2add2e"},
-    {file = "lxml-5.3.0-cp38-cp38-win_amd64.whl", hash = "sha256:315f9542011b2c4e1d280e4a20ddcca1761993dda3afc7a73b01235f8641e903"},
-    {file = "lxml-5.3.0-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:1ffc23010330c2ab67fac02781df60998ca8fe759e8efde6f8b756a20599c5de"},
-    {file = "lxml-5.3.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:2b3778cb38212f52fac9fe913017deea2fdf4eb1a4f8e4cfc6b009a13a6d3fcc"},
-    {file = "lxml-5.3.0-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4b0c7a688944891086ba192e21c5229dea54382f4836a209ff8d0a660fac06be"},
-    {file = "lxml-5.3.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:747a3d3e98e24597981ca0be0fd922aebd471fa99d0043a3842d00cdcad7ad6a"},
-    {file = "lxml-5.3.0-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:86a6b24b19eaebc448dc56b87c4865527855145d851f9fc3891673ff97950540"},
-    {file = "lxml-5.3.0-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b11a5d918a6216e521c715b02749240fb07ae5a1fefd4b7bf12f833bc8b4fe70"},
-    {file = "lxml-5.3.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:68b87753c784d6acb8a25b05cb526c3406913c9d988d51f80adecc2b0775d6aa"},
-    {file = "lxml-5.3.0-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:109fa6fede314cc50eed29e6e56c540075e63d922455346f11e4d7a036d2b8cf"},
-    {file = "lxml-5.3.0-cp39-cp39-manylinux_2_28_ppc64le.whl", hash = "sha256:02ced472497b8362c8e902ade23e3300479f4f43e45f4105c85ef43b8db85229"},
-    {file = "lxml-5.3.0-cp39-cp39-manylinux_2_28_s390x.whl", hash = "sha256:6b038cc86b285e4f9fea2ba5ee76e89f21ed1ea898e287dc277a25884f3a7dfe"},
-    {file = "lxml-5.3.0-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:7437237c6a66b7ca341e868cda48be24b8701862757426852c9b3186de1da8a2"},
-    {file = "lxml-5.3.0-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:7f41026c1d64043a36fda21d64c5026762d53a77043e73e94b71f0521939cc71"},
-    {file = "lxml-5.3.0-cp39-cp39-musllinux_1_2_ppc64le.whl", hash = "sha256:482c2f67761868f0108b1743098640fbb2a28a8e15bf3f47ada9fa59d9fe08c3"},
-    {file = "lxml-5.3.0-cp39-cp39-musllinux_1_2_s390x.whl", hash = "sha256:1483fd3358963cc5c1c9b122c80606a3a79ee0875bcac0204149fa09d6ff2727"},
-    {file = "lxml-5.3.0-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:2dec2d1130a9cda5b904696cec33b2cfb451304ba9081eeda7f90f724097300a"},
-    {file = "lxml-5.3.0-cp39-cp39-win32.whl", hash = "sha256:a0eabd0a81625049c5df745209dc7fcef6e2aea7793e5f003ba363610aa0a3ff"},
-    {file = "lxml-5.3.0-cp39-cp39-win_amd64.whl", hash = "sha256:89e043f1d9d341c52bf2af6d02e6adde62e0a46e6755d5eb60dc6e4f0b8aeca2"},
-    {file = "lxml-5.3.0-pp310-pypy310_pp73-macosx_10_15_x86_64.whl", hash = "sha256:7b1cd427cb0d5f7393c31b7496419da594fe600e6fdc4b105a54f82405e6626c"},
-    {file = "lxml-5.3.0-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:51806cfe0279e06ed8500ce19479d757db42a30fd509940b1701be9c86a5ff9a"},
-    {file = "lxml-5.3.0-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ee70d08fd60c9565ba8190f41a46a54096afa0eeb8f76bd66f2c25d3b1b83005"},
-    {file = "lxml-5.3.0-pp310-pypy310_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:8dc2c0395bea8254d8daebc76dcf8eb3a95ec2a46fa6fae5eaccee366bfe02ce"},
-    {file = "lxml-5.3.0-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:6ba0d3dcac281aad8a0e5b14c7ed6f9fa89c8612b47939fc94f80b16e2e9bc83"},
-    {file = "lxml-5.3.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:6e91cf736959057f7aac7adfc83481e03615a8e8dd5758aa1d95ea69e8931dba"},
-    {file = "lxml-5.3.0-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:94d6c3782907b5e40e21cadf94b13b0842ac421192f26b84c45f13f3c9d5dc27"},
-    {file = "lxml-5.3.0-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c300306673aa0f3ed5ed9372b21867690a17dba38c68c44b287437c362ce486b"},
-    {file = "lxml-5.3.0-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:78d9b952e07aed35fe2e1a7ad26e929595412db48535921c5013edc8aa4a35ce"},
-    {file = "lxml-5.3.0-pp37-pypy37_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:01220dca0d066d1349bd6a1726856a78f7929f3878f7e2ee83c296c69495309e"},
-    {file = "lxml-5.3.0-pp37-pypy37_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:2d9b8d9177afaef80c53c0a9e30fa252ff3036fb1c6494d427c066a4ce6a282f"},
-    {file = "lxml-5.3.0-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:20094fc3f21ea0a8669dc4c61ed7fa8263bd37d97d93b90f28fc613371e7a875"},
-    {file = "lxml-5.3.0-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:ace2c2326a319a0bb8a8b0e5b570c764962e95818de9f259ce814ee666603f19"},
-    {file = "lxml-5.3.0-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:92e67a0be1639c251d21e35fe74df6bcc40cba445c2cda7c4a967656733249e2"},
-    {file = "lxml-5.3.0-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dd5350b55f9fecddc51385463a4f67a5da829bc741e38cf689f38ec9023f54ab"},
-    {file = "lxml-5.3.0-pp38-pypy38_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:4c1fefd7e3d00921c44dc9ca80a775af49698bbfd92ea84498e56acffd4c5469"},
-    {file = "lxml-5.3.0-pp38-pypy38_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:71a8dd38fbd2f2319136d4ae855a7078c69c9a38ae06e0c17c73fd70fc6caad8"},
-    {file = "lxml-5.3.0-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:97acf1e1fd66ab53dacd2c35b319d7e548380c2e9e8c54525c6e76d21b1ae3b1"},
-    {file = "lxml-5.3.0-pp39-pypy39_pp73-macosx_10_15_x86_64.whl", hash = "sha256:68934b242c51eb02907c5b81d138cb977b2129a0a75a8f8b60b01cb8586c7b21"},
-    {file = "lxml-5.3.0-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b710bc2b8292966b23a6a0121f7a6c51d45d2347edcc75f016ac123b8054d3f2"},
-    {file = "lxml-5.3.0-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:18feb4b93302091b1541221196a2155aa296c363fd233814fa11e181adebc52f"},
-    {file = "lxml-5.3.0-pp39-pypy39_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:3eb44520c4724c2e1a57c0af33a379eee41792595023f367ba3952a2d96c2aab"},
-    {file = "lxml-5.3.0-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:609251a0ca4770e5a8768ff902aa02bf636339c5a93f9349b48eb1f606f7f3e9"},
-    {file = "lxml-5.3.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:516f491c834eb320d6c843156440fe7fc0d50b33e44387fcec5b02f0bc118a4c"},
-    {file = "lxml-5.3.0.tar.gz", hash = "sha256:4e109ca30d1edec1ac60cdbe341905dc3b8f55b16855e03a54aaf59e51ec8c6f"},
+    {file = "lxml-5.3.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:a4058f16cee694577f7e4dd410263cd0ef75644b43802a689c2b3c2a7e69453b"},
+    {file = "lxml-5.3.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:364de8f57d6eda0c16dcfb999af902da31396949efa0e583e12675d09709881b"},
+    {file = "lxml-5.3.1-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:528f3a0498a8edc69af0559bdcf8a9f5a8bf7c00051a6ef3141fdcf27017bbf5"},
+    {file = "lxml-5.3.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:db4743e30d6f5f92b6d2b7c86b3ad250e0bad8dee4b7ad8a0c44bfb276af89a3"},
+    {file = "lxml-5.3.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:17b5d7f8acf809465086d498d62a981fa6a56d2718135bb0e4aa48c502055f5c"},
+    {file = "lxml-5.3.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:928e75a7200a4c09e6efc7482a1337919cc61fe1ba289f297827a5b76d8969c2"},
+    {file = "lxml-5.3.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5a997b784a639e05b9d4053ef3b20c7e447ea80814a762f25b8ed5a89d261eac"},
+    {file = "lxml-5.3.1-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:7b82e67c5feb682dbb559c3e6b78355f234943053af61606af126df2183b9ef9"},
+    {file = "lxml-5.3.1-cp310-cp310-manylinux_2_28_ppc64le.whl", hash = "sha256:f1de541a9893cf8a1b1db9bf0bf670a2decab42e3e82233d36a74eda7822b4c9"},
+    {file = "lxml-5.3.1-cp310-cp310-manylinux_2_28_s390x.whl", hash = "sha256:de1fc314c3ad6bc2f6bd5b5a5b9357b8c6896333d27fdbb7049aea8bd5af2d79"},
+    {file = "lxml-5.3.1-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:7c0536bd9178f754b277a3e53f90f9c9454a3bd108b1531ffff720e082d824f2"},
+    {file = "lxml-5.3.1-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:68018c4c67d7e89951a91fbd371e2e34cd8cfc71f0bb43b5332db38497025d51"},
+    {file = "lxml-5.3.1-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:aa826340a609d0c954ba52fd831f0fba2a4165659ab0ee1a15e4aac21f302406"},
+    {file = "lxml-5.3.1-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:796520afa499732191e39fc95b56a3b07f95256f2d22b1c26e217fb69a9db5b5"},
+    {file = "lxml-5.3.1-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:3effe081b3135237da6e4c4530ff2a868d3f80be0bda027e118a5971285d42d0"},
+    {file = "lxml-5.3.1-cp310-cp310-win32.whl", hash = "sha256:a22f66270bd6d0804b02cd49dae2b33d4341015545d17f8426f2c4e22f557a23"},
+    {file = "lxml-5.3.1-cp310-cp310-win_amd64.whl", hash = "sha256:0bcfadea3cdc68e678d2b20cb16a16716887dd00a881e16f7d806c2138b8ff0c"},
+    {file = "lxml-5.3.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:e220f7b3e8656ab063d2eb0cd536fafef396829cafe04cb314e734f87649058f"},
+    {file = "lxml-5.3.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:0f2cfae0688fd01f7056a17367e3b84f37c545fb447d7282cf2c242b16262607"},
+    {file = "lxml-5.3.1-cp311-cp311-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:67d2f8ad9dcc3a9e826bdc7802ed541a44e124c29b7d95a679eeb58c1c14ade8"},
+    {file = "lxml-5.3.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:db0c742aad702fd5d0c6611a73f9602f20aec2007c102630c06d7633d9c8f09a"},
+    {file = "lxml-5.3.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:198bb4b4dd888e8390afa4f170d4fa28467a7eaf857f1952589f16cfbb67af27"},
+    {file = "lxml-5.3.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d2a3e412ce1849be34b45922bfef03df32d1410a06d1cdeb793a343c2f1fd666"},
+    {file = "lxml-5.3.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2b8969dbc8d09d9cd2ae06362c3bad27d03f433252601ef658a49bd9f2b22d79"},
+    {file = "lxml-5.3.1-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:5be8f5e4044146a69c96077c7e08f0709c13a314aa5315981185c1f00235fe65"},
+    {file = "lxml-5.3.1-cp311-cp311-manylinux_2_28_ppc64le.whl", hash = "sha256:133f3493253a00db2c870d3740bc458ebb7d937bd0a6a4f9328373e0db305709"},
+    {file = "lxml-5.3.1-cp311-cp311-manylinux_2_28_s390x.whl", hash = "sha256:52d82b0d436edd6a1d22d94a344b9a58abd6c68c357ed44f22d4ba8179b37629"},
+    {file = "lxml-5.3.1-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:1b6f92e35e2658a5ed51c6634ceb5ddae32053182851d8cad2a5bc102a359b33"},
+    {file = "lxml-5.3.1-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:203b1d3eaebd34277be06a3eb880050f18a4e4d60861efba4fb946e31071a295"},
+    {file = "lxml-5.3.1-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:155e1a5693cf4b55af652f5c0f78ef36596c7f680ff3ec6eb4d7d85367259b2c"},
+    {file = "lxml-5.3.1-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:22ec2b3c191f43ed21f9545e9df94c37c6b49a5af0a874008ddc9132d49a2d9c"},
+    {file = "lxml-5.3.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:7eda194dd46e40ec745bf76795a7cccb02a6a41f445ad49d3cf66518b0bd9cff"},
+    {file = "lxml-5.3.1-cp311-cp311-win32.whl", hash = "sha256:fb7c61d4be18e930f75948705e9718618862e6fc2ed0d7159b2262be73f167a2"},
+    {file = "lxml-5.3.1-cp311-cp311-win_amd64.whl", hash = "sha256:c809eef167bf4a57af4b03007004896f5c60bd38dc3852fcd97a26eae3d4c9e6"},
+    {file = "lxml-5.3.1-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:e69add9b6b7b08c60d7ff0152c7c9a6c45b4a71a919be5abde6f98f1ea16421c"},
+    {file = "lxml-5.3.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:4e52e1b148867b01c05e21837586ee307a01e793b94072d7c7b91d2c2da02ffe"},
+    {file = "lxml-5.3.1-cp312-cp312-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a4b382e0e636ed54cd278791d93fe2c4f370772743f02bcbe431a160089025c9"},
+    {file = "lxml-5.3.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c2e49dc23a10a1296b04ca9db200c44d3eb32c8d8ec532e8c1fd24792276522a"},
+    {file = "lxml-5.3.1-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4399b4226c4785575fb20998dc571bc48125dc92c367ce2602d0d70e0c455eb0"},
+    {file = "lxml-5.3.1-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5412500e0dc5481b1ee9cf6b38bb3b473f6e411eb62b83dc9b62699c3b7b79f7"},
+    {file = "lxml-5.3.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1c93ed3c998ea8472be98fb55aed65b5198740bfceaec07b2eba551e55b7b9ae"},
+    {file = "lxml-5.3.1-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:63d57fc94eb0bbb4735e45517afc21ef262991d8758a8f2f05dd6e4174944519"},
+    {file = "lxml-5.3.1-cp312-cp312-manylinux_2_28_ppc64le.whl", hash = "sha256:b450d7cabcd49aa7ab46a3c6aa3ac7e1593600a1a0605ba536ec0f1b99a04322"},
+    {file = "lxml-5.3.1-cp312-cp312-manylinux_2_28_s390x.whl", hash = "sha256:4df0ec814b50275ad6a99bc82a38b59f90e10e47714ac9871e1b223895825468"},
+    {file = "lxml-5.3.1-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:d184f85ad2bb1f261eac55cddfcf62a70dee89982c978e92b9a74a1bfef2e367"},
+    {file = "lxml-5.3.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:b725e70d15906d24615201e650d5b0388b08a5187a55f119f25874d0103f90dd"},
+    {file = "lxml-5.3.1-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:a31fa7536ec1fb7155a0cd3a4e3d956c835ad0a43e3610ca32384d01f079ea1c"},
+    {file = "lxml-5.3.1-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:3c3c8b55c7fc7b7e8877b9366568cc73d68b82da7fe33d8b98527b73857a225f"},
+    {file = "lxml-5.3.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:d61ec60945d694df806a9aec88e8f29a27293c6e424f8ff91c80416e3c617645"},
+    {file = "lxml-5.3.1-cp312-cp312-win32.whl", hash = "sha256:f4eac0584cdc3285ef2e74eee1513a6001681fd9753b259e8159421ed28a72e5"},
+    {file = "lxml-5.3.1-cp312-cp312-win_amd64.whl", hash = "sha256:29bfc8d3d88e56ea0a27e7c4897b642706840247f59f4377d81be8f32aa0cfbf"},
+    {file = "lxml-5.3.1-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:c093c7088b40d8266f57ed71d93112bd64c6724d31f0794c1e52cc4857c28e0e"},
+    {file = "lxml-5.3.1-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:b0884e3f22d87c30694e625b1e62e6f30d39782c806287450d9dc2fdf07692fd"},
+    {file = "lxml-5.3.1-cp313-cp313-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1637fa31ec682cd5760092adfabe86d9b718a75d43e65e211d5931809bc111e7"},
+    {file = "lxml-5.3.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a364e8e944d92dcbf33b6b494d4e0fb3499dcc3bd9485beb701aa4b4201fa414"},
+    {file = "lxml-5.3.1-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:779e851fd0e19795ccc8a9bb4d705d6baa0ef475329fe44a13cf1e962f18ff1e"},
+    {file = "lxml-5.3.1-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c4393600915c308e546dc7003d74371744234e8444a28622d76fe19b98fa59d1"},
+    {file = "lxml-5.3.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:673b9d8e780f455091200bba8534d5f4f465944cbdd61f31dc832d70e29064a5"},
+    {file = "lxml-5.3.1-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:2e4a570f6a99e96c457f7bec5ad459c9c420ee80b99eb04cbfcfe3fc18ec6423"},
+    {file = "lxml-5.3.1-cp313-cp313-manylinux_2_28_ppc64le.whl", hash = "sha256:71f31eda4e370f46af42fc9f264fafa1b09f46ba07bdbee98f25689a04b81c20"},
+    {file = "lxml-5.3.1-cp313-cp313-manylinux_2_28_s390x.whl", hash = "sha256:42978a68d3825eaac55399eb37a4d52012a205c0c6262199b8b44fcc6fd686e8"},
+    {file = "lxml-5.3.1-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:8b1942b3e4ed9ed551ed3083a2e6e0772de1e5e3aca872d955e2e86385fb7ff9"},
+    {file = "lxml-5.3.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:85c4f11be9cf08917ac2a5a8b6e1ef63b2f8e3799cec194417e76826e5f1de9c"},
+    {file = "lxml-5.3.1-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:231cf4d140b22a923b1d0a0a4e0b4f972e5893efcdec188934cc65888fd0227b"},
+    {file = "lxml-5.3.1-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:5865b270b420eda7b68928d70bb517ccbe045e53b1a428129bb44372bf3d7dd5"},
+    {file = "lxml-5.3.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:dbf7bebc2275016cddf3c997bf8a0f7044160714c64a9b83975670a04e6d2252"},
+    {file = "lxml-5.3.1-cp313-cp313-win32.whl", hash = "sha256:d0751528b97d2b19a388b302be2a0ee05817097bab46ff0ed76feeec24951f78"},
+    {file = "lxml-5.3.1-cp313-cp313-win_amd64.whl", hash = "sha256:91fb6a43d72b4f8863d21f347a9163eecbf36e76e2f51068d59cd004c506f332"},
+    {file = "lxml-5.3.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:016b96c58e9a4528219bb563acf1aaaa8bc5452e7651004894a973f03b84ba81"},
+    {file = "lxml-5.3.1-cp36-cp36m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:82a4bb10b0beef1434fb23a09f001ab5ca87895596b4581fd53f1e5145a8934a"},
+    {file = "lxml-5.3.1-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3d68eeef7b4d08a25e51897dac29bcb62aba830e9ac6c4e3297ee7c6a0cf6439"},
+    {file = "lxml-5.3.1-cp36-cp36m-manylinux_2_28_x86_64.whl", hash = "sha256:f12582b8d3b4c6be1d298c49cb7ae64a3a73efaf4c2ab4e37db182e3545815ac"},
+    {file = "lxml-5.3.1-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:2df7ed5edeb6bd5590914cd61df76eb6cce9d590ed04ec7c183cf5509f73530d"},
+    {file = "lxml-5.3.1-cp36-cp36m-musllinux_1_2_x86_64.whl", hash = "sha256:585c4dc429deebc4307187d2b71ebe914843185ae16a4d582ee030e6cfbb4d8a"},
+    {file = "lxml-5.3.1-cp36-cp36m-win32.whl", hash = "sha256:06a20d607a86fccab2fc15a77aa445f2bdef7b49ec0520a842c5c5afd8381576"},
+    {file = "lxml-5.3.1-cp36-cp36m-win_amd64.whl", hash = "sha256:057e30d0012439bc54ca427a83d458752ccda725c1c161cc283db07bcad43cf9"},
+    {file = "lxml-5.3.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:4867361c049761a56bd21de507cab2c2a608c55102311d142ade7dab67b34f32"},
+    {file = "lxml-5.3.1-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3dddf0fb832486cc1ea71d189cb92eb887826e8deebe128884e15020bb6e3f61"},
+    {file = "lxml-5.3.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1bcc211542f7af6f2dfb705f5f8b74e865592778e6cafdfd19c792c244ccce19"},
+    {file = "lxml-5.3.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:aaca5a812f050ab55426c32177091130b1e49329b3f002a32934cd0245571307"},
+    {file = "lxml-5.3.1-cp37-cp37m-manylinux_2_28_aarch64.whl", hash = "sha256:236610b77589faf462337b3305a1be91756c8abc5a45ff7ca8f245a71c5dab70"},
+    {file = "lxml-5.3.1-cp37-cp37m-manylinux_2_28_x86_64.whl", hash = "sha256:aed57b541b589fa05ac248f4cb1c46cbb432ab82cbd467d1c4f6a2bdc18aecf9"},
+    {file = "lxml-5.3.1-cp37-cp37m-musllinux_1_2_aarch64.whl", hash = "sha256:75fa3d6946d317ffc7016a6fcc44f42db6d514b7fdb8b4b28cbe058303cb6e53"},
+    {file = "lxml-5.3.1-cp37-cp37m-musllinux_1_2_x86_64.whl", hash = "sha256:96eef5b9f336f623ffc555ab47a775495e7e8846dde88de5f941e2906453a1ce"},
+    {file = "lxml-5.3.1-cp37-cp37m-win32.whl", hash = "sha256:ef45f31aec9be01379fc6c10f1d9c677f032f2bac9383c827d44f620e8a88407"},
+    {file = "lxml-5.3.1-cp37-cp37m-win_amd64.whl", hash = "sha256:a0611da6b07dd3720f492db1b463a4d1175b096b49438761cc9f35f0d9eaaef5"},
+    {file = "lxml-5.3.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:b2aca14c235c7a08558fe0a4786a1a05873a01e86b474dfa8f6df49101853a4e"},
+    {file = "lxml-5.3.1-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ae82fce1d964f065c32c9517309f0c7be588772352d2f40b1574a214bd6e6098"},
+    {file = "lxml-5.3.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7aae7a3d63b935babfdc6864b31196afd5145878ddd22f5200729006366bc4d5"},
+    {file = "lxml-5.3.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e8e0d177b1fe251c3b1b914ab64135475c5273c8cfd2857964b2e3bb0fe196a7"},
+    {file = "lxml-5.3.1-cp38-cp38-manylinux_2_28_aarch64.whl", hash = "sha256:6c4dd3bfd0c82400060896717dd261137398edb7e524527438c54a8c34f736bf"},
+    {file = "lxml-5.3.1-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:f1208c1c67ec9e151d78aa3435aa9b08a488b53d9cfac9b699f15255a3461ef2"},
+    {file = "lxml-5.3.1-cp38-cp38-musllinux_1_2_aarch64.whl", hash = "sha256:c6aacf00d05b38a5069826e50ae72751cb5bc27bdc4d5746203988e429b385bb"},
+    {file = "lxml-5.3.1-cp38-cp38-musllinux_1_2_x86_64.whl", hash = "sha256:5881aaa4bf3a2d086c5f20371d3a5856199a0d8ac72dd8d0dbd7a2ecfc26ab73"},
+    {file = "lxml-5.3.1-cp38-cp38-win32.whl", hash = "sha256:45fbb70ccbc8683f2fb58bea89498a7274af1d9ec7995e9f4af5604e028233fc"},
+    {file = "lxml-5.3.1-cp38-cp38-win_amd64.whl", hash = "sha256:7512b4d0fc5339d5abbb14d1843f70499cab90d0b864f790e73f780f041615d7"},
+    {file = "lxml-5.3.1-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:5885bc586f1edb48e5d68e7a4b4757b5feb2a496b64f462b4d65950f5af3364f"},
+    {file = "lxml-5.3.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:1b92fe86e04f680b848fff594a908edfa72b31bfc3499ef7433790c11d4c8cd8"},
+    {file = "lxml-5.3.1-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a091026c3bf7519ab1e64655a3f52a59ad4a4e019a6f830c24d6430695b1cf6a"},
+    {file = "lxml-5.3.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8ffb141361108e864ab5f1813f66e4e1164181227f9b1f105b042729b6c15125"},
+    {file = "lxml-5.3.1-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3715cdf0dd31b836433af9ee9197af10e3df41d273c19bb249230043667a5dfd"},
+    {file = "lxml-5.3.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:88b72eb7222d918c967202024812c2bfb4048deeb69ca328363fb8e15254c549"},
+    {file = "lxml-5.3.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:aa59974880ab5ad8ef3afaa26f9bda148c5f39e06b11a8ada4660ecc9fb2feb3"},
+    {file = "lxml-5.3.1-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:3bb8149840daf2c3f97cebf00e4ed4a65a0baff888bf2605a8d0135ff5cf764e"},
+    {file = "lxml-5.3.1-cp39-cp39-manylinux_2_28_ppc64le.whl", hash = "sha256:0d6b2fa86becfa81f0a0271ccb9eb127ad45fb597733a77b92e8a35e53414914"},
+    {file = "lxml-5.3.1-cp39-cp39-manylinux_2_28_s390x.whl", hash = "sha256:136bf638d92848a939fd8f0e06fcf92d9f2e4b57969d94faae27c55f3d85c05b"},
+    {file = "lxml-5.3.1-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:89934f9f791566e54c1d92cdc8f8fd0009447a5ecdb1ec6b810d5f8c4955f6be"},
+    {file = "lxml-5.3.1-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:a8ade0363f776f87f982572c2860cc43c65ace208db49c76df0a21dde4ddd16e"},
+    {file = "lxml-5.3.1-cp39-cp39-musllinux_1_2_ppc64le.whl", hash = "sha256:bfbbab9316330cf81656fed435311386610f78b6c93cc5db4bebbce8dd146675"},
+    {file = "lxml-5.3.1-cp39-cp39-musllinux_1_2_s390x.whl", hash = "sha256:172d65f7c72a35a6879217bcdb4bb11bc88d55fb4879e7569f55616062d387c2"},
+    {file = "lxml-5.3.1-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:e3c623923967f3e5961d272718655946e5322b8d058e094764180cdee7bab1af"},
+    {file = "lxml-5.3.1-cp39-cp39-win32.whl", hash = "sha256:ce0930a963ff593e8bb6fda49a503911accc67dee7e5445eec972668e672a0f0"},
+    {file = "lxml-5.3.1-cp39-cp39-win_amd64.whl", hash = "sha256:f7b64fcd670bca8800bc10ced36620c6bbb321e7bc1214b9c0c0df269c1dddc2"},
+    {file = "lxml-5.3.1-pp310-pypy310_pp73-macosx_10_15_x86_64.whl", hash = "sha256:afa578b6524ff85fb365f454cf61683771d0170470c48ad9d170c48075f86725"},
+    {file = "lxml-5.3.1-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:67f5e80adf0aafc7b5454f2c1cb0cde920c9b1f2cbd0485f07cc1d0497c35c5d"},
+    {file = "lxml-5.3.1-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2dd0b80ac2d8f13ffc906123a6f20b459cb50a99222d0da492360512f3e50f84"},
+    {file = "lxml-5.3.1-pp310-pypy310_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:422c179022ecdedbe58b0e242607198580804253da220e9454ffe848daa1cfd2"},
+    {file = "lxml-5.3.1-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:524ccfded8989a6595dbdda80d779fb977dbc9a7bc458864fc9a0c2fc15dc877"},
+    {file = "lxml-5.3.1-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:48fd46bf7155def2e15287c6f2b133a2f78e2d22cdf55647269977b873c65499"},
+    {file = "lxml-5.3.1-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:05123fad495a429f123307ac6d8fd6f977b71e9a0b6d9aeeb8f80c017cb17131"},
+    {file = "lxml-5.3.1-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a243132767150a44e6a93cd1dde41010036e1cbc63cc3e9fe1712b277d926ce3"},
+    {file = "lxml-5.3.1-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c92ea6d9dd84a750b2bae72ff5e8cf5fdd13e58dda79c33e057862c29a8d5b50"},
+    {file = "lxml-5.3.1-pp37-pypy37_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:2f1be45d4c15f237209bbf123a0e05b5d630c8717c42f59f31ea9eae2ad89394"},
+    {file = "lxml-5.3.1-pp37-pypy37_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:a83d3adea1e0ee36dac34627f78ddd7f093bb9cfc0a8e97f1572a949b695cb98"},
+    {file = "lxml-5.3.1-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:3edbb9c9130bac05d8c3fe150c51c337a471cc7fdb6d2a0a7d3a88e88a829314"},
+    {file = "lxml-5.3.1-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:2f23cf50eccb3255b6e913188291af0150d89dab44137a69e14e4dcb7be981f1"},
+    {file = "lxml-5.3.1-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:df7e5edac4778127f2bf452e0721a58a1cfa4d1d9eac63bdd650535eb8543615"},
+    {file = "lxml-5.3.1-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:094b28ed8a8a072b9e9e2113a81fda668d2053f2ca9f2d202c2c8c7c2d6516b1"},
+    {file = "lxml-5.3.1-pp38-pypy38_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:514fe78fc4b87e7a7601c92492210b20a1b0c6ab20e71e81307d9c2e377c64de"},
+    {file = "lxml-5.3.1-pp38-pypy38_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:8fffc08de02071c37865a155e5ea5fce0282e1546fd5bde7f6149fcaa32558ac"},
+    {file = "lxml-5.3.1-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:4b0d5cdba1b655d5b18042ac9c9ff50bda33568eb80feaaca4fc237b9c4fbfde"},
+    {file = "lxml-5.3.1-pp39-pypy39_pp73-macosx_10_15_x86_64.whl", hash = "sha256:3031e4c16b59424e8d78522c69b062d301d951dc55ad8685736c3335a97fc270"},
+    {file = "lxml-5.3.1-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cb659702a45136c743bc130760c6f137870d4df3a9e14386478b8a0511abcfca"},
+    {file = "lxml-5.3.1-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5a11b16a33656ffc43c92a5343a28dc71eefe460bcc2a4923a96f292692709f6"},
+    {file = "lxml-5.3.1-pp39-pypy39_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:c5ae125276f254b01daa73e2c103363d3e99e3e10505686ac7d9d2442dd4627a"},
+    {file = "lxml-5.3.1-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:c76722b5ed4a31ba103e0dc77ab869222ec36efe1a614e42e9bcea88a36186fe"},
+    {file = "lxml-5.3.1-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:33e06717c00c788ab4e79bc4726ecc50c54b9bfb55355eae21473c145d83c2d2"},
+    {file = "lxml-5.3.1.tar.gz", hash = "sha256:106b7b5d2977b339f1e97efe2778e2ab20e99994cbb0ec5e55771ed0795920c8"},
 ]
 
 [package.extras]
 cssselect = ["cssselect (>=0.7)"]
-html-clean = ["lxml-html-clean"]
+html-clean = ["lxml_html_clean"]
 html5 = ["html5lib"]
 htmlsoup = ["BeautifulSoup4"]
-source = ["Cython (>=3.0.11)"]
+source = ["Cython (>=3.0.11,<3.1.0)"]
 
 [[package]]
 name = "lz4"
@@ -6074,15 +6078,15 @@ pydantic = ">=1.9,<3.0"
 
 [[package]]
 name = "posthog"
-version = "3.11.0"
+version = "3.13.0"
 description = "Integrate PostHog into any python application."
 optional = false
 python-versions = "*"
 groups = ["vdb"]
 markers = "python_version == \"3.11\" or python_version >= \"3.12\""
 files = [
-    {file = "posthog-3.11.0-py2.py3-none-any.whl", hash = "sha256:8cbd52c26bcdfbe65c4ea84a8090cfa2e046879d6b6d71da68e279a5b4aedb46"},
-    {file = "posthog-3.11.0.tar.gz", hash = "sha256:42a1f88cbcddeceaf6e8900a528db62d84fc56f6e5809f3d6dfb40e6f743091e"},
+    {file = "posthog-3.13.0-py2.py3-none-any.whl", hash = "sha256:0afd0132055a3da9c6b0ecf763e7f2ce2b66659ef16169883394d0835c30d501"},
+    {file = "posthog-3.13.0.tar.gz", hash = "sha256:54e9de232459846b1686a0cfb58acb02b7ccda379d837e1eb1c3af62c3775915"},
 ]
 
 [package.dependencies]
@@ -6093,10 +6097,10 @@ requests = ">=2.7,<3.0"
 six = ">=1.5"
 
 [package.extras]
-dev = ["black", "flake8", "flake8-print", "isort", "pre-commit"]
+dev = ["black", "django-stubs", "flake8", "flake8-print", "isort", "lxml", "mypy", "mypy-baseline", "pre-commit", "pydantic", "types-mock", "types-python-dateutil", "types-requests", "types-setuptools", "types-six"]
 langchain = ["langchain (>=0.2.0)"]
 sentry = ["django", "sentry-sdk"]
-test = ["anthropic", "coverage", "django", "flake8", "freezegun (==0.3.15)", "langchain-anthropic (>=0.2.0)", "langchain-community (>=0.2.0)", "langchain-openai (>=0.2.0)", "langgraph", "mock (>=2.0.0)", "openai", "pydantic", "pylint", "pytest", "pytest-asyncio", "pytest-timeout"]
+test = ["anthropic", "coverage", "django", "flake8", "freezegun (==1.5.1)", "langchain-anthropic (>=0.2.0)", "langchain-community (>=0.2.0)", "langchain-openai (>=0.2.0)", "langgraph", "mock (>=2.0.0)", "openai", "pydantic", "pylint", "pytest", "pytest-asyncio", "pytest-timeout"]
 
 [[package]]
 name = "prompt-toolkit"
@@ -6250,34 +6254,27 @@ files = [
 
 [[package]]
 name = "psutil"
-version = "6.1.1"
-description = "Cross-platform lib for process and system monitoring in Python."
+version = "7.0.0"
+description = "Cross-platform lib for process and system monitoring in Python.  NOTE: the syntax of this script MUST be kept compatible with Python 2.7."
 optional = false
-python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,>=2.7"
+python-versions = ">=3.6"
 groups = ["main"]
 markers = "python_version == \"3.11\" or python_version >= \"3.12\""
 files = [
-    {file = "psutil-6.1.1-cp27-cp27m-macosx_10_9_x86_64.whl", hash = "sha256:9ccc4316f24409159897799b83004cb1e24f9819b0dcf9c0b68bdcb6cefee6a8"},
-    {file = "psutil-6.1.1-cp27-cp27m-manylinux2010_i686.whl", hash = "sha256:ca9609c77ea3b8481ab005da74ed894035936223422dc591d6772b147421f777"},
-    {file = "psutil-6.1.1-cp27-cp27m-manylinux2010_x86_64.whl", hash = "sha256:8df0178ba8a9e5bc84fed9cfa61d54601b371fbec5c8eebad27575f1e105c0d4"},
-    {file = "psutil-6.1.1-cp27-cp27mu-manylinux2010_i686.whl", hash = "sha256:1924e659d6c19c647e763e78670a05dbb7feaf44a0e9c94bf9e14dfc6ba50468"},
-    {file = "psutil-6.1.1-cp27-cp27mu-manylinux2010_x86_64.whl", hash = "sha256:018aeae2af92d943fdf1da6b58665124897cfc94faa2ca92098838f83e1b1bca"},
-    {file = "psutil-6.1.1-cp27-none-win32.whl", hash = "sha256:6d4281f5bbca041e2292be3380ec56a9413b790579b8e593b1784499d0005dac"},
-    {file = "psutil-6.1.1-cp27-none-win_amd64.whl", hash = "sha256:c777eb75bb33c47377c9af68f30e9f11bc78e0f07fbf907be4a5d70b2fe5f030"},
-    {file = "psutil-6.1.1-cp36-abi3-macosx_10_9_x86_64.whl", hash = "sha256:fc0ed7fe2231a444fc219b9c42d0376e0a9a1a72f16c5cfa0f68d19f1a0663e8"},
-    {file = "psutil-6.1.1-cp36-abi3-macosx_11_0_arm64.whl", hash = "sha256:0bdd4eab935276290ad3cb718e9809412895ca6b5b334f5a9111ee6d9aff9377"},
-    {file = "psutil-6.1.1-cp36-abi3-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b6e06c20c05fe95a3d7302d74e7097756d4ba1247975ad6905441ae1b5b66003"},
-    {file = "psutil-6.1.1-cp36-abi3-manylinux_2_12_x86_64.manylinux2010_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:97f7cb9921fbec4904f522d972f0c0e1f4fabbdd4e0287813b21215074a0f160"},
-    {file = "psutil-6.1.1-cp36-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:33431e84fee02bc84ea36d9e2c4a6d395d479c9dd9bba2376c1f6ee8f3a4e0b3"},
-    {file = "psutil-6.1.1-cp36-cp36m-win32.whl", hash = "sha256:384636b1a64b47814437d1173be1427a7c83681b17a450bfc309a1953e329603"},
-    {file = "psutil-6.1.1-cp36-cp36m-win_amd64.whl", hash = "sha256:8be07491f6ebe1a693f17d4f11e69d0dc1811fa082736500f649f79df7735303"},
-    {file = "psutil-6.1.1-cp37-abi3-win32.whl", hash = "sha256:eaa912e0b11848c4d9279a93d7e2783df352b082f40111e078388701fd479e53"},
-    {file = "psutil-6.1.1-cp37-abi3-win_amd64.whl", hash = "sha256:f35cfccb065fff93529d2afb4a2e89e363fe63ca1e4a5da22b603a85833c2649"},
-    {file = "psutil-6.1.1.tar.gz", hash = "sha256:cf8496728c18f2d0b45198f06895be52f36611711746b7f30c464b422b50e2f5"},
+    {file = "psutil-7.0.0-cp36-abi3-macosx_10_9_x86_64.whl", hash = "sha256:101d71dc322e3cffd7cea0650b09b3d08b8e7c4109dd6809fe452dfd00e58b25"},
+    {file = "psutil-7.0.0-cp36-abi3-macosx_11_0_arm64.whl", hash = "sha256:39db632f6bb862eeccf56660871433e111b6ea58f2caea825571951d4b6aa3da"},
+    {file = "psutil-7.0.0-cp36-abi3-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1fcee592b4c6f146991ca55919ea3d1f8926497a713ed7faaf8225e174581e91"},
+    {file = "psutil-7.0.0-cp36-abi3-manylinux_2_12_x86_64.manylinux2010_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4b1388a4f6875d7e2aff5c4ca1cc16c545ed41dd8bb596cefea80111db353a34"},
+    {file = "psutil-7.0.0-cp36-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a5f098451abc2828f7dc6b58d44b532b22f2088f4999a937557b603ce72b1993"},
+    {file = "psutil-7.0.0-cp36-cp36m-win32.whl", hash = "sha256:84df4eb63e16849689f76b1ffcb36db7b8de703d1bc1fe41773db487621b6c17"},
+    {file = "psutil-7.0.0-cp36-cp36m-win_amd64.whl", hash = "sha256:1e744154a6580bc968a0195fd25e80432d3afec619daf145b9e5ba16cc1d688e"},
+    {file = "psutil-7.0.0-cp37-abi3-win32.whl", hash = "sha256:ba3fcef7523064a6c9da440fc4d6bd07da93ac726b5733c29027d7dc95b39d99"},
+    {file = "psutil-7.0.0-cp37-abi3-win_amd64.whl", hash = "sha256:4cf3d4eb1aa9b348dec30105c55cd9b7d4629285735a102beb4441e38db90553"},
+    {file = "psutil-7.0.0.tar.gz", hash = "sha256:7be9c3eba38beccb6495ea33afd982a44074b78f28c434a1f51cc07fd315c456"},
 ]
 
 [package.extras]
-dev = ["abi3audit", "black", "check-manifest", "coverage", "packaging", "pylint", "pyperf", "pypinfo", "pytest-cov", "requests", "rstcheck", "ruff", "sphinx", "sphinx_rtd_theme", "toml-sort", "twine", "virtualenv", "vulture", "wheel"]
+dev = ["abi3audit", "black (==24.10.0)", "check-manifest", "coverage", "packaging", "pylint", "pyperf", "pypinfo", "pytest", "pytest-cov", "pytest-xdist", "requests", "rstcheck", "ruff", "setuptools", "sphinx", "sphinx_rtd_theme", "toml-sort", "twine", "virtualenv", "vulture", "wheel"]
 test = ["pytest", "pytest-xdist", "setuptools"]
 
 [[package]]
@@ -6348,6 +6345,7 @@ files = [
     {file = "psycopg2_binary-2.9.10-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:bb89f0a835bcfc1d42ccd5f41f04870c1b936d8507c6df12b7737febc40f0909"},
     {file = "psycopg2_binary-2.9.10-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:f0c2d907a1e102526dd2986df638343388b94c33860ff3bbe1384130828714b1"},
     {file = "psycopg2_binary-2.9.10-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:f8157bed2f51db683f31306aa497311b560f2265998122abe1dce6428bd86567"},
+    {file = "psycopg2_binary-2.9.10-cp313-cp313-win_amd64.whl", hash = "sha256:27422aa5f11fbcd9b18da48373eb67081243662f9b46e6fd07c3eb46e4535142"},
     {file = "psycopg2_binary-2.9.10-cp38-cp38-macosx_12_0_x86_64.whl", hash = "sha256:eb09aa7f9cecb45027683bb55aebaaf45a0df8bf6de68801a6afdc7947bb09d4"},
     {file = "psycopg2_binary-2.9.10-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b73d6d7f0ccdad7bc43e6d34273f70d587ef62f824d7261c4ae9b8b1b6af90e8"},
     {file = "psycopg2_binary-2.9.10-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ce5ab4bf46a211a8e924d307c1b1fcda82368586a19d0a24f8ae166f5c784864"},
@@ -6822,15 +6820,15 @@ diagrams = ["jinja2", "railroad-diagrams"]
 
 [[package]]
 name = "pypdf"
-version = "5.2.0"
+version = "5.3.0"
 description = "A pure-python PDF library capable of splitting, merging, cropping, and transforming PDF files"
 optional = false
 python-versions = ">=3.8"
 groups = ["main"]
 markers = "python_version == \"3.11\" or python_version >= \"3.12\""
 files = [
-    {file = "pypdf-5.2.0-py3-none-any.whl", hash = "sha256:d107962ec45e65e3bd10c1d9242bdbbedaa38193c9e3a6617bd6d996e5747b19"},
-    {file = "pypdf-5.2.0.tar.gz", hash = "sha256:7c38e68420f038f2c4998fd9d6717b6db4f6cef1642e9cf384d519c9cf094663"},
+    {file = "pypdf-5.3.0-py3-none-any.whl", hash = "sha256:d7b6db242f5f8fdb4990ae11815c394b8e1b955feda0befcce862efd8559c181"},
+    {file = "pypdf-5.3.0.tar.gz", hash = "sha256:08393660dfea25b27ec6fe863fb2f2248e6270da5103fae49e9dea8178741951"},
 ]
 
 [package.extras]
@@ -7153,19 +7151,19 @@ cli = ["click (>=5.0)"]
 
 [[package]]
 name = "python-iso639"
-version = "2025.1.28"
+version = "2025.2.8"
 description = "ISO 639 language codes, names, and other associated information"
 optional = false
 python-versions = ">=3.9"
 groups = ["main"]
 markers = "python_version == \"3.11\" or python_version >= \"3.12\""
 files = [
-    {file = "python_iso639-2025.1.28-py3-none-any.whl", hash = "sha256:66bcd88838727bc8ed1dfc9b5a354a27ed5c4bab8322473da81071fae265228b"},
-    {file = "python_iso639-2025.1.28.tar.gz", hash = "sha256:42b18bf52ad6ce5882c0e4acec9ae528310c7ef2966b776fc49d154c654580c5"},
+    {file = "python_iso639-2025.2.8-py3-none-any.whl", hash = "sha256:fc072f1f2007eae4a877778a73d7653c51020973e719b502e0d31e95a92c99d0"},
+    {file = "python_iso639-2025.2.8.tar.gz", hash = "sha256:94f27c0286fc81ff0e033d7b63d63a5967eef584b97f13289366bf178953f5d7"},
 ]
 
 [package.extras]
-dev = ["black (==24.10.0)", "build (==1.2.2)", "flake8 (==7.1.1)", "mypy (==1.14.1)", "pytest (==8.3.4)", "requests (==2.32.3)", "twine (==6.1.0)"]
+dev = ["black (==25.1.0)", "build (==1.2.2)", "flake8 (==7.1.1)", "mypy (==1.15.0)", "pytest (==8.3.4)", "requests (==2.32.3)", "twine (==6.1.0)"]
 
 [[package]]
 name = "python-magic"
@@ -7916,31 +7914,31 @@ pyasn1 = ">=0.1.3"
 
 [[package]]
 name = "ruff"
-version = "0.9.5"
+version = "0.9.6"
 description = "An extremely fast Python linter and code formatter, written in Rust."
 optional = false
 python-versions = ">=3.7"
 groups = ["lint"]
 markers = "python_version == \"3.11\" or python_version >= \"3.12\""
 files = [
-    {file = "ruff-0.9.5-py3-none-linux_armv6l.whl", hash = "sha256:d466d2abc05f39018d53f681fa1c0ffe9570e6d73cde1b65d23bb557c846f442"},
-    {file = "ruff-0.9.5-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:38840dbcef63948657fa7605ca363194d2fe8c26ce8f9ae12eee7f098c85ac8a"},
-    {file = "ruff-0.9.5-py3-none-macosx_11_0_arm64.whl", hash = "sha256:d56ba06da53536b575fbd2b56517f6f95774ff7be0f62c80b9e67430391eeb36"},
-    {file = "ruff-0.9.5-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4f7cb2a01da08244c50b20ccfaeb5972e4228c3c3a1989d3ece2bc4b1f996001"},
-    {file = "ruff-0.9.5-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:96d5c76358419bc63a671caac70c18732d4fd0341646ecd01641ddda5c39ca0b"},
-    {file = "ruff-0.9.5-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:deb8304636ed394211f3a6d46c0e7d9535b016f53adaa8340139859b2359a070"},
-    {file = "ruff-0.9.5-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:df455000bf59e62b3e8c7ba5ed88a4a2bc64896f900f311dc23ff2dc38156440"},
-    {file = "ruff-0.9.5-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:de92170dfa50c32a2b8206a647949590e752aca8100a0f6b8cefa02ae29dce80"},
-    {file = "ruff-0.9.5-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:3d28532d73b1f3f627ba88e1456f50748b37f3a345d2be76e4c653bec6c3e393"},
-    {file = "ruff-0.9.5-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2c746d7d1df64f31d90503ece5cc34d7007c06751a7a3bbeee10e5f2463d52d2"},
-    {file = "ruff-0.9.5-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:11417521d6f2d121fda376f0d2169fb529976c544d653d1d6044f4c5562516ee"},
-    {file = "ruff-0.9.5-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:5b9d71c3879eb32de700f2f6fac3d46566f644a91d3130119a6378f9312a38e1"},
-    {file = "ruff-0.9.5-py3-none-musllinux_1_2_i686.whl", hash = "sha256:2e36c61145e70febcb78483903c43444c6b9d40f6d2f800b5552fec6e4a7bb9a"},
-    {file = "ruff-0.9.5-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:2f71d09aeba026c922aa7aa19a08d7bd27c867aedb2f74285a2639644c1c12f5"},
-    {file = "ruff-0.9.5-py3-none-win32.whl", hash = "sha256:134f958d52aa6fdec3b294b8ebe2320a950d10c041473c4316d2e7d7c2544723"},
-    {file = "ruff-0.9.5-py3-none-win_amd64.whl", hash = "sha256:78cc6067f6d80b6745b67498fb84e87d32c6fc34992b52bffefbdae3442967d6"},
-    {file = "ruff-0.9.5-py3-none-win_arm64.whl", hash = "sha256:18a29f1a005bddb229e580795627d297dfa99f16b30c7039e73278cf6b5f9fa9"},
-    {file = "ruff-0.9.5.tar.gz", hash = "sha256:11aecd7a633932875ab3cb05a484c99970b9d52606ce9ea912b690b02653d56c"},
+    {file = "ruff-0.9.6-py3-none-linux_armv6l.whl", hash = "sha256:2f218f356dd2d995839f1941322ff021c72a492c470f0b26a34f844c29cdf5ba"},
+    {file = "ruff-0.9.6-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:b908ff4df65dad7b251c9968a2e4560836d8f5487c2f0cc238321ed951ea0504"},
+    {file = "ruff-0.9.6-py3-none-macosx_11_0_arm64.whl", hash = "sha256:b109c0ad2ececf42e75fa99dc4043ff72a357436bb171900714a9ea581ddef83"},
+    {file = "ruff-0.9.6-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1de4367cca3dac99bcbd15c161404e849bb0bfd543664db39232648dc00112dc"},
+    {file = "ruff-0.9.6-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:ac3ee4d7c2c92ddfdaedf0bf31b2b176fa7aa8950efc454628d477394d35638b"},
+    {file = "ruff-0.9.6-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:5dc1edd1775270e6aa2386119aea692039781429f0be1e0949ea5884e011aa8e"},
+    {file = "ruff-0.9.6-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:4a091729086dffa4bd070aa5dab7e39cc6b9d62eb2bef8f3d91172d30d599666"},
+    {file = "ruff-0.9.6-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d1bbc6808bf7b15796cef0815e1dfb796fbd383e7dbd4334709642649625e7c5"},
+    {file = "ruff-0.9.6-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:589d1d9f25b5754ff230dce914a174a7c951a85a4e9270613a2b74231fdac2f5"},
+    {file = "ruff-0.9.6-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dc61dd5131742e21103fbbdcad683a8813be0e3c204472d520d9a5021ca8b217"},
+    {file = "ruff-0.9.6-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:5e2d9126161d0357e5c8f30b0bd6168d2c3872372f14481136d13de9937f79b6"},
+    {file = "ruff-0.9.6-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:68660eab1a8e65babb5229a1f97b46e3120923757a68b5413d8561f8a85d4897"},
+    {file = "ruff-0.9.6-py3-none-musllinux_1_2_i686.whl", hash = "sha256:c4cae6c4cc7b9b4017c71114115db0445b00a16de3bcde0946273e8392856f08"},
+    {file = "ruff-0.9.6-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:19f505b643228b417c1111a2a536424ddde0db4ef9023b9e04a46ed8a1cb4656"},
+    {file = "ruff-0.9.6-py3-none-win32.whl", hash = "sha256:194d8402bceef1b31164909540a597e0d913c0e4952015a5b40e28c146121b5d"},
+    {file = "ruff-0.9.6-py3-none-win_amd64.whl", hash = "sha256:03482d5c09d90d4ee3f40d97578423698ad895c87314c4de39ed2af945633caa"},
+    {file = "ruff-0.9.6-py3-none-win_arm64.whl", hash = "sha256:0e2bb706a2be7ddfea4a4af918562fdc1bcb16df255e5fa595bbd800ce322a5a"},
+    {file = "ruff-0.9.6.tar.gz", hash = "sha256:81761592f72b620ec8fa1068a6fd00e98a5ebee342a3642efd84454f3031dca9"},
 ]
 
 [[package]]
@@ -9812,6 +9810,27 @@ files = [
     {file = "wrapt-1.17.2.tar.gz", hash = "sha256:41388e9d4d1522446fe79d3213196bd9e3b301a336965b9e27ca2788ebd122f3"},
 ]
 
+[[package]]
+name = "xinference-client"
+version = "1.2.2"
+description = "Client for Xinference"
+optional = false
+python-versions = "*"
+groups = ["vdb"]
+markers = "python_version == \"3.11\" or python_version >= \"3.12\""
+files = [
+    {file = "xinference-client-1.2.2.tar.gz", hash = "sha256:85d2ba0fcbaae616b06719c422364123cbac97f3e3c82e614095fe6d0e630ed0"},
+    {file = "xinference_client-1.2.2-py3-none-any.whl", hash = "sha256:6941d87cf61283a9d6e81cee6cb2609a183d34c6b7d808c6ba0c33437520518f"},
+]
+
+[package.dependencies]
+pydantic = "*"
+requests = "*"
+typing-extensions = "*"
+
+[package.extras]
+dev = ["black", "cython (>=0.29)", "flake8 (>=3.8.0)", "ipython (>=6.5.0)", "pytest (>=3.5.0)", "pytest-asyncio (>=0.14.0)", "pytest-cov (>=2.5.0)", "pytest-forked (>=1.0)", "pytest-mock (>=3.11.1)", "pytest-timeout (>=1.2.0)"]
+
 [[package]]
 name = "xlrd"
 version = "2.0.1"
@@ -10168,4 +10187,4 @@ cffi = ["cffi (>=1.11)"]
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.11,<3.13"
-content-hash = "7bb979b6667b099ad0ba75a9cad287409c6d7739b595c05197581ad1c0d702ce"
+content-hash = "3befd048b44db64797e91c36c41c7c44fdca2b59a76a5b24bf78d365b41214d7"

api/pyproject.toml

@@ -18,7 +18,7 @@ package-mode = false
 authlib = "1.3.1"
 azure-identity = "1.16.1"
 beautifulsoup4 = "4.12.2"
-boto3 = "1.36.12"
+boto3 = "1.37.1"
 bs4 = "~0.0.1"
 cachetools = "~5.3.0"
 celery = "~5.4.0"
@@ -134,6 +134,7 @@ tidb-vector = "0.0.9"
 upstash-vector = "0.6.0"
 volcengine-compat = "~1.0.156"
 weaviate-client = "~3.21.0"
+xinference-client = "~1.2.2"
 
 ############################################################
 # [ Dev ] dependency group

api/pytest.ini

@@ -1,4 +1,5 @@
 [pytest]
+continue-on-collection-errors = true
 env =
     ANTHROPIC_API_KEY = sk-ant-api11-IamNotARealKeyJustForMockTestKawaiiiiiiiiii-NotBaka-ASkksz
     AZURE_OPENAI_API_BASE = https://difyai-openai.openai.azure.com

api/services/app_dsl_service.py

@@ -1,5 +1,6 @@
 import logging
 import uuid
+from collections.abc import Mapping
 from enum import StrEnum
 from typing import Optional
 from urllib.parse import urlparse
@@ -256,6 +257,16 @@ class AppDslService:
             check_dependencies_pending_data = None
             if dependencies:
                 check_dependencies_pending_data = [PluginDependency.model_validate(d) for d in dependencies]
+            elif imported_version <= "0.1.5":
+                if "workflow" in data:
+                    graph = data.get("workflow", {}).get("graph", {})
+                    dependencies_list = self._extract_dependencies_from_workflow_graph(graph)
+                else:
+                    dependencies_list = self._extract_dependencies_from_model_config(data.get("model_config", {}))
+
+                check_dependencies_pending_data = DependenciesAnalysisService.generate_latest_dependencies(
+                    dependencies_list
+                )
 
             # Create or update app
             app = self._create_or_update_app(
@@ -558,7 +569,7 @@ class AppDslService:
             raise ValueError("Missing app configuration, please check.")
 
         export_data["model_config"] = app_model_config.to_dict()
-        dependencies = cls._extract_dependencies_from_model_config(app_model_config)
+        dependencies = cls._extract_dependencies_from_model_config(app_model_config.to_dict())
         export_data["dependencies"] = [
             jsonable_encoder(d.model_dump())
             for d in DependenciesAnalysisService.generate_dependencies(
@@ -574,6 +585,16 @@ class AppDslService:
         :return: dependencies list format like ["langgenius/google"]
         """
         graph = workflow.graph_dict
+        dependencies = cls._extract_dependencies_from_workflow_graph(graph)
+        return dependencies
+
+    @classmethod
+    def _extract_dependencies_from_workflow_graph(cls, graph: Mapping) -> list[str]:
+        """
+        Extract dependencies from workflow graph
+        :param graph: Workflow graph
+        :return: dependencies list format like ["langgenius/google"]
+        """
         dependencies = []
         for node in graph.get("nodes", []):
             try:
@@ -647,24 +668,24 @@ class AppDslService:
         return dependencies
 
     @classmethod
-    def _extract_dependencies_from_model_config(cls, model_config: AppModelConfig) -> list[str]:
+    def _extract_dependencies_from_model_config(cls, model_config: Mapping) -> list[str]:
         """
         Extract dependencies from model config
-        :param model_config: AppModelConfig instance
-        :return: dependencies list format like ["langgenius/google:1.0.0@abcdef1234567890"]
+        :param model_config: model config dict
+        :return: dependencies list format like ["langgenius/google"]
         """
         dependencies = []
 
         try:
             # completion model
-            model_dict = model_config.model_dict
+            model_dict = model_config.get("model", {})
             if model_dict:
                 dependencies.append(
                     DependenciesAnalysisService.analyze_model_provider_dependency(model_dict.get("provider", ""))
                 )
 
             # reranking model
-            dataset_configs = model_config.dataset_configs_dict
+            dataset_configs = model_config.get("dataset_configs", {})
             if dataset_configs:
                 for dataset_config in dataset_configs.get("datasets", {}).get("datasets", []):
                     if dataset_config.get("reranking_model"):
@@ -677,7 +698,7 @@ class AppDslService:
                         )
 
             # tools
-            agent_configs = model_config.agent_mode_dict
+            agent_configs = model_config.get("agent_mode", {})
             if agent_configs:
                 for agent_config in agent_configs.get("tools", []):
                     dependencies.append(

api/services/dataset_service.py

@@ -13,10 +13,10 @@ from sqlalchemy.orm import Session
 from werkzeug.exceptions import NotFound
 
 from configs import dify_config
-from core.entities import DEFAULT_PLUGIN_ID
 from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
 from core.model_manager import ModelManager
 from core.model_runtime.entities.model_entities import ModelType
+from core.plugin.entities.plugin import ModelProviderID
 from core.rag.index_processor.constant.index_type import IndexType
 from core.rag.retrieval.retrieval_methods import RetrievalMethod
 from events.dataset_event import dataset_was_deleted
@@ -328,14 +328,10 @@ class DatasetService:
             else:
                 # add default plugin id to both setting sets, to make sure the plugin model provider is consistent
                 plugin_model_provider = dataset.embedding_model_provider
-                if "/" not in plugin_model_provider:
-                    plugin_model_provider = f"{DEFAULT_PLUGIN_ID}/{plugin_model_provider}/{plugin_model_provider}"
+                plugin_model_provider = str(ModelProviderID(plugin_model_provider))
 
                 new_plugin_model_provider = data["embedding_model_provider"]
-                if "/" not in new_plugin_model_provider:
-                    new_plugin_model_provider = (
-                        f"{DEFAULT_PLUGIN_ID}/{new_plugin_model_provider}/{new_plugin_model_provider}"
-                    )
+                new_plugin_model_provider = str(ModelProviderID(new_plugin_model_provider))
 
                 if (
                     new_plugin_model_provider != plugin_model_provider
@@ -979,6 +975,8 @@ class DocumentService:
                                     "notion_page_icon": page.page_icon.model_dump() if page.page_icon else None,
                                     "type": page.type,
                                 }
+                                # Truncate page name to 255 characters to prevent DB field length errors
+                                truncated_page_name = page.page_name[:255] if page.page_name else "nopagename"
                                 document = DocumentService.build_document(
                                     dataset,
                                     dataset_process_rule.id,  # type: ignore
@@ -989,7 +987,7 @@ class DocumentService:
                                     created_from,
                                     position,
                                     account,
-                                    page.page_name,
+                                    truncated_page_name,
                                     batch,
                                     knowledge_config.metadata,
                                 )

api/services/hit_testing_service.py

@@ -47,7 +47,7 @@ class HitTestingService:
         all_documents = RetrievalService.retrieve(
             retrieval_method=retrieval_model.get("search_method", "semantic_search"),
             dataset_id=dataset.id,
-            query=cls.escape_query_for_search(query),
+            query=query,
             top_k=retrieval_model.get("top_k", 2),
             score_threshold=retrieval_model.get("score_threshold", 0.0)
             if retrieval_model["score_threshold_enabled"]

api/services/message_service.py

@@ -46,6 +46,8 @@ class MessageService:
             app_model=app_model, user=user, conversation_id=conversation_id
         )
 
+        fetch_limit = limit + 1
+
         if first_id:
             first_message = (
                 db.session.query(Message)
@@ -64,7 +66,7 @@ class MessageService:
                     Message.id != first_message.id,
                 )
                 .order_by(Message.created_at.desc())
-                .limit(limit)
+                .limit(fetch_limit)
                 .all()
             )
         else:
@@ -72,25 +74,14 @@ class MessageService:
                 db.session.query(Message)
                 .filter(Message.conversation_id == conversation.id)
                 .order_by(Message.created_at.desc())
-                .limit(limit)
+                .limit(fetch_limit)
                 .all()
             )
 
         has_more = False
-        if len(history_messages) == limit:
-            current_page_first_message = history_messages[-1]
-            rest_count = (
-                db.session.query(Message)
-                .filter(
-                    Message.conversation_id == conversation.id,
-                    Message.created_at < current_page_first_message.created_at,
-                    Message.id != current_page_first_message.id,
-                )
-                .count()
-            )
-
-            if rest_count > 0:
-                has_more = True
+        if len(history_messages) > limit:
+            has_more = True
+            history_messages = history_messages[:-1]
 
         if order == "asc":
             history_messages = list(reversed(history_messages))
@@ -112,6 +103,8 @@ class MessageService:
 
         base_query = db.session.query(Message)
 
+        fetch_limit = limit + 1
+
         if conversation_id is not None:
             conversation = ConversationService.get_conversation(
                 app_model=app_model, user=user, conversation_id=conversation_id
@@ -131,21 +124,16 @@ class MessageService:
             history_messages = (
                 base_query.filter(Message.created_at < last_message.created_at, Message.id != last_message.id)
                 .order_by(Message.created_at.desc())
-                .limit(limit)
+                .limit(fetch_limit)
                 .all()
             )
         else:
-            history_messages = base_query.order_by(Message.created_at.desc()).limit(limit).all()
+            history_messages = base_query.order_by(Message.created_at.desc()).limit(fetch_limit).all()
 
         has_more = False
-        if len(history_messages) == limit:
-            current_page_first_message = history_messages[-1]
-            rest_count = base_query.filter(
-                Message.created_at < current_page_first_message.created_at, Message.id != current_page_first_message.id
-            ).count()
-
-            if rest_count > 0:
-                has_more = True
+        if len(history_messages) > limit:
+            has_more = True
+            history_messages = history_messages[:-1]
 
         return InfiniteScrollPagination(data=history_messages, limit=limit, has_more=has_more)
 

api/services/plugin/dependencies_analysis.py

@@ -1,4 +1,5 @@
-from core.plugin.entities.plugin import GenericProviderID, PluginDependency, PluginInstallationSource
+from core.helper import marketplace
+from core.plugin.entities.plugin import ModelProviderID, PluginDependency, PluginInstallationSource, ToolProviderID
 from core.plugin.manager.plugin import PluginInstallationManager
 
 
@@ -11,8 +12,7 @@ class DependenciesAnalysisService:
         Convert the tool id to the plugin_id
         """
         try:
-            tool_provider_id = GenericProviderID(tool_id)
-            return tool_provider_id.plugin_id
+            return ToolProviderID(tool_id).plugin_id
         except Exception as e:
             raise e
 
@@ -24,8 +24,7 @@ class DependenciesAnalysisService:
         Convert the model provider id to the plugin_id
         """
         try:
-            generic_provider_id = GenericProviderID(model_provider_id)
-            return generic_provider_id.plugin_id
+            return ModelProviderID(model_provider_id).plugin_id
         except Exception as e:
             raise e
 
@@ -39,15 +38,22 @@ class DependenciesAnalysisService:
             required_plugin_unique_identifiers.append(dependency.value.plugin_unique_identifier)
 
         manager = PluginInstallationManager()
-        missing_plugin_unique_identifiers = manager.fetch_missing_dependencies(
-            tenant_id, required_plugin_unique_identifiers
-        )
+
+        # get leaked dependencies
+        missing_plugins = manager.fetch_missing_dependencies(tenant_id, required_plugin_unique_identifiers)
+        missing_plugin_unique_identifiers = {plugin.plugin_unique_identifier: plugin for plugin in missing_plugins}
 
         leaked_dependencies = []
         for dependency in dependencies:
             unique_identifier = dependency.value.plugin_unique_identifier
             if unique_identifier in missing_plugin_unique_identifiers:
-                leaked_dependencies.append(dependency)
+                leaked_dependencies.append(
+                    PluginDependency(
+                        type=dependency.type,
+                        value=dependency.value,
+                        current_identifier=missing_plugin_unique_identifiers[unique_identifier].current_identifier,
+                    )
+                )
 
         return leaked_dependencies
 
@@ -98,3 +104,18 @@ class DependenciesAnalysisService:
                 raise ValueError(f"Unknown plugin source: {plugin.source}")
 
         return result
+
+    @classmethod
+    def generate_latest_dependencies(cls, dependencies: list[str]) -> list[PluginDependency]:
+        """
+        Generate the latest version of dependencies
+        """
+        dependencies = list(set(dependencies))
+        deps = marketplace.batch_fetch_plugin_manifests(dependencies)
+        return [
+            PluginDependency(
+                type=PluginDependency.Type.Marketplace,
+                value=PluginDependency.Marketplace(marketplace_plugin_unique_identifier=dep.latest_package_identifier),
+            )
+            for dep in deps
+        ]

api/services/plugin/plugin_migration.py

@@ -14,9 +14,8 @@ from flask import Flask, current_app
 from sqlalchemy.orm import Session
 
 from core.agent.entities import AgentToolEntity
-from core.entities import DEFAULT_PLUGIN_ID
 from core.helper import marketplace
-from core.plugin.entities.plugin import PluginInstallationSource
+from core.plugin.entities.plugin import ModelProviderID, PluginInstallationSource, ToolProviderID
 from core.plugin.entities.plugin_daemon import PluginInstallTaskStatus
 from core.plugin.manager.plugin import PluginInstallationManager
 from core.tools.entities.tool_entities import ToolProviderType
@@ -37,7 +36,6 @@ class PluginMigration:
         """
         Migrate plugin.
         """
-        import concurrent.futures
         from threading import Lock
 
         click.echo(click.style("Migrating models/tools to new plugin Mechanism", fg="white"))
@@ -54,7 +52,7 @@ class PluginMigration:
         file_lock = Lock()
         counter_lock = Lock()
 
-        thread_pool = concurrent.futures.ThreadPoolExecutor(max_workers=workers)
+        thread_pool = ThreadPoolExecutor(max_workers=workers)
 
         def process_tenant(flask_app: Flask, tenant_id: str) -> None:
             with flask_app.app_context():
@@ -204,13 +202,7 @@ class PluginMigration:
             result = []
             for row in rs:
                 provider_name = str(row[0])
-                if provider_name and "/" not in provider_name:
-                    if provider_name == "google":
-                        provider_name = "gemini"
-
-                    result.append(DEFAULT_PLUGIN_ID + "/" + provider_name)
-                elif provider_name:
-                    result.append(provider_name)
+                result.append(ModelProviderID(provider_name).plugin_id)
 
             return result
 
@@ -223,30 +215,10 @@ class PluginMigration:
             rs = session.query(BuiltinToolProvider).filter(BuiltinToolProvider.tenant_id == tenant_id).all()
             result = []
             for row in rs:
-                if "/" not in row.provider:
-                    result.append(DEFAULT_PLUGIN_ID + "/" + row.provider)
-                else:
-                    result.append(row.provider)
+                result.append(ToolProviderID(row.provider).plugin_id)
 
             return result
 
-    @classmethod
-    def _handle_builtin_tool_provider(cls, provider_name: str) -> str:
-        """
-        Handle builtin tool provider.
-        """
-        if provider_name == "jina":
-            provider_name = "jina_tool"
-        elif provider_name == "siliconflow":
-            provider_name = "siliconflow_tool"
-        elif provider_name == "stepfun":
-            provider_name = "stepfun_tool"
-
-        if "/" not in provider_name:
-            return DEFAULT_PLUGIN_ID + "/" + provider_name
-        else:
-            return provider_name
-
     @classmethod
     def extract_workflow_tables(cls, tenant_id: str) -> Sequence[str]:
         """
@@ -267,8 +239,7 @@ class PluginMigration:
                         provider_name = data.get("provider_name")
                         provider_type = data.get("provider_type")
                         if provider_name not in excluded_providers and provider_type == ToolProviderType.BUILT_IN.value:
-                            provider_name = cls._handle_builtin_tool_provider(provider_name)
-                            result.append(provider_name)
+                            result.append(ToolProviderID(provider_name).plugin_id)
 
             return result
 
@@ -299,7 +270,7 @@ class PluginMigration:
                                     tool_entity.provider_type == ToolProviderType.BUILT_IN.value
                                     and tool_entity.provider_id not in excluded_providers
                                 ):
-                                    result.append(cls._handle_builtin_tool_provider(tool_entity.provider_id))
+                                    result.append(ToolProviderID(tool_entity.provider_id).plugin_id)
 
                             except Exception:
                                 logger.exception(f"Failed to process tool {tool}")
@@ -340,10 +311,14 @@ class PluginMigration:
                         plugin_ids.append(plugin_id)
 
         def fetch_plugin(plugin_id):
-            unique_identifier = cls._fetch_plugin_unique_identifier(plugin_id)
-            if unique_identifier:
-                plugins[plugin_id] = unique_identifier
-            else:
+            try:
+                unique_identifier = cls._fetch_plugin_unique_identifier(plugin_id)
+                if unique_identifier:
+                    plugins[plugin_id] = unique_identifier
+                else:
+                    plugin_not_exist.append(plugin_id)
+            except Exception:
+                logger.exception(f"Failed to fetch plugin unique identifier for {plugin_id}")
                 plugin_not_exist.append(plugin_id)
 
         with ThreadPoolExecutor(max_workers=10) as executor:
@@ -352,7 +327,7 @@ class PluginMigration:
         return {"plugins": plugins, "plugin_not_exist": plugin_not_exist}
 
     @classmethod
-    def install_plugins(cls, extracted_plugins: str, output_file: str) -> None:
+    def install_plugins(cls, extracted_plugins: str, output_file: str, workers: int = 100) -> None:
         """
         Install plugins.
         """
@@ -366,7 +341,7 @@ class PluginMigration:
         fake_tenant_id = uuid4().hex
         logger.info(f"Installing {len(plugins['plugins'])} plugin instances for fake tenant {fake_tenant_id}")
 
-        thread_pool = ThreadPoolExecutor(max_workers=40)
+        thread_pool = ThreadPoolExecutor(max_workers=workers)
 
         response = cls.handle_plugin_instance_install(fake_tenant_id, plugins["plugins"])
         if response.get("failed"):
@@ -374,10 +349,17 @@ class PluginMigration:
 
         def install(tenant_id: str, plugin_ids: list[str]) -> None:
             logger.info(f"Installing {len(plugin_ids)} plugins for tenant {tenant_id}")
+            # fetch plugin already installed
+            installed_plugins = manager.list_plugins(tenant_id)
+            installed_plugins_ids = [plugin.plugin_id for plugin in installed_plugins]
             # at most 64 plugins one batch
             for i in range(0, len(plugin_ids), 64):
                 batch_plugin_ids = plugin_ids[i : i + 64]
-                batch_plugin_identifiers = [plugins["plugins"][plugin_id] for plugin_id in batch_plugin_ids]
+                batch_plugin_identifiers = [
+                    plugins["plugins"][plugin_id]
+                    for plugin_id in batch_plugin_ids
+                    if plugin_id not in installed_plugins_ids and plugin_id in plugins["plugins"]
+                ]
                 manager.install_from_identifiers(
                     tenant_id,
                     batch_plugin_identifiers,
@@ -472,9 +454,9 @@ class PluginMigration:
 
         reverse_map = {v: k for k, v in plugin_identifiers_map.items()}
 
-        # at most 64 plugins one batch
-        for i in range(0, len(plugin_identifiers_map), 64):
-            batch_plugin_ids = list(plugin_identifiers_map.keys())[i : i + 64]
+        # at most 8 plugins one batch
+        for i in range(0, len(plugin_identifiers_map), 8):
+            batch_plugin_ids = list(plugin_identifiers_map.keys())[i : i + 8]
             batch_plugin_identifiers = [plugin_identifiers_map[plugin_id] for plugin_id in batch_plugin_ids]
 
             try:

api/services/tools/builtin_tools_manage_service.py

@@ -233,56 +233,57 @@ class BuiltinToolManageService:
         # get all builtin providers
         provider_controllers = ToolManager.list_builtin_providers(tenant_id)
 
-        # get all user added providers
-        db_providers: list[BuiltinToolProvider] = (
-            db.session.query(BuiltinToolProvider).filter(BuiltinToolProvider.tenant_id == tenant_id).all() or []
-        )
+        with db.session.no_autoflush:
+            # get all user added providers
+            db_providers: list[BuiltinToolProvider] = (
+                db.session.query(BuiltinToolProvider).filter(BuiltinToolProvider.tenant_id == tenant_id).all() or []
+            )
 
-        # rewrite db_providers
-        for db_provider in db_providers:
-            db_provider.provider = str(ToolProviderID(db_provider.provider))
+            # rewrite db_providers
+            for db_provider in db_providers:
+                db_provider.provider = str(ToolProviderID(db_provider.provider))
 
-        # find provider
-        def find_provider(provider):
-            return next(filter(lambda db_provider: db_provider.provider == provider, db_providers), None)
+            # find provider
+            def find_provider(provider):
+                return next(filter(lambda db_provider: db_provider.provider == provider, db_providers), None)
 
-        result: list[ToolProviderApiEntity] = []
+            result: list[ToolProviderApiEntity] = []
 
-        for provider_controller in provider_controllers:
-            try:
-                # handle include, exclude
-                if is_filtered(
-                    include_set=dify_config.POSITION_TOOL_INCLUDES_SET,  # type: ignore
-                    exclude_set=dify_config.POSITION_TOOL_EXCLUDES_SET,  # type: ignore
-                    data=provider_controller,
-                    name_func=lambda x: x.identity.name,
-                ):
-                    continue
+            for provider_controller in provider_controllers:
+                try:
+                    # handle include, exclude
+                    if is_filtered(
+                        include_set=dify_config.POSITION_TOOL_INCLUDES_SET,  # type: ignore
+                        exclude_set=dify_config.POSITION_TOOL_EXCLUDES_SET,  # type: ignore
+                        data=provider_controller,
+                        name_func=lambda x: x.identity.name,
+                    ):
+                        continue
 
-                # convert provider controller to user provider
-                user_builtin_provider = ToolTransformService.builtin_provider_to_user_provider(
-                    provider_controller=provider_controller,
-                    db_provider=find_provider(provider_controller.entity.identity.name),
-                    decrypt_credentials=True,
-                )
-
-                # add icon
-                ToolTransformService.repack_provider(tenant_id=tenant_id, provider=user_builtin_provider)
-
-                tools = provider_controller.get_tools()
-                for tool in tools or []:
-                    user_builtin_provider.tools.append(
-                        ToolTransformService.convert_tool_entity_to_api_entity(
-                            tenant_id=tenant_id,
-                            tool=tool,
-                            credentials=user_builtin_provider.original_credentials,
-                            labels=ToolLabelManager.get_tool_labels(provider_controller),
-                        )
+                    # convert provider controller to user provider
+                    user_builtin_provider = ToolTransformService.builtin_provider_to_user_provider(
+                        provider_controller=provider_controller,
+                        db_provider=find_provider(provider_controller.entity.identity.name),
+                        decrypt_credentials=True,
                     )
 
-                result.append(user_builtin_provider)
-            except Exception as e:
-                raise e
+                    # add icon
+                    ToolTransformService.repack_provider(tenant_id=tenant_id, provider=user_builtin_provider)
+
+                    tools = provider_controller.get_tools()
+                    for tool in tools or []:
+                        user_builtin_provider.tools.append(
+                            ToolTransformService.convert_tool_entity_to_api_entity(
+                                tenant_id=tenant_id,
+                                tool=tool,
+                                credentials=user_builtin_provider.original_credentials,
+                                labels=ToolLabelManager.get_tool_labels(provider_controller),
+                            )
+                        )
+
+                    result.append(user_builtin_provider)
+                except Exception as e:
+                    raise e
 
         return BuiltinToolProviderSort.sort(result)
 

api/tests/integration_tests/vdb/tidb_vector/check_tiflash_ready.py

@@ -0,0 +1,59 @@
+import time
+
+import pymysql
+
+
+def check_tiflash_ready() -> bool:
+    try:
+        connection = pymysql.connect(
+            host="localhost",
+            port=4000,
+            user="root",
+            password="",
+        )
+
+        with connection.cursor() as cursor:
+            # Doc reference:
+            # https://docs.pingcap.com/zh/tidb/stable/information-schema-cluster-hardware
+            select_tiflash_query = """
+            SELECT * FROM information_schema.cluster_hardware
+            WHERE TYPE='tiflash'
+            LIMIT 1;
+            """
+            cursor.execute(select_tiflash_query)
+            result = cursor.fetchall()
+            return result is not None and len(result) > 0
+    except Exception as e:
+        print(f"TiFlash is not ready. Exception: {e}")
+        return False
+    finally:
+        if connection:
+            connection.close()
+
+
+def main():
+    max_attempts = 30
+    retry_interval_seconds = 2
+    is_tiflash_ready = False
+    for attempt in range(max_attempts):
+        try:
+            is_tiflash_ready = check_tiflash_ready()
+        except Exception as e:
+            print(f"TiFlash is not ready. Exception: {e}")
+            is_tiflash_ready = False
+
+        if is_tiflash_ready:
+            break
+        else:
+            print(f"Attempt {attempt + 1} failed，retry in {retry_interval_seconds} seconds...")
+            time.sleep(retry_interval_seconds)
+
+    if is_tiflash_ready:
+        print("TiFlash is ready in TiDB.")
+    else:
+        print(f"TiFlash is not ready in TiDB after {max_attempts} attempting checks.")
+        exit(1)
+
+
+if __name__ == "__main__":
+    main()

api/tests/unit_tests/core/workflow/nodes/test_document_extractor_node.py

@@ -8,7 +8,7 @@ from core.variables.variables import StringVariable
 from core.workflow.entities.node_entities import NodeRunResult
 from core.workflow.nodes.document_extractor import DocumentExtractorNode, DocumentExtractorNodeData
 from core.workflow.nodes.document_extractor.node import (
-    _extract_text_from_doc,
+    _extract_text_from_docx,
     _extract_text_from_pdf,
     _extract_text_from_plain_text,
 )
@@ -120,7 +120,7 @@ def test_run_extract_text(
         monkeypatch.setattr("core.workflow.nodes.document_extractor.node._extract_text_from_pdf", mock_pdf_extract)
     elif mime_type.startswith("application/vnd.openxmlformats"):
         mock_docx_extract = Mock(return_value=expected_text[0])
-        monkeypatch.setattr("core.workflow.nodes.document_extractor.node._extract_text_from_doc", mock_docx_extract)
+        monkeypatch.setattr("core.workflow.nodes.document_extractor.node._extract_text_from_docx", mock_docx_extract)
 
     result = document_extractor_node._run()
 
@@ -163,14 +163,14 @@ def test_extract_text_from_pdf(mock_pdf_document):
 
 
 @patch("docx.Document")
-def test_extract_text_from_doc(mock_document):
+def test_extract_text_from_docx(mock_document):
     mock_paragraph1 = Mock()
     mock_paragraph1.text = "Paragraph 1"
     mock_paragraph2 = Mock()
     mock_paragraph2.text = "Paragraph 2"
     mock_document.return_value.paragraphs = [mock_paragraph1, mock_paragraph2]
 
-    text = _extract_text_from_doc(b"PK\x03\x04")
+    text = _extract_text_from_docx(b"PK\x03\x04")
     assert text == "Paragraph 1\nParagraph 2"
 
 

docker/.env.example

@@ -887,6 +887,10 @@ SSRF_HTTP_PORT=3128
 SSRF_COREDUMP_DIR=/var/spool/squid
 SSRF_REVERSE_PROXY_PORT=8194
 SSRF_SANDBOX_HOST=sandbox
+SSRF_DEFAULT_TIME_OUT=5
+SSRF_DEFAULT_CONNECT_TIME_OUT=5
+SSRF_DEFAULT_READ_TIME_OUT=5
+SSRF_DEFAULT_WRITE_TIME_OUT=5
 
 # ------------------------------
 # docker env var for specifying vector db type at startup

docker/docker-compose-template.yaml

@@ -64,6 +64,7 @@ services:
       MARKETPLACE_URL: ${MARKETPLACE_URL:-https://marketplace.dify.ai}
       TOP_K_MAX_VALUE: ${TOP_K_MAX_VALUE:-}
       INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH: ${INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH:-}
+      PM2_INSTANCES: ${PM2_INSTANCES:-2}
 
   # The postgres database.
   db:
@@ -121,6 +122,7 @@ services:
       SANDBOX_PORT: ${SANDBOX_PORT:-8194}
     volumes:
       - ./volumes/sandbox/dependencies:/dependencies
+      - ./volumes/sandbox/conf:/conf
     healthcheck:
       test: [ 'CMD', 'curl', '-f', 'http://localhost:8194/health' ]
     networks:
@@ -128,7 +130,7 @@ services:
 
   # plugin daemon
   plugin_daemon:
-    image: langgenius/dify-plugin-daemon:0.0.1-local
+    image: langgenius/dify-plugin-daemon:0.0.3-local
     restart: always
     environment:
       # Use the shared environment variables.
@@ -231,16 +233,6 @@ services:
       - '${EXPOSE_NGINX_PORT:-80}:${NGINX_PORT:-80}'
       - '${EXPOSE_NGINX_SSL_PORT:-443}:${NGINX_SSL_PORT:-443}'
 
-  # The TiDB vector store.
-  # For production use, please refer to https://github.com/pingcap/tidb-docker-compose
-  tidb:
-    image: pingcap/tidb:v8.4.0
-    profiles:
-      - tidb
-    command:
-      - --store=unistore
-    restart: always
-
   # The Weaviate vector store.
   weaviate:
     image: semitechnologies/weaviate:1.19.0

docker/docker-compose.middleware.yaml

@@ -66,7 +66,7 @@ services:
 
   # plugin daemon
   plugin_daemon:
-    image: langgenius/dify-plugin-daemon:0.0.1-local
+    image: langgenius/dify-plugin-daemon:0.0.3-local
     restart: always
     environment:
       # Use the shared environment variables.

docker/docker-compose.yaml

@@ -377,6 +377,10 @@ x-shared-env: &shared-api-worker-env
   SSRF_COREDUMP_DIR: ${SSRF_COREDUMP_DIR:-/var/spool/squid}
   SSRF_REVERSE_PROXY_PORT: ${SSRF_REVERSE_PROXY_PORT:-8194}
   SSRF_SANDBOX_HOST: ${SSRF_SANDBOX_HOST:-sandbox}
+  SSRF_DEFAULT_TIME_OUT: ${SSRF_DEFAULT_TIME_OUT:-5}
+  SSRF_DEFAULT_CONNECT_TIME_OUT: ${SSRF_DEFAULT_CONNECT_TIME_OUT:-5}
+  SSRF_DEFAULT_READ_TIME_OUT: ${SSRF_DEFAULT_READ_TIME_OUT:-5}
+  SSRF_DEFAULT_WRITE_TIME_OUT: ${SSRF_DEFAULT_WRITE_TIME_OUT:-5}
   EXPOSE_NGINX_PORT: ${EXPOSE_NGINX_PORT:-80}
   EXPOSE_NGINX_SSL_PORT: ${EXPOSE_NGINX_SSL_PORT:-443}
   POSITION_TOOL_PINS: ${POSITION_TOOL_PINS:-}
@@ -472,6 +476,7 @@ services:
       MARKETPLACE_URL: ${MARKETPLACE_URL:-https://marketplace.dify.ai}
       TOP_K_MAX_VALUE: ${TOP_K_MAX_VALUE:-}
       INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH: ${INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH:-}
+      PM2_INSTANCES: ${PM2_INSTANCES:-2}
 
   # The postgres database.
   db:
@@ -529,6 +534,7 @@ services:
       SANDBOX_PORT: ${SANDBOX_PORT:-8194}
     volumes:
       - ./volumes/sandbox/dependencies:/dependencies
+      - ./volumes/sandbox/conf:/conf
     healthcheck:
       test: [ 'CMD', 'curl', '-f', 'http://localhost:8194/health' ]
     networks:
@@ -536,7 +542,7 @@ services:
 
   # plugin daemon
   plugin_daemon:
-    image: langgenius/dify-plugin-daemon:0.0.1-local
+    image: langgenius/dify-plugin-daemon:0.0.3-local
     restart: always
     environment:
       # Use the shared environment variables.
@@ -639,16 +645,6 @@ services:
       - '${EXPOSE_NGINX_PORT:-80}:${NGINX_PORT:-80}'
       - '${EXPOSE_NGINX_SSL_PORT:-443}:${NGINX_SSL_PORT:-443}'
 
-  # The TiDB vector store.
-  # For production use, please refer to https://github.com/pingcap/tidb-docker-compose
-  tidb:
-    image: pingcap/tidb:v8.4.0
-    profiles:
-      - tidb
-    command:
-      - --store=unistore
-    restart: always
-
   # The Weaviate vector store.
   weaviate:
     image: semitechnologies/weaviate:1.19.0