From dd089573817205ff039debbbab05d20f4df491c2 Mon Sep 17 00:00:00 2001 From: Jyong <76649700+JohnJyong@users.noreply.github.com> Date: Tue, 23 Sep 2025 16:40:26 +0800 Subject: [PATCH 01/11] fix full_text_search name (#26104) --- api/core/workflow/nodes/knowledge_index/entities.py | 2 +- .../entities/knowledge_entities/rag_pipeline_entities.py | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/api/core/workflow/nodes/knowledge_index/entities.py b/api/core/workflow/nodes/knowledge_index/entities.py index 2a2e983a0c..c79373afd5 100644 --- a/api/core/workflow/nodes/knowledge_index/entities.py +++ b/api/core/workflow/nodes/knowledge_index/entities.py @@ -63,7 +63,7 @@ class RetrievalSetting(BaseModel): Retrieval Setting. """ - search_method: Literal["semantic_search", "keyword_search", "fulltext_search", "hybrid_search"] + search_method: Literal["semantic_search", "keyword_search", "full_text_search", "hybrid_search"] top_k: int score_threshold: float | None = 0.5 score_threshold_enabled: bool = False diff --git a/api/services/entities/knowledge_entities/rag_pipeline_entities.py b/api/services/entities/knowledge_entities/rag_pipeline_entities.py index ac96b5c8ad..860bfde401 100644 --- a/api/services/entities/knowledge_entities/rag_pipeline_entities.py +++ b/api/services/entities/knowledge_entities/rag_pipeline_entities.py @@ -83,7 +83,7 @@ class RetrievalSetting(BaseModel): Retrieval Setting. """ - search_method: Literal["semantic_search", "fulltext_search", "keyword_search", "hybrid_search"] + search_method: Literal["semantic_search", "full_text_search", "keyword_search", "hybrid_search"] top_k: int score_threshold: float | None = 0.5 score_threshold_enabled: bool = False From 8b74ae683a0a242e70c58d0dee247e00127ed7ae Mon Sep 17 00:00:00 2001 From: 17hz <0x149527@gmail.com> Date: Tue, 23 Sep 2025 16:59:26 +0800 Subject: [PATCH 02/11] bump nextjs to 15.5 and turbopack for development mode (#24346) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Co-authored-by: crazywoola <427733928@qq.com> Co-authored-by: 非法操作 --- web/app/styles/globals.css | 14 ++-- web/next.config.js | 14 ++-- web/package.json | 4 +- web/pnpm-lock.yaml | 129 +++++++++++++++++++++---------------- web/tsconfig.json | 3 + 5 files changed, 96 insertions(+), 68 deletions(-) diff --git a/web/app/styles/globals.css b/web/app/styles/globals.css index 353cfa2fff..c1078b6eb6 100644 --- a/web/app/styles/globals.css +++ b/web/app/styles/globals.css @@ -1,12 +1,18 @@ @import "preflight.css"; -@tailwind base; -@tailwind components; + @import '../../themes/light.css'; @import '../../themes/dark.css'; @import "../../themes/manual-light.css"; @import "../../themes/manual-dark.css"; +@import "../components/base/button/index.css"; +@import "../components/base/action-button/index.css"; +@import "../components/base/modal/index.css"; + +@tailwind base; +@tailwind components; + html { color-scheme: light; } @@ -680,10 +686,6 @@ button:focus-within { display: none; } -@import "../components/base/button/index.css"; -@import "../components/base/action-button/index.css"; -@import "../components/base/modal/index.css"; - @tailwind utilities; @layer utilities { diff --git a/web/next.config.js b/web/next.config.js index 7e89c33e62..9c5e331f34 100644 --- a/web/next.config.js +++ b/web/next.config.js @@ -91,12 +91,10 @@ const remoteImageURLs = [hasSetWebPrefix ? new URL(`${process.env.NEXT_PUBLIC_WE /** @type {import('next').NextConfig} */ const nextConfig = { basePath: process.env.NEXT_PUBLIC_BASE_PATH || '', - webpack: (config, { dev, isServer }) => { - if (dev) { - config.plugins.push(codeInspectorPlugin({ bundler: 'webpack' })) - } - - return config + turbopack: { + rules: codeInspectorPlugin({ + bundler: 'turbopack' + }) }, productionBrowserSourceMaps: false, // enable browser source map generation during the production build // Configure pageExtensions to include md and mdx @@ -112,6 +110,10 @@ const nextConfig = { })), }, experimental: { + optimizePackageImports: [ + '@remixicon/react', + '@heroicons/react' + ], }, // fix all before production. Now it slow the develop speed. eslint: { diff --git a/web/package.json b/web/package.json index 57ab734eb2..78e62c9aa7 100644 --- a/web/package.json +++ b/web/package.json @@ -19,7 +19,7 @@ "and_qq >= 14.9" ], "scripts": { - "dev": "cross-env NODE_OPTIONS='--inspect' next dev", + "dev": "cross-env NODE_OPTIONS='--inspect' next dev --turbopack", "build": "next build", "build:docker": "next build && node scripts/optimize-standalone.js", "start": "cp -r .next/static .next/standalone/.next/static && cp -r public .next/standalone/public && cross-env PORT=$npm_config_port HOSTNAME=$npm_config_host node .next/standalone/server.js", @@ -203,7 +203,7 @@ "autoprefixer": "^10.4.20", "babel-loader": "^10.0.0", "bing-translate-api": "^4.0.2", - "code-inspector-plugin": "^0.18.1", + "code-inspector-plugin": "1.2.9", "cross-env": "^7.0.3", "eslint": "^9.35.0", "eslint-config-next": "15.5.0", diff --git a/web/pnpm-lock.yaml b/web/pnpm-lock.yaml index 5d4308288c..e47985fd71 100644 --- a/web/pnpm-lock.yaml +++ b/web/pnpm-lock.yaml @@ -519,8 +519,8 @@ importers: specifier: ^4.0.2 version: 4.1.0 code-inspector-plugin: - specifier: ^0.18.1 - version: 0.18.3 + specifier: 1.2.9 + version: 1.2.9 cross-env: specifier: ^7.0.3 version: 7.0.3 @@ -1372,6 +1372,24 @@ packages: '@clack/prompts@0.11.0': resolution: {integrity: sha512-pMN5FcrEw9hUkZA4f+zLlzivQSeQf5dRGJjSUbvVYDLvpKCdQx5OaknvKzgbtXOizhP+SJJJjqEbOe55uKKfAw==} + '@code-inspector/core@1.2.9': + resolution: {integrity: sha512-A1w+G73HlTB6S8X6sA6tT+ziWHTAcTyH+7FZ1Sgd3ZLXF/E/jT+hgRbKposjXMwxcbodRc6hBG6UyiV+VxwE6Q==} + + '@code-inspector/esbuild@1.2.9': + resolution: {integrity: sha512-DuyfxGupV43CN8YElIqynAniBtE86i037+3OVJYrm3jlJscXzbV98/kOzvu+VJQQvElcDgpgD6C/aGmPvFEiUg==} + + '@code-inspector/mako@1.2.9': + resolution: {integrity: sha512-8N+MHdr64AnthLB4v+YGe8/9bgog3BnkxIW/fqX5iVS0X06mF7X1pxfZOD2bABVtv1tW25lRtNs5AgvYJs0vpg==} + + '@code-inspector/turbopack@1.2.9': + resolution: {integrity: sha512-UVOUbqU6rpi5eOkrFamKrdeSWb0/OFFJQBaxbgs1RK5V5f4/iVwC5KjO2wkjv8cOGU4EppLfBVSBI1ysOo8S5A==} + + '@code-inspector/vite@1.2.9': + resolution: {integrity: sha512-saIokJ3o3SdrHEgTEg1fbbowbKfh7J4mYtu0i1mVfah1b1UfdCF/iFHTEJ6SADMiY47TeNZTg0TQWTlU1AWPww==} + + '@code-inspector/webpack@1.2.9': + resolution: {integrity: sha512-9YEykVrOIc0zMV7pyTyZhCprjScjn6gPPmxb4/OQXKCrP2fAm+NB188rg0s95e4sM7U3qRUpPA4NUH5F7Ogo+g==} + '@cspotcode/source-map-support@0.8.1': resolution: {integrity: sha512-IchNf6dN4tHoMFIn/7OE8LWZ19Y6q/67Bmf6vnGREv8RSbBVb9LPJxEcnwrcwX6ixSvaiGoomAUvu4YSxXrVgw==} engines: {node: '>=12'} @@ -4425,11 +4443,8 @@ packages: resolution: {integrity: sha512-QVb0dM5HvG+uaxitm8wONl7jltx8dqhfU33DcqtOZcLSVIKSDDLDi7+0LbAKiyI8hD9u42m2YxXSkMGWThaecQ==} engines: {iojs: '>= 1.0.0', node: '>= 0.12.0'} - code-inspector-core@0.18.3: - resolution: {integrity: sha512-60pT2cPoguMTUYdN1MMpjoPUnuF0ud/u7M2y+Vqit/bniLEit9dySEWAVxLU/Ukc5ILrDeLKEttc6fCMl9RUrA==} - - code-inspector-plugin@0.18.3: - resolution: {integrity: sha512-d9oJXZUsnvfTaQDwFmDNA2F+AR/TXIxWg1rr8KGcEskltR2prbZsfuu1z70EAn4khpx0smfi/PvIIwNJQ7FAMw==} + code-inspector-plugin@1.2.9: + resolution: {integrity: sha512-PGp/AQ03vaajimG9rn5+eQHGifrym5CSNLCViPtwzot7FM3MqEkGNqcvimH0FVuv3wDOcP5KvETAUSLf1BE3HA==} collapse-white-space@2.1.0: resolution: {integrity: sha512-loKTxY1zCOuG4j9f6EPnuyyYkf58RnhhWTvRoZEokgB+WbdXehfjFviyOVYkqzEWz1Q5kRiZdBYS5SwxbQYwzw==} @@ -5055,9 +5070,6 @@ packages: esast-util-from-js@2.0.1: resolution: {integrity: sha512-8Ja+rNJ0Lt56Pcf3TAmpBZjmx8ZcK5Ts4cAzIOjsjevg9oSXJnl6SUQ2EevU8tv3h6ZLWmoKL5H4fgWvdvfETw==} - esbuild-code-inspector-plugin@0.18.3: - resolution: {integrity: sha512-FaPt5eFMtW1oXMWqAcqfAJByNagP1V/R9dwDDLQO29JmryMF35+frskTqy+G53whmTaVi19+TCrFqhNbMZH5ZQ==} - esbuild-register@3.6.0: resolution: {integrity: sha512-H2/S7Pm8a9CL1uhp9OvjwrBh5Pvx0H8qVOxNu8Wed9Y7qv56MPtq+GGM8RJpq6glYJn9Wspr8uw7l55uyinNeg==} peerDependencies: @@ -6413,8 +6425,8 @@ packages: resolution: {integrity: sha512-MbjN408fEndfiQXbFQ1vnd+1NoLDsnQW41410oQBXiyXDMYH5z505juWa4KUE1LqxRC7DgOgZDbKLxHIwm27hA==} engines: {node: '>=0.10'} - launch-ide@1.0.1: - resolution: {integrity: sha512-U7qBxSNk774PxWq4XbmRe0ThiIstPoa4sMH/OGSYxrFVvg8x3biXcF1fsH6wasDpEmEXMdINUrQhBdwsSgKyMg==} + launch-ide@1.2.0: + resolution: {integrity: sha512-7nXSPQOt3b2JT52Ge8jp4miFcY+nrUEZxNLWBzrEfjmByDTb9b5ytqMSwGhsNwY6Cntwop+6n7rWIFN0+S8PTw==} layout-base@1.0.2: resolution: {integrity: sha512-8h2oVEZNktL4BH2JCOI90iD1yXwL6iNW7KcCKT2QZgQJR2vbqDsldCTPRU9NifTCqHZci57XvQQ15YTu+sTYPg==} @@ -8693,9 +8705,6 @@ packages: vfile@6.0.3: resolution: {integrity: sha512-KzIbH/9tXat2u30jf+smMwFCsno4wHVdNmzFyL+T/L3UGqqk6JKfVqOFOZEpZSHADH1k40ab6NUIXZq422ov3Q==} - vite-code-inspector-plugin@0.18.3: - resolution: {integrity: sha512-178H73vbDUHE+JpvfAfioUHlUr7qXCYIEa2YNXtzenFQGOjtae59P1jjcxGfa6pPHEnOoaitb13K+0qxwhi/WA==} - vm-browserify@1.1.2: resolution: {integrity: sha512-2ham8XPWTONajOR0ohOKOHXkm3+gaBmGut3SRuu75xLd/RRaY6vqgh8NBYYk7+RW3u5AtzPQZG8F10LHkl0lAQ==} @@ -8754,9 +8763,6 @@ packages: engines: {node: '>= 10.13.0'} hasBin: true - webpack-code-inspector-plugin@0.18.3: - resolution: {integrity: sha512-3782rsJhBnRiw0IpR6EqnyGDQoiSq0CcGeLJ52rZXlszYCe8igXtcujq7OhI0byaivWQ1LW7sXKyMEoVpBhq0w==} - webpack-dev-middleware@6.1.3: resolution: {integrity: sha512-A4ChP0Qj8oGociTs6UdlRUGANIGrCDL3y+pmQMc+dSsraXHCatFpmMey4mYELA+juqwUqwQsUgJJISXl1KWmiw==} engines: {node: '>= 14.15.0'} @@ -9993,6 +9999,48 @@ snapshots: picocolors: 1.1.1 sisteransi: 1.0.5 + '@code-inspector/core@1.2.9': + dependencies: + '@vue/compiler-dom': 3.5.17 + chalk: 4.1.2 + dotenv: 16.6.1 + launch-ide: 1.2.0 + portfinder: 1.0.37 + transitivePeerDependencies: + - supports-color + + '@code-inspector/esbuild@1.2.9': + dependencies: + '@code-inspector/core': 1.2.9 + transitivePeerDependencies: + - supports-color + + '@code-inspector/mako@1.2.9': + dependencies: + '@code-inspector/core': 1.2.9 + transitivePeerDependencies: + - supports-color + + '@code-inspector/turbopack@1.2.9': + dependencies: + '@code-inspector/core': 1.2.9 + '@code-inspector/webpack': 1.2.9 + transitivePeerDependencies: + - supports-color + + '@code-inspector/vite@1.2.9': + dependencies: + '@code-inspector/core': 1.2.9 + chalk: 4.1.1 + transitivePeerDependencies: + - supports-color + + '@code-inspector/webpack@1.2.9': + dependencies: + '@code-inspector/core': 1.2.9 + transitivePeerDependencies: + - supports-color + '@cspotcode/source-map-support@0.8.1': dependencies: '@jridgewell/trace-mapping': 0.3.9 @@ -12799,7 +12847,7 @@ snapshots: '@vue/compiler-core@3.5.17': dependencies: - '@babel/parser': 7.28.0 + '@babel/parser': 7.28.4 '@vue/shared': 3.5.17 entities: 4.5.0 estree-walker: 2.0.2 @@ -13503,24 +13551,15 @@ snapshots: co@4.6.0: {} - code-inspector-core@0.18.3: + code-inspector-plugin@1.2.9: dependencies: - '@vue/compiler-dom': 3.5.17 + '@code-inspector/core': 1.2.9 + '@code-inspector/esbuild': 1.2.9 + '@code-inspector/mako': 1.2.9 + '@code-inspector/turbopack': 1.2.9 + '@code-inspector/vite': 1.2.9 + '@code-inspector/webpack': 1.2.9 chalk: 4.1.1 - dotenv: 16.6.1 - launch-ide: 1.0.1 - portfinder: 1.0.37 - transitivePeerDependencies: - - supports-color - - code-inspector-plugin@0.18.3: - dependencies: - chalk: 4.1.1 - code-inspector-core: 0.18.3 - dotenv: 16.6.1 - esbuild-code-inspector-plugin: 0.18.3 - vite-code-inspector-plugin: 0.18.3 - webpack-code-inspector-plugin: 0.18.3 transitivePeerDependencies: - supports-color @@ -14160,12 +14199,6 @@ snapshots: esast-util-from-estree: 2.0.0 vfile-message: 4.0.2 - esbuild-code-inspector-plugin@0.18.3: - dependencies: - code-inspector-core: 0.18.3 - transitivePeerDependencies: - - supports-color - esbuild-register@3.6.0(esbuild@0.25.0): dependencies: debug: 4.4.1 @@ -16020,7 +16053,7 @@ snapshots: dependencies: language-subtag-registry: 0.3.23 - launch-ide@1.0.1: + launch-ide@1.2.0: dependencies: chalk: 4.1.2 dotenv: 16.6.1 @@ -18779,12 +18812,6 @@ snapshots: '@types/unist': 3.0.3 vfile-message: 4.0.2 - vite-code-inspector-plugin@0.18.3: - dependencies: - code-inspector-core: 0.18.3 - transitivePeerDependencies: - - supports-color - vm-browserify@1.1.2: {} void-elements@3.1.0: {} @@ -18855,12 +18882,6 @@ snapshots: - bufferutil - utf-8-validate - webpack-code-inspector-plugin@0.18.3: - dependencies: - code-inspector-core: 0.18.3 - transitivePeerDependencies: - - supports-color - webpack-dev-middleware@6.1.3(webpack@5.100.2(esbuild@0.25.0)(uglify-js@3.19.3)): dependencies: colorette: 2.0.20 diff --git a/web/tsconfig.json b/web/tsconfig.json index c3e0bca665..3b022e4708 100644 --- a/web/tsconfig.json +++ b/web/tsconfig.json @@ -26,6 +26,9 @@ "paths": { "@/*": [ "./*" + ], + "~@/*": [ + "./*" ] } }, From fb6ccccc3da48739c20ce0d8a4bee9fa8ad89908 Mon Sep 17 00:00:00 2001 From: GuanMu Date: Tue, 23 Sep 2025 17:04:56 +0800 Subject: [PATCH 03/11] chore: refactor component exports for consistency (#26033) Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> --- web/app/components/app/log/list.tsx | 2 +- web/app/components/base/copy-icon/index.tsx | 2 +- web/app/components/base/markdown-blocks/think-block.tsx | 2 +- web/app/components/base/svg-gallery/index.tsx | 2 +- .../json-schema-config-modal/json-schema-generator/index.tsx | 2 +- 5 files changed, 5 insertions(+), 5 deletions(-) diff --git a/web/app/components/app/log/list.tsx b/web/app/components/app/log/list.tsx index b73d1f19de..8b3370b678 100644 --- a/web/app/components/app/log/list.tsx +++ b/web/app/components/app/log/list.tsx @@ -35,7 +35,7 @@ import { useStore as useAppStore } from '@/app/components/app/store' import { useAppContext } from '@/context/app-context' import useTimestamp from '@/hooks/use-timestamp' import Tooltip from '@/app/components/base/tooltip' -import { CopyIcon } from '@/app/components/base/copy-icon' +import CopyIcon from '@/app/components/base/copy-icon' import { buildChatItemTree, getThreadMessages } from '@/app/components/base/chat/utils' import { getProcessedFilesFromResponse } from '@/app/components/base/file-uploader/utils' import cn from '@/utils/classnames' diff --git a/web/app/components/base/copy-icon/index.tsx b/web/app/components/base/copy-icon/index.tsx index 196e256978..158eaa5fbe 100644 --- a/web/app/components/base/copy-icon/index.tsx +++ b/web/app/components/base/copy-icon/index.tsx @@ -15,7 +15,7 @@ type Props = { const prefixEmbedded = 'appOverview.overview.appInfo.embedded' -export const CopyIcon = ({ content }: Props) => { +const CopyIcon = ({ content }: Props) => { const { t } = useTranslation() const [isCopied, setIsCopied] = useState(false) diff --git a/web/app/components/base/markdown-blocks/think-block.tsx b/web/app/components/base/markdown-blocks/think-block.tsx index a5813266f1..acceecd433 100644 --- a/web/app/components/base/markdown-blocks/think-block.tsx +++ b/web/app/components/base/markdown-blocks/think-block.tsx @@ -63,7 +63,7 @@ const useThinkTimer = (children: any) => { return { elapsedTime, isComplete } } -export const ThinkBlock = ({ children, ...props }: any) => { +const ThinkBlock = ({ children, ...props }: React.ComponentProps<'details'>) => { const { elapsedTime, isComplete } = useThinkTimer(children) const displayContent = removeEndThink(children) const { t } = useTranslation() diff --git a/web/app/components/base/svg-gallery/index.tsx b/web/app/components/base/svg-gallery/index.tsx index 710a0107fb..b6b2fe9db4 100644 --- a/web/app/components/base/svg-gallery/index.tsx +++ b/web/app/components/base/svg-gallery/index.tsx @@ -3,7 +3,7 @@ import { SVG } from '@svgdotjs/svg.js' import DOMPurify from 'dompurify' import ImagePreview from '@/app/components/base/image-uploader/image-preview' -export const SVGRenderer = ({ content }: { content: string }) => { +const SVGRenderer = ({ content }: { content: string }) => { const svgRef = useRef(null) const [imagePreview, setImagePreview] = useState('') const [windowSize, setWindowSize] = useState({ diff --git a/web/app/components/workflow/nodes/llm/components/json-schema-config-modal/json-schema-generator/index.tsx b/web/app/components/workflow/nodes/llm/components/json-schema-config-modal/json-schema-generator/index.tsx index 64138b3cbd..1a4eb3cfdb 100644 --- a/web/app/components/workflow/nodes/llm/components/json-schema-config-modal/json-schema-generator/index.tsx +++ b/web/app/components/workflow/nodes/llm/components/json-schema-config-modal/json-schema-generator/index.tsx @@ -30,7 +30,7 @@ enum GeneratorView { result = 'result', } -export const JsonSchemaGenerator: FC = ({ +const JsonSchemaGenerator: FC = ({ onApply, crossAxisOffset, }) => { From 24b4289d6cfb641e0619099a64d176b57b8d22da Mon Sep 17 00:00:00 2001 From: longbingljw Date: Tue, 23 Sep 2025 17:06:06 +0800 Subject: [PATCH 04/11] fix:add some explanation for oceanbase parser selection (#26071) Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com> --- api/configs/middleware/vdb/oceanbase_config.py | 8 ++++++-- api/core/rag/datasource/vdb/oceanbase/oceanbase_vector.py | 2 +- docker/.env.example | 2 ++ 3 files changed, 9 insertions(+), 3 deletions(-) diff --git a/api/configs/middleware/vdb/oceanbase_config.py b/api/configs/middleware/vdb/oceanbase_config.py index 99f4c49407..7c9376f86b 100644 --- a/api/configs/middleware/vdb/oceanbase_config.py +++ b/api/configs/middleware/vdb/oceanbase_config.py @@ -40,8 +40,12 @@ class OceanBaseVectorConfig(BaseSettings): OCEANBASE_FULLTEXT_PARSER: str | None = Field( description=( - "Fulltext parser to use for text indexing. Options: 'japanese_ftparser' (Japanese), " - "'thai_ftparser' (Thai), 'ik' (Chinese). Default is 'ik'" + "Fulltext parser to use for text indexing. " + "Built-in options: 'ngram' (N-gram tokenizer for English/numbers), " + "'beng' (Basic English tokenizer), 'space' (Space-based tokenizer), " + "'ngram2' (Improved N-gram tokenizer), 'ik' (Chinese tokenizer). " + "External plugins (require installation): 'japanese_ftparser' (Japanese tokenizer), " + "'thai_ftparser' (Thai tokenizer). Default is 'ik'" ), default="ik", ) diff --git a/api/core/rag/datasource/vdb/oceanbase/oceanbase_vector.py b/api/core/rag/datasource/vdb/oceanbase/oceanbase_vector.py index 49cf900126..b3db7332e8 100644 --- a/api/core/rag/datasource/vdb/oceanbase/oceanbase_vector.py +++ b/api/core/rag/datasource/vdb/oceanbase/oceanbase_vector.py @@ -123,7 +123,7 @@ class OceanBaseVector(BaseVector): # Get parser from config or use default ik parser parser_name = dify_config.OCEANBASE_FULLTEXT_PARSER or "ik" - allowed_parsers = ["ik", "japanese_ftparser", "thai_ftparser"] + allowed_parsers = ["ngram", "beng", "space", "ngram2", "ik", "japanese_ftparser", "thai_ftparser"] if parser_name not in allowed_parsers: raise ValueError( f"Invalid OceanBase full-text parser: {parser_name}. " diff --git a/docker/.env.example b/docker/.env.example index d4e8ab3beb..07b4088470 100644 --- a/docker/.env.example +++ b/docker/.env.example @@ -655,6 +655,8 @@ LINDORM_USING_UGC=True LINDORM_QUERY_TIMEOUT=1 # OceanBase Vector configuration, only available when VECTOR_STORE is `oceanbase` +# Built-in fulltext parsers are `ngram`, `beng`, `space`, `ngram2`, `ik` +# External fulltext parsers (require plugin installation) are `japanese_ftparser`, `thai_ftparser` OCEANBASE_VECTOR_HOST=oceanbase OCEANBASE_VECTOR_PORT=2881 OCEANBASE_VECTOR_USER=root@test From d9e45a1abe01ca778b3e9440c0ffa7e045bbbeb0 Mon Sep 17 00:00:00 2001 From: Wu Tianwei <30284043+WTW0313@users.noreply.github.com> Date: Tue, 23 Sep 2025 18:18:22 +0800 Subject: [PATCH 05/11] feat(pipeline): add language support to built-in pipeline templates and update related components (#26124) --- .../list/built-in-pipeline-list.tsx | 11 ++++++++++- web/app/components/plugins/plugin-item/index.tsx | 7 +++---- web/app/components/tools/provider/detail.tsx | 3 +-- web/models/pipeline.ts | 1 + web/service/use-pipeline.ts | 6 ++++-- 5 files changed, 19 insertions(+), 9 deletions(-) diff --git a/web/app/components/datasets/create-from-pipeline/list/built-in-pipeline-list.tsx b/web/app/components/datasets/create-from-pipeline/list/built-in-pipeline-list.tsx index 9d3d0e7717..6d22f2115a 100644 --- a/web/app/components/datasets/create-from-pipeline/list/built-in-pipeline-list.tsx +++ b/web/app/components/datasets/create-from-pipeline/list/built-in-pipeline-list.tsx @@ -1,9 +1,18 @@ import { usePipelineTemplateList } from '@/service/use-pipeline' import TemplateCard from './template-card' import CreateCard from './create-card' +import { useI18N } from '@/context/i18n' +import { useMemo } from 'react' +import { LanguagesSupported } from '@/i18n-config/language' const BuiltInPipelineList = () => { - const { data: pipelineList, isLoading } = usePipelineTemplateList({ type: 'built-in' }) + const { locale } = useI18N() + const language = useMemo(() => { + if (['zh-Hans', 'ja-JP'].includes(locale)) + return locale + return LanguagesSupported[0] + }, [locale]) + const { data: pipelineList, isLoading } = usePipelineTemplateList({ type: 'built-in', language }) const list = pipelineList?.pipeline_templates || [] return ( diff --git a/web/app/components/plugins/plugin-item/index.tsx b/web/app/components/plugins/plugin-item/index.tsx index c228ca4db4..ed7cf47bb7 100644 --- a/web/app/components/plugins/plugin-item/index.tsx +++ b/web/app/components/plugins/plugin-item/index.tsx @@ -146,7 +146,6 @@ const PluginItem: FC = ({ {/* Organization & Name */}
= ({ {category === PluginType.extension && ( <>
·
-
- +
+ = ({ && <>
{t('plugin.from')} marketplace
- + } diff --git a/web/app/components/tools/provider/detail.tsx b/web/app/components/tools/provider/detail.tsx index 87d09bd527..dd2972a9d6 100644 --- a/web/app/components/tools/provider/detail.tsx +++ b/web/app/components/tools/provider/detail.tsx @@ -244,9 +244,8 @@ const ProviderDetail = ({
</div> - <div className='mb-1 flex h-4 items-center justify-between'> + <div className='mb-1 mt-0.5 flex h-4 items-center justify-between'> <OrgInfo - className="mt-0.5" packageNameClassName='w-auto' orgName={collection.author} packageName={collection.name} diff --git a/web/models/pipeline.ts b/web/models/pipeline.ts index d644d43bf3..1c2211b6d9 100644 --- a/web/models/pipeline.ts +++ b/web/models/pipeline.ts @@ -17,6 +17,7 @@ export enum DatasourceType { export type PipelineTemplateListParams = { type: 'built-in' | 'customized' + language?: string } export type PipelineTemplate = { diff --git a/web/service/use-pipeline.ts b/web/service/use-pipeline.ts index 870fb5bc84..a7b9c89410 100644 --- a/web/service/use-pipeline.ts +++ b/web/service/use-pipeline.ts @@ -40,8 +40,9 @@ const NAME_SPACE = 'pipeline' export const PipelineTemplateListQueryKeyPrefix = [NAME_SPACE, 'template-list'] export const usePipelineTemplateList = (params: PipelineTemplateListParams) => { + const { type, language } = params return useQuery<PipelineTemplateListResponse>({ - queryKey: [...PipelineTemplateListQueryKeyPrefix, params.type], + queryKey: [...PipelineTemplateListQueryKeyPrefix, type, language], queryFn: () => { return get<PipelineTemplateListResponse>('/rag/pipeline/templates', { params }) }, @@ -55,7 +56,7 @@ export const useInvalidCustomizedTemplateList = () => { export const usePipelineTemplateById = (params: PipelineTemplateByIdRequest, enabled: boolean) => { const { template_id, type } = params return useQuery<PipelineTemplateByIdResponse>({ - queryKey: [NAME_SPACE, 'template', template_id], + queryKey: [NAME_SPACE, 'template', type, template_id], queryFn: () => { return get<PipelineTemplateByIdResponse>(`/rag/pipeline/templates/${template_id}`, { params: { @@ -64,6 +65,7 @@ export const usePipelineTemplateById = (params: PipelineTemplateByIdRequest, ena }) }, enabled, + staleTime: 0, }) } From 2913d17fe23bda01c5d00d3c8e139845bf9203a2 Mon Sep 17 00:00:00 2001 From: QuantumGhost <obelisk.reg+git@gmail.com> Date: Tue, 23 Sep 2025 18:48:02 +0800 Subject: [PATCH 06/11] ci: Add hotfix/** branches to build-push workflow triggers (#26129) --- .github/workflows/build-push.yml | 1 + 1 file changed, 1 insertion(+) diff --git a/.github/workflows/build-push.yml b/.github/workflows/build-push.yml index 17af047267..24a9da4400 100644 --- a/.github/workflows/build-push.yml +++ b/.github/workflows/build-push.yml @@ -8,6 +8,7 @@ on: - "deploy/enterprise" - "build/**" - "release/e-*" + - "hotfix/**" tags: - "*" From 96a0b9991e274c8e61fa2f2aaf46b7df3eb52906 Mon Sep 17 00:00:00 2001 From: QuantumGhost <obelisk.reg+git@gmail.com> Date: Tue, 23 Sep 2025 21:30:46 +0800 Subject: [PATCH 07/11] fix(api): Fix variable truncation for `list[File]` value in output mapping (#26133) --- api/services/variable_truncator.py | 8 ++++++++ api/tests/unit_tests/services/test_variable_truncator.py | 8 ++++++++ 2 files changed, 16 insertions(+) diff --git a/api/services/variable_truncator.py b/api/services/variable_truncator.py index 4362bb0291..d02508e4f3 100644 --- a/api/services/variable_truncator.py +++ b/api/services/variable_truncator.py @@ -262,6 +262,14 @@ class VariableTruncator: target_length = self._array_element_limit for i, item in enumerate(value): + # Dirty fix: + # The output of `Start` node may contain list of `File` elements, + # causing `AssertionError` while invoking `_truncate_json_primitives`. + # + # This check ensures that `list[File]` are handled separately + if isinstance(item, File): + truncated_value.append(item) + continue if i >= target_length: return _PartResult(truncated_value, used_size, True) if i > 0: diff --git a/api/tests/unit_tests/services/test_variable_truncator.py b/api/tests/unit_tests/services/test_variable_truncator.py index 0ad056c985..6761f939e3 100644 --- a/api/tests/unit_tests/services/test_variable_truncator.py +++ b/api/tests/unit_tests/services/test_variable_truncator.py @@ -588,3 +588,11 @@ class TestIntegrationScenarios: if isinstance(result.result, ObjectSegment): result_size = truncator.calculate_json_size(result.result.value) assert result_size <= original_size + + def test_file_and_array_file_variable_mapping(self, file): + truncator = VariableTruncator(string_length_limit=30, array_element_limit=3, max_size_bytes=300) + + mapping = {"array_file": [file]} + truncated_mapping, truncated = truncator.truncate_variable_mapping(mapping) + assert truncated is False + assert truncated_mapping == mapping From 25c69ac54089e9676e8e926603e28ac252f6f231 Mon Sep 17 00:00:00 2001 From: Asuka Minato <i@asukaminato.eu.org> Date: Wed, 24 Sep 2025 04:32:48 +0900 Subject: [PATCH 08/11] one example of Session (#24135) Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com> Co-authored-by: -LAN- <laipz8200@outlook.com> --- api/commands.py | 152 +++++++++--------- api/controllers/console/app/conversation.py | 5 +- .../console/datasets/datasets_document.py | 5 +- api/models/dataset.py | 4 +- api/models/model.py | 6 +- api/services/app_service.py | 3 +- api/services/dataset_service.py | 12 +- api/services/plugin/plugin_migration.py | 2 +- api/services/tag_service.py | 3 +- api/tasks/document_indexing_sync_task.py | 3 +- 10 files changed, 100 insertions(+), 95 deletions(-) diff --git a/api/commands.py b/api/commands.py index cb8aa8430a..82efe34611 100644 --- a/api/commands.py +++ b/api/commands.py @@ -10,6 +10,7 @@ from flask import current_app from pydantic import TypeAdapter from sqlalchemy import select from sqlalchemy.exc import SQLAlchemyError +from sqlalchemy.orm import sessionmaker from configs import dify_config from constants.languages import languages @@ -61,31 +62,30 @@ def reset_password(email, new_password, password_confirm): if str(new_password).strip() != str(password_confirm).strip(): click.echo(click.style("Passwords do not match.", fg="red")) return + with sessionmaker(db.engine, expire_on_commit=False).begin() as session: + account = session.query(Account).where(Account.email == email).one_or_none() - account = db.session.query(Account).where(Account.email == email).one_or_none() + if not account: + click.echo(click.style(f"Account not found for email: {email}", fg="red")) + return - if not account: - click.echo(click.style(f"Account not found for email: {email}", fg="red")) - return + try: + valid_password(new_password) + except: + click.echo(click.style(f"Invalid password. Must match {password_pattern}", fg="red")) + return - try: - valid_password(new_password) - except: - click.echo(click.style(f"Invalid password. Must match {password_pattern}", fg="red")) - return + # generate password salt + salt = secrets.token_bytes(16) + base64_salt = base64.b64encode(salt).decode() - # generate password salt - salt = secrets.token_bytes(16) - base64_salt = base64.b64encode(salt).decode() - - # encrypt password with salt - password_hashed = hash_password(new_password, salt) - base64_password_hashed = base64.b64encode(password_hashed).decode() - account.password = base64_password_hashed - account.password_salt = base64_salt - db.session.commit() - AccountService.reset_login_error_rate_limit(email) - click.echo(click.style("Password reset successfully.", fg="green")) + # encrypt password with salt + password_hashed = hash_password(new_password, salt) + base64_password_hashed = base64.b64encode(password_hashed).decode() + account.password = base64_password_hashed + account.password_salt = base64_salt + AccountService.reset_login_error_rate_limit(email) + click.echo(click.style("Password reset successfully.", fg="green")) @click.command("reset-email", help="Reset the account email.") @@ -100,22 +100,21 @@ def reset_email(email, new_email, email_confirm): if str(new_email).strip() != str(email_confirm).strip(): click.echo(click.style("New emails do not match.", fg="red")) return + with sessionmaker(db.engine, expire_on_commit=False).begin() as session: + account = session.query(Account).where(Account.email == email).one_or_none() - account = db.session.query(Account).where(Account.email == email).one_or_none() + if not account: + click.echo(click.style(f"Account not found for email: {email}", fg="red")) + return - if not account: - click.echo(click.style(f"Account not found for email: {email}", fg="red")) - return + try: + email_validate(new_email) + except: + click.echo(click.style(f"Invalid email: {new_email}", fg="red")) + return - try: - email_validate(new_email) - except: - click.echo(click.style(f"Invalid email: {new_email}", fg="red")) - return - - account.email = new_email - db.session.commit() - click.echo(click.style("Email updated successfully.", fg="green")) + account.email = new_email + click.echo(click.style("Email updated successfully.", fg="green")) @click.command( @@ -139,25 +138,24 @@ def reset_encrypt_key_pair(): if dify_config.EDITION != "SELF_HOSTED": click.echo(click.style("This command is only for SELF_HOSTED installations.", fg="red")) return + with sessionmaker(db.engine, expire_on_commit=False).begin() as session: + tenants = session.query(Tenant).all() + for tenant in tenants: + if not tenant: + click.echo(click.style("No workspaces found. Run /install first.", fg="red")) + return - tenants = db.session.query(Tenant).all() - for tenant in tenants: - if not tenant: - click.echo(click.style("No workspaces found. Run /install first.", fg="red")) - return + tenant.encrypt_public_key = generate_key_pair(tenant.id) - tenant.encrypt_public_key = generate_key_pair(tenant.id) + session.query(Provider).where(Provider.provider_type == "custom", Provider.tenant_id == tenant.id).delete() + session.query(ProviderModel).where(ProviderModel.tenant_id == tenant.id).delete() - db.session.query(Provider).where(Provider.provider_type == "custom", Provider.tenant_id == tenant.id).delete() - db.session.query(ProviderModel).where(ProviderModel.tenant_id == tenant.id).delete() - db.session.commit() - - click.echo( - click.style( - f"Congratulations! The asymmetric key pair of workspace {tenant.id} has been reset.", - fg="green", + click.echo( + click.style( + f"Congratulations! The asymmetric key pair of workspace {tenant.id} has been reset.", + fg="green", + ) ) - ) @click.command("vdb-migrate", help="Migrate vector db.") @@ -182,14 +180,15 @@ def migrate_annotation_vector_database(): try: # get apps info per_page = 50 - apps = ( - db.session.query(App) - .where(App.status == "normal") - .order_by(App.created_at.desc()) - .limit(per_page) - .offset((page - 1) * per_page) - .all() - ) + with sessionmaker(db.engine, expire_on_commit=False).begin() as session: + apps = ( + session.query(App) + .where(App.status == "normal") + .order_by(App.created_at.desc()) + .limit(per_page) + .offset((page - 1) * per_page) + .all() + ) if not apps: break except SQLAlchemyError: @@ -203,26 +202,27 @@ def migrate_annotation_vector_database(): ) try: click.echo(f"Creating app annotation index: {app.id}") - app_annotation_setting = ( - db.session.query(AppAnnotationSetting).where(AppAnnotationSetting.app_id == app.id).first() - ) + with sessionmaker(db.engine, expire_on_commit=False).begin() as session: + app_annotation_setting = ( + session.query(AppAnnotationSetting).where(AppAnnotationSetting.app_id == app.id).first() + ) - if not app_annotation_setting: - skipped_count = skipped_count + 1 - click.echo(f"App annotation setting disabled: {app.id}") - continue - # get dataset_collection_binding info - dataset_collection_binding = ( - db.session.query(DatasetCollectionBinding) - .where(DatasetCollectionBinding.id == app_annotation_setting.collection_binding_id) - .first() - ) - if not dataset_collection_binding: - click.echo(f"App annotation collection binding not found: {app.id}") - continue - annotations = db.session.scalars( - select(MessageAnnotation).where(MessageAnnotation.app_id == app.id) - ).all() + if not app_annotation_setting: + skipped_count = skipped_count + 1 + click.echo(f"App annotation setting disabled: {app.id}") + continue + # get dataset_collection_binding info + dataset_collection_binding = ( + session.query(DatasetCollectionBinding) + .where(DatasetCollectionBinding.id == app_annotation_setting.collection_binding_id) + .first() + ) + if not dataset_collection_binding: + click.echo(f"App annotation collection binding not found: {app.id}") + continue + annotations = session.scalars( + select(MessageAnnotation).where(MessageAnnotation.app_id == app.id) + ).all() dataset = Dataset( id=app.id, tenant_id=app.tenant_id, diff --git a/api/controllers/console/app/conversation.py b/api/controllers/console/app/conversation.py index c0cbf6613e..f104ab5dee 100644 --- a/api/controllers/console/app/conversation.py +++ b/api/controllers/console/app/conversation.py @@ -1,6 +1,7 @@ from datetime import datetime import pytz # pip install pytz +import sqlalchemy as sa from flask_login import current_user from flask_restx import Resource, marshal_with, reqparse from flask_restx.inputs import int_range @@ -70,7 +71,7 @@ class CompletionConversationApi(Resource): parser.add_argument("limit", type=int_range(1, 100), default=20, location="args") args = parser.parse_args() - query = db.select(Conversation).where( + query = sa.select(Conversation).where( Conversation.app_id == app_model.id, Conversation.mode == "completion", Conversation.is_deleted.is_(False) ) @@ -236,7 +237,7 @@ class ChatConversationApi(Resource): .subquery() ) - query = db.select(Conversation).where(Conversation.app_id == app_model.id, Conversation.is_deleted.is_(False)) + query = sa.select(Conversation).where(Conversation.app_id == app_model.id, Conversation.is_deleted.is_(False)) if args["keyword"]: keyword_filter = f"%{args['keyword']}%" diff --git a/api/controllers/console/datasets/datasets_document.py b/api/controllers/console/datasets/datasets_document.py index 5de1f6c6ee..e6f5daa87b 100644 --- a/api/controllers/console/datasets/datasets_document.py +++ b/api/controllers/console/datasets/datasets_document.py @@ -4,6 +4,7 @@ from argparse import ArgumentTypeError from collections.abc import Sequence from typing import Literal, cast +import sqlalchemy as sa from flask import request from flask_login import current_user from flask_restx import Resource, fields, marshal, marshal_with, reqparse @@ -211,13 +212,13 @@ class DatasetDocumentListApi(Resource): if sort == "hit_count": sub_query = ( - db.select(DocumentSegment.document_id, db.func.sum(DocumentSegment.hit_count).label("total_hit_count")) + sa.select(DocumentSegment.document_id, sa.func.sum(DocumentSegment.hit_count).label("total_hit_count")) .group_by(DocumentSegment.document_id) .subquery() ) query = query.outerjoin(sub_query, sub_query.c.document_id == Document.id).order_by( - sort_logic(db.func.coalesce(sub_query.c.total_hit_count, 0)), + sort_logic(sa.func.coalesce(sub_query.c.total_hit_count, 0)), sort_logic(Document.position), ) elif sort == "created_at": diff --git a/api/models/dataset.py b/api/models/dataset.py index 2c4059f800..25ebe14738 100644 --- a/api/models/dataset.py +++ b/api/models/dataset.py @@ -910,7 +910,7 @@ class AppDatasetJoin(Base): id = mapped_column(StringUUID, primary_key=True, nullable=False, server_default=sa.text("uuid_generate_v4()")) app_id = mapped_column(StringUUID, nullable=False) dataset_id = mapped_column(StringUUID, nullable=False) - created_at: Mapped[datetime] = mapped_column(DateTime, nullable=False, server_default=db.func.current_timestamp()) + created_at: Mapped[datetime] = mapped_column(DateTime, nullable=False, server_default=sa.func.current_timestamp()) @property def app(self): @@ -931,7 +931,7 @@ class DatasetQuery(Base): source_app_id = mapped_column(StringUUID, nullable=True) created_by_role = mapped_column(String, nullable=False) created_by = mapped_column(StringUUID, nullable=False) - created_at: Mapped[datetime] = mapped_column(DateTime, nullable=False, server_default=db.func.current_timestamp()) + created_at: Mapped[datetime] = mapped_column(DateTime, nullable=False, server_default=sa.func.current_timestamp()) class DatasetKeywordTable(Base): diff --git a/api/models/model.py b/api/models/model.py index 9bcb81b41b..a8218c3a4e 100644 --- a/api/models/model.py +++ b/api/models/model.py @@ -1731,7 +1731,7 @@ class MessageChain(Base): type: Mapped[str] = mapped_column(String(255), nullable=False) input = mapped_column(sa.Text, nullable=True) output = mapped_column(sa.Text, nullable=True) - created_at = mapped_column(sa.DateTime, nullable=False, server_default=db.func.current_timestamp()) + created_at = mapped_column(sa.DateTime, nullable=False, server_default=sa.func.current_timestamp()) class MessageAgentThought(Base): @@ -1769,7 +1769,7 @@ class MessageAgentThought(Base): latency: Mapped[float | None] = mapped_column(sa.Float, nullable=True) created_by_role = mapped_column(String, nullable=False) created_by = mapped_column(StringUUID, nullable=False) - created_at = mapped_column(sa.DateTime, nullable=False, server_default=db.func.current_timestamp()) + created_at = mapped_column(sa.DateTime, nullable=False, server_default=sa.func.current_timestamp()) @property def files(self) -> list[Any]: @@ -1872,7 +1872,7 @@ class DatasetRetrieverResource(Base): index_node_hash = mapped_column(sa.Text, nullable=True) retriever_from = mapped_column(sa.Text, nullable=False) created_by = mapped_column(StringUUID, nullable=False) - created_at = mapped_column(sa.DateTime, nullable=False, server_default=db.func.current_timestamp()) + created_at = mapped_column(sa.DateTime, nullable=False, server_default=sa.func.current_timestamp()) class Tag(Base): diff --git a/api/services/app_service.py b/api/services/app_service.py index d524adbf3e..4fc6cf2494 100644 --- a/api/services/app_service.py +++ b/api/services/app_service.py @@ -2,6 +2,7 @@ import json import logging from typing import TypedDict, cast +import sqlalchemy as sa from flask_sqlalchemy.pagination import Pagination from configs import dify_config @@ -65,7 +66,7 @@ class AppService: return None app_models = db.paginate( - db.select(App).where(*filters).order_by(App.created_at.desc()), + sa.select(App).where(*filters).order_by(App.created_at.desc()), page=args["page"], per_page=args["limit"], error_out=False, diff --git a/api/services/dataset_service.py b/api/services/dataset_service.py index 8b3720026d..c9dd78ddd1 100644 --- a/api/services/dataset_service.py +++ b/api/services/dataset_service.py @@ -115,12 +115,12 @@ class DatasetService: # Check if permitted_dataset_ids is not empty to avoid WHERE false condition if permitted_dataset_ids and len(permitted_dataset_ids) > 0: query = query.where( - db.or_( + sa.or_( Dataset.permission == DatasetPermissionEnum.ALL_TEAM, - db.and_( + sa.and_( Dataset.permission == DatasetPermissionEnum.ONLY_ME, Dataset.created_by == user.id ), - db.and_( + sa.and_( Dataset.permission == DatasetPermissionEnum.PARTIAL_TEAM, Dataset.id.in_(permitted_dataset_ids), ), @@ -128,9 +128,9 @@ class DatasetService: ) else: query = query.where( - db.or_( + sa.or_( Dataset.permission == DatasetPermissionEnum.ALL_TEAM, - db.and_( + sa.and_( Dataset.permission == DatasetPermissionEnum.ONLY_ME, Dataset.created_by == user.id ), ) @@ -1879,7 +1879,7 @@ class DocumentService: # for notion_info in notion_info_list: # workspace_id = notion_info.workspace_id # data_source_binding = DataSourceOauthBinding.query.filter( - # db.and_( + # sa.and_( # DataSourceOauthBinding.tenant_id == current_user.current_tenant_id, # DataSourceOauthBinding.provider == "notion", # DataSourceOauthBinding.disabled == False, diff --git a/api/services/plugin/plugin_migration.py b/api/services/plugin/plugin_migration.py index 5db19711e6..99946d8fa9 100644 --- a/api/services/plugin/plugin_migration.py +++ b/api/services/plugin/plugin_migration.py @@ -471,7 +471,7 @@ class PluginMigration: total_failed_tenant = 0 while True: # paginate - tenants = db.paginate(db.select(Tenant).order_by(Tenant.created_at.desc()), page=page, per_page=100) + tenants = db.paginate(sa.select(Tenant).order_by(Tenant.created_at.desc()), page=page, per_page=100) if tenants.items is None or len(tenants.items) == 0: break diff --git a/api/services/tag_service.py b/api/services/tag_service.py index 4674335ba8..db7ed3d5c3 100644 --- a/api/services/tag_service.py +++ b/api/services/tag_service.py @@ -1,5 +1,6 @@ import uuid +import sqlalchemy as sa from flask_login import current_user from sqlalchemy import func, select from werkzeug.exceptions import NotFound @@ -18,7 +19,7 @@ class TagService: .where(Tag.type == tag_type, Tag.tenant_id == current_tenant_id) ) if keyword: - query = query.where(db.and_(Tag.name.ilike(f"%{keyword}%"))) + query = query.where(sa.and_(Tag.name.ilike(f"%{keyword}%"))) query = query.group_by(Tag.id, Tag.type, Tag.name, Tag.created_at) results: list = query.order_by(Tag.created_at.desc()).all() return results diff --git a/api/tasks/document_indexing_sync_task.py b/api/tasks/document_indexing_sync_task.py index 10da9a9af4..4c1f38c3bb 100644 --- a/api/tasks/document_indexing_sync_task.py +++ b/api/tasks/document_indexing_sync_task.py @@ -2,6 +2,7 @@ import logging import time import click +import sqlalchemy as sa from celery import shared_task from sqlalchemy import select @@ -51,7 +52,7 @@ def document_indexing_sync_task(dataset_id: str, document_id: str): data_source_binding = ( db.session.query(DataSourceOauthBinding) .where( - db.and_( + sa.and_( DataSourceOauthBinding.tenant_id == document.tenant_id, DataSourceOauthBinding.provider == "notion", DataSourceOauthBinding.disabled == False, From a4acc64afd87d07fc1522a17f26bd287802ecc42 Mon Sep 17 00:00:00 2001 From: quicksand <quicksandzn@gmail.com> Date: Wed, 24 Sep 2025 10:09:35 +0800 Subject: [PATCH 09/11] fix(api):LLM node losing Flask context during parallel iterations (#26098) --- .../nodes/iteration/iteration_node.py | 36 +++++++++++-------- 1 file changed, 22 insertions(+), 14 deletions(-) diff --git a/api/core/workflow/nodes/iteration/iteration_node.py b/api/core/workflow/nodes/iteration/iteration_node.py index 593281c9b5..1a417b5739 100644 --- a/api/core/workflow/nodes/iteration/iteration_node.py +++ b/api/core/workflow/nodes/iteration/iteration_node.py @@ -1,9 +1,11 @@ +import contextvars import logging from collections.abc import Generator, Mapping, Sequence from concurrent.futures import Future, ThreadPoolExecutor, as_completed from datetime import UTC, datetime from typing import TYPE_CHECKING, Any, NewType, cast +from flask import Flask, current_app from typing_extensions import TypeIs from core.variables import IntegerVariable, NoneSegment @@ -35,6 +37,7 @@ from core.workflow.nodes.base.entities import BaseNodeData, RetryConfig from core.workflow.nodes.base.node import Node from core.workflow.nodes.iteration.entities import ErrorHandleMode, IterationNodeData from libs.datetime_utils import naive_utc_now +from libs.flask_utils import preserve_flask_contexts from .exc import ( InvalidIteratorValueError, @@ -239,6 +242,8 @@ class IterationNode(Node): self._execute_single_iteration_parallel, index=index, item=item, + flask_app=current_app._get_current_object(), # type: ignore + context_vars=contextvars.copy_context(), ) future_to_index[future] = index @@ -281,26 +286,29 @@ class IterationNode(Node): self, index: int, item: object, + flask_app: Flask, + context_vars: contextvars.Context, ) -> tuple[datetime, list[GraphNodeEventBase], object | None, int]: """Execute a single iteration in parallel mode and return results.""" - iter_start_at = datetime.now(UTC).replace(tzinfo=None) - events: list[GraphNodeEventBase] = [] - outputs_temp: list[object] = [] + with preserve_flask_contexts(flask_app=flask_app, context_vars=context_vars): + iter_start_at = datetime.now(UTC).replace(tzinfo=None) + events: list[GraphNodeEventBase] = [] + outputs_temp: list[object] = [] - graph_engine = self._create_graph_engine(index, item) + graph_engine = self._create_graph_engine(index, item) - # Collect events instead of yielding them directly - for event in self._run_single_iter( - variable_pool=graph_engine.graph_runtime_state.variable_pool, - outputs=outputs_temp, - graph_engine=graph_engine, - ): - events.append(event) + # Collect events instead of yielding them directly + for event in self._run_single_iter( + variable_pool=graph_engine.graph_runtime_state.variable_pool, + outputs=outputs_temp, + graph_engine=graph_engine, + ): + events.append(event) - # Get the output value from the temporary outputs list - output_value = outputs_temp[0] if outputs_temp else None + # Get the output value from the temporary outputs list + output_value = outputs_temp[0] if outputs_temp else None - return iter_start_at, events, output_value, graph_engine.graph_runtime_state.total_tokens + return iter_start_at, events, output_value, graph_engine.graph_runtime_state.total_tokens def _handle_iteration_success( self, From 9b360592920a69c1da8201be94211110ffa1e3de Mon Sep 17 00:00:00 2001 From: yangzheli <43645580+yangzheli@users.noreply.github.com> Date: Wed, 24 Sep 2025 15:53:59 +0800 Subject: [PATCH 10/11] fix(search-input): ensure proper value extraction in composition end handler (#26147) --- web/app/components/base/search-input/index.tsx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/web/app/components/base/search-input/index.tsx b/web/app/components/base/search-input/index.tsx index cf9bc1c376..3330b55330 100644 --- a/web/app/components/base/search-input/index.tsx +++ b/web/app/components/base/search-input/index.tsx @@ -53,7 +53,7 @@ const SearchInput: FC<SearchInputProps> = ({ }} onCompositionEnd={(e) => { isComposing.current = false - onChange(e.data) + onChange(e.currentTarget.value) }} onFocus={() => setFocus(true)} onBlur={() => setFocus(false)} From 4cebaa331e1ddf48f0de44b3814977eec32b1849 Mon Sep 17 00:00:00 2001 From: jyong <718720800@qq.com> Date: Thu, 25 Sep 2025 17:18:23 +0800 Subject: [PATCH 11/11] add pipeline template endpoint --- api/configs/enterprise/__init__.py | 15 ++ .../datasets/rag_pipeline/rag_pipeline.py | 191 +++++++++++++++++- ...0bcbf45396_remove_builtin_template_user.py | 37 ++++ api/models/dataset.py | 9 - .../rag_pipeline_entities.py | 7 + .../database/database_retrieval.py | 1 - api/services/rag_pipeline/rag_pipeline.py | 140 +++++++++++++ 7 files changed, 383 insertions(+), 17 deletions(-) create mode 100644 api/migrations/versions/2025_09_25_1650-bf0bcbf45396_remove_builtin_template_user.py diff --git a/api/configs/enterprise/__init__.py b/api/configs/enterprise/__init__.py index eda6345e14..af5640934e 100644 --- a/api/configs/enterprise/__init__.py +++ b/api/configs/enterprise/__init__.py @@ -18,3 +18,18 @@ class EnterpriseFeatureConfig(BaseSettings): description="Allow customization of the enterprise logo.", default=False, ) + + UPLOAD_KNOWLEDGE_PIPELINE_TEMPLATE_TOKEN: str = Field( + description="Token for uploading knowledge pipeline template.", + default="", + ) + + KNOWLEDGE_PIPELINE_TEMPLATE_COPYRIGHT: str = Field( + description="Knowledge pipeline template copyright.", + default="Copyright 2023 Dify", + ) + + KNOWLEDGE_PIPELINE_TEMPLATE_PRIVACY_POLICY: str = Field( + description="Knowledge pipeline template privacy policy.", + default="https://dify.ai", + ) diff --git a/api/controllers/console/datasets/rag_pipeline/rag_pipeline.py b/api/controllers/console/datasets/rag_pipeline/rag_pipeline.py index f04b0e04c3..c8bb976c44 100644 --- a/api/controllers/console/datasets/rag_pipeline/rag_pipeline.py +++ b/api/controllers/console/datasets/rag_pipeline/rag_pipeline.py @@ -14,7 +14,10 @@ from controllers.console.wraps import ( from extensions.ext_database import db from libs.login import login_required from models.dataset import PipelineCustomizedTemplate -from services.entities.knowledge_entities.rag_pipeline_entities import PipelineTemplateInfoEntity +from services.entities.knowledge_entities.rag_pipeline_entities import ( + PipelineBuiltInTemplateEntity, + PipelineTemplateInfoEntity, +) from services.rag_pipeline.rag_pipeline import RagPipelineService logger = logging.getLogger(__name__) @@ -26,12 +29,6 @@ def _validate_name(name): return name -def _validate_description_length(description): - if len(description) > 400: - raise ValueError("Description cannot exceed 400 characters.") - return description - - class PipelineTemplateListApi(Resource): @setup_required @login_required @@ -146,6 +143,186 @@ class PublishCustomizedPipelineTemplateApi(Resource): return {"result": "success"} +class PipelineTemplateInstallApi(Resource): + """API endpoint for installing built-in pipeline templates""" + + def post(self): + """ + Install a built-in pipeline template + + Args: + template_id: The template ID from URL parameter + + Returns: + Success response or error with appropriate HTTP status + """ + try: + # Extract and validate Bearer token + auth_token = self._extract_bearer_token() + + # Parse and validate request parameters + template_args = self._parse_template_args() + + # Process uploaded template file + file_content = self._process_template_file() + + # Create template entity + pipeline_built_in_template_entity = PipelineBuiltInTemplateEntity(**template_args) + + # Install the template + rag_pipeline_service = RagPipelineService() + rag_pipeline_service.install_built_in_pipeline_template( + pipeline_built_in_template_entity, file_content, auth_token + ) + + return {"result": "success", "message": "Template installed successfully"}, 200 + + except ValueError as e: + logger.exception("Validation error in template installation") + return {"error": str(e)}, 400 + except Exception as e: + logger.exception("Unexpected error in template installation") + return {"error": "An unexpected error occurred during template installation"}, 500 + + def _extract_bearer_token(self) -> str: + """ + Extract and validate Bearer token from Authorization header + + Returns: + The extracted token string + + Raises: + ValueError: If token is missing or invalid + """ + auth_header = request.headers.get("Authorization", "").strip() + + if not auth_header: + raise ValueError("Authorization header is required") + + if not auth_header.startswith("Bearer "): + raise ValueError("Authorization header must start with 'Bearer '") + + token_parts = auth_header.split(" ", 1) + if len(token_parts) != 2: + raise ValueError("Invalid Authorization header format") + + auth_token = token_parts[1].strip() + if not auth_token: + raise ValueError("Bearer token cannot be empty") + + return auth_token + + def _parse_template_args(self) -> dict: + """ + Parse and validate template arguments from form data + + Args: + template_id: The template ID from URL + + Returns: + Dictionary of validated template arguments + """ + # Use reqparse for consistent parameter parsing + parser = reqparse.RequestParser() + + parser.add_argument( + "template_id", + type=str, + location="form", + required=False, + help="Template ID for updating existing template" + ) + parser.add_argument( + "language", + type=str, + location="form", + required=True, + default="en-US", + choices=["en-US", "zh-CN", "ja-JP"], + help="Template language code" + ) + parser.add_argument( + "name", + type=str, + location="form", + required=True, + default="New Pipeline Template", + help="Template name (1-200 characters)" + ) + parser.add_argument( + "description", + type=str, + location="form", + required=False, + default="", + help="Template description (max 1000 characters)" + ) + + args = parser.parse_args() + + # Additional validation + if args.get("name"): + args["name"] = self._validate_name(args["name"]) + + if args.get("description") and len(args["description"]) > 1000: + raise ValueError("Description must not exceed 1000 characters") + + # Filter out None values + return {k: v for k, v in args.items() if v is not None} + + def _validate_name(self, name: str) -> str: + """ + Validate template name + + Args: + name: Template name to validate + + Returns: + Validated and trimmed name + + Raises: + ValueError: If name is invalid + """ + name = name.strip() + if not name or len(name) < 1 or len(name) > 200: + raise ValueError("Template name must be between 1 and 200 characters") + return name + + def _process_template_file(self) -> str: + """ + Process and validate uploaded template file + + Returns: + File content as string + + Raises: + ValueError: If file is missing or invalid + """ + if "file" not in request.files: + raise ValueError("Template file is required") + + file = request.files["file"] + + # Validate file + if not file or not file.filename: + raise ValueError("No file selected") + + filename = file.filename.strip() + if not filename: + raise ValueError("File name cannot be empty") + + # Check file extension + if not filename.lower().endswith(".pipeline"): + raise ValueError("Template file must be a pipeline file (.pipeline)") + + try: + file_content = file.read().decode("utf-8") + except UnicodeDecodeError: + raise ValueError("Template file must be valid UTF-8 text") + + return file_content + + api.add_resource( PipelineTemplateListApi, "/rag/pipeline/templates", diff --git a/api/migrations/versions/2025_09_25_1650-bf0bcbf45396_remove_builtin_template_user.py b/api/migrations/versions/2025_09_25_1650-bf0bcbf45396_remove_builtin_template_user.py new file mode 100644 index 0000000000..67731111f9 --- /dev/null +++ b/api/migrations/versions/2025_09_25_1650-bf0bcbf45396_remove_builtin_template_user.py @@ -0,0 +1,37 @@ +"""remove-builtin-template-user + +Revision ID: bf0bcbf45396 +Revises: 68519ad5cd18 +Create Date: 2025-09-25 16:50:32.245503 + +""" +from alembic import op +import models as models +import sqlalchemy as sa + + +# revision identifiers, used by Alembic. +revision = 'bf0bcbf45396' +down_revision = '68519ad5cd18' +branch_labels = None +depends_on = None + + +def upgrade(): + # ### commands auto generated by Alembic - please adjust! ### + + with op.batch_alter_table('pipeline_built_in_templates', schema=None) as batch_op: + batch_op.drop_column('updated_by') + batch_op.drop_column('created_by') + + # ### end Alembic commands ### + + +def downgrade(): + # ### commands auto generated by Alembic - please adjust! ### + + with op.batch_alter_table('pipeline_built_in_templates', schema=None) as batch_op: + batch_op.add_column(sa.Column('created_by', sa.UUID(), autoincrement=False, nullable=False)) + batch_op.add_column(sa.Column('updated_by', sa.UUID(), autoincrement=False, nullable=True)) + + # ### end Alembic commands ### diff --git a/api/models/dataset.py b/api/models/dataset.py index 25ebe14738..d7d204e2bc 100644 --- a/api/models/dataset.py +++ b/api/models/dataset.py @@ -1239,15 +1239,6 @@ class PipelineBuiltInTemplate(Base): # type: ignore[name-defined] language = db.Column(db.String(255), nullable=False) created_at = db.Column(db.DateTime, nullable=False, server_default=func.current_timestamp()) updated_at = db.Column(db.DateTime, nullable=False, server_default=func.current_timestamp()) - created_by = db.Column(StringUUID, nullable=False) - updated_by = db.Column(StringUUID, nullable=True) - - @property - def created_user_name(self): - account = db.session.query(Account).where(Account.id == self.created_by).first() - if account: - return account.name - return "" class PipelineCustomizedTemplate(Base): # type: ignore[name-defined] diff --git a/api/services/entities/knowledge_entities/rag_pipeline_entities.py b/api/services/entities/knowledge_entities/rag_pipeline_entities.py index 860bfde401..022fa47525 100644 --- a/api/services/entities/knowledge_entities/rag_pipeline_entities.py +++ b/api/services/entities/knowledge_entities/rag_pipeline_entities.py @@ -128,3 +128,10 @@ class KnowledgeConfiguration(BaseModel): if v is None: return "" return v + + +class PipelineBuiltInTemplateEntity(BaseModel): + template_id: str | None = None + name: str + description: str + language: str diff --git a/api/services/rag_pipeline/pipeline_template/database/database_retrieval.py b/api/services/rag_pipeline/pipeline_template/database/database_retrieval.py index ec91f79606..908f9a2684 100644 --- a/api/services/rag_pipeline/pipeline_template/database/database_retrieval.py +++ b/api/services/rag_pipeline/pipeline_template/database/database_retrieval.py @@ -74,5 +74,4 @@ class DatabasePipelineTemplateRetrieval(PipelineTemplateRetrievalBase): "chunk_structure": pipeline_template.chunk_structure, "export_data": pipeline_template.yaml_content, "graph": graph_data, - "created_by": pipeline_template.created_user_name, } diff --git a/api/services/rag_pipeline/rag_pipeline.py b/api/services/rag_pipeline/rag_pipeline.py index fdaaa73bcc..14e3364690 100644 --- a/api/services/rag_pipeline/rag_pipeline.py +++ b/api/services/rag_pipeline/rag_pipeline.py @@ -8,6 +8,7 @@ from datetime import UTC, datetime from typing import Any, Union, cast from uuid import uuid4 +import yaml from flask_login import current_user from sqlalchemy import func, or_, select from sqlalchemy.orm import Session, sessionmaker @@ -60,6 +61,7 @@ from models.dataset import ( # type: ignore Document, DocumentPipelineExecutionLog, Pipeline, + PipelineBuiltInTemplate, PipelineCustomizedTemplate, PipelineRecommendedPlugin, ) @@ -76,6 +78,7 @@ from repositories.factory import DifyAPIRepositoryFactory from services.datasource_provider_service import DatasourceProviderService from services.entities.knowledge_entities.rag_pipeline_entities import ( KnowledgeConfiguration, + PipelineBuiltInTemplateEntity, PipelineTemplateInfoEntity, ) from services.errors.app import WorkflowHashNotEqualError @@ -1454,3 +1457,140 @@ class RagPipelineService: if not pipeline: raise ValueError("Pipeline not found") return pipeline + + def install_built_in_pipeline_template( + self, args: PipelineBuiltInTemplateEntity, file_content: str, auth_token: str + ) -> None: + """ + Install built-in pipeline template + + Args: + args: Pipeline built-in template entity with template metadata + file_content: YAML content of the pipeline template + auth_token: Authentication token for authorization + + Raises: + ValueError: If validation fails or template processing errors occur + """ + # Validate authentication + self._validate_auth_token(auth_token) + + # Parse and validate template content + pipeline_template_dsl = self._parse_template_content(file_content) + + # Extract template metadata + icon = self._extract_icon_metadata(pipeline_template_dsl) + chunk_structure = self._extract_chunk_structure(pipeline_template_dsl) + + # Prepare template data + template_data = { + "name": args.name, + "description": args.description, + "chunk_structure": chunk_structure, + "icon": icon, + "language": args.language, + "yaml_content": file_content, + } + + # Use transaction for database operations + try: + if args.template_id: + self._update_existing_template(args.template_id, template_data) + else: + self._create_new_template(template_data) + db.session.commit() + except Exception as e: + db.session.rollback() + raise ValueError(f"Failed to install pipeline template: {str(e)}") + + def _validate_auth_token(self, auth_token: str) -> None: + """Validate the authentication token""" + config_auth_token = dify_config.UPLOAD_KNOWLEDGE_PIPELINE_TEMPLATE_TOKEN + if not config_auth_token: + raise ValueError("Auth token configuration is required") + if config_auth_token != auth_token: + raise ValueError("Auth token is incorrect") + + def _parse_template_content(self, file_content: str) -> dict: + """Parse and validate YAML template content""" + try: + pipeline_template_dsl = yaml.safe_load(file_content) + except yaml.YAMLError as e: + raise ValueError(f"Invalid YAML content: {str(e)}") + + if not pipeline_template_dsl: + raise ValueError("Pipeline template DSL is required") + + return pipeline_template_dsl + + def _extract_icon_metadata(self, pipeline_template_dsl: dict) -> dict: + """Extract icon metadata from template DSL""" + rag_pipeline_info = pipeline_template_dsl.get("rag_pipeline", {}) + + return { + "icon": rag_pipeline_info.get("icon", "📙"), + "icon_type": rag_pipeline_info.get("icon_type", "emoji"), + "icon_background": rag_pipeline_info.get("icon_background", "#FFEAD5"), + "icon_url": rag_pipeline_info.get("icon_url"), + } + + def _extract_chunk_structure(self, pipeline_template_dsl: dict) -> str: + """Extract chunk structure from template DSL""" + nodes = pipeline_template_dsl.get("workflow", {}).get("graph", {}).get("nodes", []) + + # Use generator expression for efficiency + chunk_structure = next( + ( + node.get("data", {}).get("chunk_structure") + for node in nodes + if node.get("data", {}).get("type") == NodeType.KNOWLEDGE_INDEX.value + ), + None + ) + + if not chunk_structure: + raise ValueError("Chunk structure is required in template") + + return chunk_structure + + def _update_existing_template(self, template_id: str, template_data: dict) -> None: + """Update an existing pipeline template""" + pipeline_built_in_template = ( + db.session.query(PipelineBuiltInTemplate) + .filter(PipelineBuiltInTemplate.id == template_id) + .first() + ) + + if not pipeline_built_in_template: + raise ValueError(f"Pipeline built-in template not found: {template_id}") + + # Update template fields + for key, value in template_data.items(): + setattr(pipeline_built_in_template, key, value) + + db.session.add(pipeline_built_in_template) + + def _create_new_template(self, template_data: dict) -> None: + """Create a new pipeline template""" + # Get the next available position + position = self._get_next_position(template_data["language"]) + + # Add additional fields for new template + template_data.update({ + "position": position, + "install_count": 0, + "copyright": dify_config.KNOWLEDGE_PIPELINE_TEMPLATE_COPYRIGHT, + "privacy_policy": dify_config.KNOWLEDGE_PIPELINE_TEMPLATE_PRIVACY_POLICY, + }) + + new_template = PipelineBuiltInTemplate(**template_data) + db.session.add(new_template) + + def _get_next_position(self, language: str) -> int: + """Get the next available position for a template in the specified language""" + max_position = ( + db.session.query(func.max(PipelineBuiltInTemplate.position)) + .filter(PipelineBuiltInTemplate.language == language) + .scalar() + ) + return (max_position or 0) + 1