{"id":"24fc1160-d133-4a93-a335-3f3858409dab","entityType":"agent","slug":"dify-lyy","name":"发票审核工作流","canonicalUrl":"https://www.xpersona.co/agent/dify-lyy","canonicalPath":"/agent/dify-lyy","generatedAt":"2026-10-09T04:15:19.593Z","source":"DIFY_MARKETPLACE","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-09T01:20:58.015Z","emptyReason":null},"description":"发票审核工作流 是一套自动化发票审核工作流，可同时处理图片格式与 PDF 格式的发票。它借助阿里云通义系列多模态大语言模型，从发票中提取结构化数据，再通过基于规则的 Python 审核引擎对每张发票进行合规校验，最终以清晰的 Markdown 表格形式输出审核结果，将通过与未通过的发票分类呈现。 **1. 安装通义插件** 前往**插件市场**，搜索并安装**通义**插件（langgenius/tongyi）。随后进入**设置 → 模型供应商**，填写您的阿里云 API Key，以激活本工作流所需的以下两个模型： - qwen-vl-plus — 多模态视觉模型，用于识别**图片格式发票** - qvq-max-latest — 推理模型，用于提取**PDF 格式发票**中的结构化数据 **2. 配置开始节点** 开始节点接收一个名为 files 的文件列表输入变量，请确保以下上传配置已正确设置： - **支持的文件类型：** 图片（.JPG、.JPEG、.PNG、.GIF、.WEBP、.SVG）及文档（PDF） - **上传方式：** 本地文件上传与远程 URL - 该输入变量将同时为图片处理流水线与 PDF 处理流水线提供数据 **3. 了解双流水线架构** 工作流在开始节点之后立即分为两条并行处理分支： - **图","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. Last updated 10/9/2026.","installCommand":null,"sourceUrl":"https://marketplace.dify.ai/api/v1/templates/d3446581-8a4c-4731-b570-bfd57ecd1dc0","homepage":null,"primaryLinks":[{"label":"View on Dify","url":"https://marketplace.dify.ai/api/v1/templates/d3446581-8a4c-4731-b570-bfd57ecd1dc0","kind":"source"}],"safetyScore":82,"overallRank":88.8,"popularityScore":94,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"发票审核工作流 是一套自动化发票审核工作流，可同时处理图片格式与 PDF 格式的发票。它借助阿里云通义系列多模态大语言模型，从发票中提取结构化数据，再通过基于规则的 Python 审核引擎对每张发票进行合规校验，最终以清晰的 Markdown 表格形式输出审核结果，将通过与未通过的发票分类呈现。 **1. 安装通义插件"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T01:20:58.015Z","emptyReason":null},"protocols":[],"capabilities":[{"label":"workflow","status":"self-declared"},{"label":"support","status":"self-declared"},{"label":"tongyi","status":"self-declared"}],"verifiedCount":0,"selfDeclaredCount":3,"capabilityMatrix":{"rows":[{"key":"workflow","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"},{"key":"support","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"},{"key":"tongyi","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"}],"flattenedTokens":"capability:workflow|supported|profile capability:support|supported|profile capability:tongyi|supported|profile"}},"adoption":{"evidence":{"source":"no-adoption-signals","verified":false,"confidence":"low","updatedAt":"2026-10-09T01:20:58.015Z","emptyReason":"No source adoption metrics were available."},"stars":null,"forks":null,"downloads":null,"packageName":null,"latestVersion":null,"tractionLabel":null},"release":{"evidence":{"source":"agent-index","verified":false,"confidence":"medium","updatedAt":"2026-10-09T01:20:58.011Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T01:20:58.015Z","lastCrawledAt":"2026-10-09T01:20:58.011Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-11T01:20:58.011Z","lastVerifiedAt":null,"highlights":[]},"execution":{"evidence":{"source":"Dify","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":null,"setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/dify-lyy/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/dify-lyy/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/dify-lyy/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/dify-lyy/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/dify-lyy/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/dify-lyy/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":[]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"DIFY_MARKETPLACE","generatedAt":"2026-10-09T04:15:19.593Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/dify-lyy/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/dify-lyy/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/dify-lyy/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/dify-lyy/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"Dify","verified":false,"confidence":"high","updatedAt":"2026-10-09T01:20:58.015Z","emptyReason":null},"readme":"**1. 安装通义插件**\n\n前往**插件市场**，搜索并安装**通义**插件（`langgenius/tongyi`）。随后进入**设置 → 模型供应商**，填写您的阿里云 API Key，以激活本工作流所需的以下两个模型：\n- `qwen-vl-plus` — 多模态视觉模型，用于识别**图片格式发票**\n- `qvq-max-latest` — 推理模型，用于提取**PDF 格式发票**中的结构化数据\n\n**2. 配置开始节点**\n\n开始节点接收一个名为 `files` 的文件列表输入变量，请确保以下上传配置已正确设置：\n- **支持的文件类型：** 图片（`.JPG`、`.JPEG`、`.PNG`、`.GIF`、`.WEBP`、`.SVG`）及文档（PDF）\n- **上传方式：** 本地文件上传与远程 URL\n- 该输入变量将同时为图片处理流水线与 PDF 处理流水线提供数据\n\n**3. 了解双流水线架构**\n\n工作流在开始节点之后立即分为两条并行处理分支：\n\n- **图片流水线：** 列表操作（筛选图片）→ 迭代（迭代识别图片）→ LLM 视觉识别（`qwen-vl-plus`）\n- **PDF 流水线：** 列表操作（筛选 PDF）→ 迭代（迭代识别 PDF）→ 文档提取器 → LLM 结构化提取（`qvq-max-latest`）\n\n两条流水线均从每张发票中提取以下 8 个结构化字段：\n\n| 字段 | 说明 |\n|---|---|\n| `file_name` | 文件名称 |\n| `file_type` | 文件类型 |\n| `payer_name` | 购买方公司名称 |\n| `taxpayer_num` | 统一社会信用代码 / 纳税人识别号 |\n| `project_name` | 项目名称（提取 `*` 包裹的内容） |\n| `invoicing_date` | 开票日期（YYYY-MM-DD 格式） |\n| `tax_num` | 发票号码 |\n| `total_price` | 价税合计金额（小写数字，不含货币符号） |\n\n**4. 自定义审核规则（重要）**\n\n**机器审核**代码节点中包含硬编码的 Python 业务校验规则，在正式上线前，您**必须**将其替换为贵公司的实际审核要求：\n\n- **`payer_name`** — 当前校验值为 `北京字节多多科技有限责任公司`，请替换为您的公司名称。\n- **`taxpayer_num`** — 当前校验值为 `91110112MA01P0AAXL`，请替换为您公司的统一社会信用代码。\n- **`project_name`** — 当前仅接受 `住宿服务`、`咨询服务`、`餐饮服务`，请按实际允许的费用类别进行更新。\n- **`invoicing_date`** — 当前拒绝 2025 年以前的发票，请根据实际需求调整年份阈值。\n- **`tax_num`** — 当前通过白名单方式校验两个特定发票号码，请替换为您自己的校验逻辑。\n\n**5. 确认输出格式**\n\n最终的**输出为表格**代码节点将生成一份 Markdown 审核报告，包含以下两个部分：\n\n- `✅ 通过审核的发票` — 审核通过的发票（不含 `is_ok` 与 `reason` 字段）\n- `❌ 未通过审核的发票` — 审核未通过的发票（保留 `reason` 字段，说明未通过原因）\n\n如无特殊需求，此节点无需修改；如需自定义表格格式或输出语言，可按需调整代码。\n\n**6. 测试并发布**\n\n点击**预览**，上传一批测试发票（包含图片与 PDF 混合格式），验证以下内容：\n- 两条流水线均能正确提取所有 8 个结构化字段\n- 审核规则能够准确标记不合规发票，并给出相应的不通过原因\n- 输出的 Markdown 表格渲染正常\n\n确认无误后，点击**发布**，即可获取 WebApp 链接或 API 接口，供后续系统集成使用。","readmeExcerpt":"**1. 安装通义插件** 前往**插件市场**，搜索并安装**通义**插件（langgenius/tongyi）。随后进入**设置 → 模型供应商**，填写您的阿里云 API Key，以激活本工作流所需的以下两个模型： - qwen-vl-plus — 多模态视觉模型，用于识别**图片格式发票** - qvq-max-latest — 推理模型，用于提取**PDF 格式发票**中的结构化数据 **2. 配置开始节点** 开始节点接收一个名为 files 的文件列表输入变量，请确保以下上传配置已正确设置： - **支持的文件类型：** 图片（.JPG、.JPEG、.PNG、.GIF、.WEBP、.SVG）及文档（PDF） - **上传方式：** 本地文件上传与远程 URL - 该输入变量将同时为图片处理流水线与 PDF 处理流水线提供数据 **3. 了解双流水线架构** 工作流在开始节点之后立即分为两条并行处理分支： - **图","codeSnippets":[],"executableExamples":[],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[],"languages":["zh-Hans"],"docsSourceLabel":"Dify","editorialOverview":"发票审核工作流 是一套自动化发票审核工作流，可同时处理图片格式与 PDF 格式的发票。它借助阿里云通义系列多模态大语言模型，从发票中提取结构化数据，再通过基于规则的 Python 审核引擎对每张发票进行合规校验，最终以清晰的 Markdown 表格形式输出审核结果，将通过与未通过的发票分类呈现。 **1. 安装通义插件** 前往**插件市场**，搜索并安装**通义**插件（langgenius/tongyi）。随后进入**设置 → 模型供应商**，填写您的阿里云 API Key，以激活本工作流所需的以下两个模型： - qwen-vl-plus — 多模态视觉模型，用于识别**图片格式发票** - qvq-max-latest — 推理模型，用于提取**PDF 格式发票**中的结构化数据 **2. 配置开始节点** 开始节点接收一个名为 files 的文件列表输入变量，请确保以下上传配置已正确设置： - **支持的文件类型：** 图片（.JPG、.JPEG、.PNG、.GIF、.WEBP、.SVG）及文档（PDF） - **上传方式：** 本地文件上传与远程 URL - 该输入变量将同时为图片处理流水线与 PDF 处理流水线提供数据 **3. 了解双流水线架构** 工作流在开始节点之后立即分为两条并行处理分支： - **图","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":314,"uniquenessScore":73,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T01:20:58.015Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-09T01:20:58.015Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"agent-directory","verified":false,"confidence":"low","updatedAt":"2026-10-09T04:15:19.593Z","emptyReason":"No close protocol neighbors were found."},"items":[],"links":{"hub":"/agent","source":"/agent/source/dify_marketplace","protocols":[]}}}