8
n8n 中文网amn8n.com

解析、规范化、提取 PDF 内容并存储到 Pinecone 以用于 RAG

高级

这是一个AI RAG, Multimodal AI领域的自动化工作流，包含 18 个节点。主要使用 If, Code, Wait, GoogleDrive, HttpRequest 等节点。 使用LlamaIndex、OpenAI嵌入和Pinecone向量数据库构建PDF问答系统

前置要求
  • •Google Drive API 凭证
  • •可能需要目标 API 的认证凭证
  • •OpenAI API Key
  • •Pinecone API Key

使用的节点 (18)

If
Code
Wait
StickyNote
GoogleDrive
HttpRequest
GoogleDriveTrigger
EmbeddingsOpenAi
VectorStorePinecone
DocumentDefaultDataLoader
TextSplitterRecursiveCharacterTextSplitter

分类

AI RAG 检索增强
多模态 AI
工作流预览
可视化展示节点连接关系，支持缩放和平移
React Flow
导出工作流
复制以下 JSON 配置到 n8n 导入，即可使用此工作流
{
  "id": "xDiuqZUZnShKpPzX",
  "meta": {
    "instanceId": "70273a2379644db63ce659827cfd8abac2d0b189210eafa02dd5376e3a62cd1d",
    "templateCredsSetupCompleted": true
  },
  "name": "解析、规范化、提取 PDF 内容并存储到 Pinecone 以用于 RAG",
  "tags": [],
  "nodes": [
    {
      "id": "19b009db-a418-458c-a216-bdcc9af6fd2f",
      "name": "Google Drive触发器",
      "type": "n8n-nodes-base.googleDriveTrigger",
      "position": [
        -1504,
        2080
      ],
      "parameters": {
        "event": "fileCreated",
        "options": {},
        "pollTimes": {
          "item": [
            {
              "mode": "everyMinute"
            }
          ]
        },
        "triggerOn": "specificFolder",
        "folderToWatch": {
          "__rl": true,
          "mode": "list",
          "value": ""
        }
      },
      "credentials": {
        "googleDriveOAuth2Api": {
          "id": "aU33fzddE6s3ZQw6",
          "name": "LearnBy-Google-Drive"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "ff933f76-d719-40b5-b193-8a29e5fa2197",
      "name": "下载文件",
      "type": "n8n-nodes-base.googleDrive",
      "position": [
        -1248,
        2096
      ],
      "parameters": {
        "fileId": {
          "__rl": true,
          "mode": "id",
          "value": "={{ $json.id }}"
        },
        "options": {},
        "operation": "download"
      },
      "credentials": {
        "googleDriveOAuth2Api": {
          "id": "aU33fzddE6s3ZQw6",
          "name": "LearnBy-Google-Drive"
        }
      },
      "typeVersion": 3
    },
    {
      "id": "127b41ed-ad45-4234-b87f-4f3c2b6ea531",
      "name": "默认数据加载器",
      "type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
      "position": [
        528,
        2192
      ],
      "parameters": {
        "options": {},
        "textSplittingMode": "custom"
      },
      "typeVersion": 1.1
    },
    {
      "id": "0316c7d4-449f-4275-a9b1-8848545beba8",
      "name": "便签",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        336,
        1712
      ],
      "parameters": {
        "width": 736,
        "height": 832,
        "content": "## 保存到向量数据库"
      },
      "typeVersion": 1
    },
    {
      "id": "b06702b5-c322-4a5a-949a-855c8b97dadc",
      "name": "便签1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1088,
        1720
      ],
      "parameters": {
        "color": 4,
        "width": 1392,
        "height": 656,
        "content": "## 准备数据 - 解析和规范化"
      },
      "typeVersion": 1
    },
    {
      "id": "05034e35-f6bf-45a6-860e-94f4da566daf",
      "name": "等待",
      "type": "n8n-nodes-base.wait",
      "position": [
        -720,
        2088
      ],
      "webhookId": "a0518843-31f8-44f9-bd8e-1189e16de0f1",
      "parameters": {
        "amount": 30
      },
      "typeVersion": 1.1
    },
    {
      "id": "9bb49bf6-a02e-4cf7-a1d1-ca4addff2bc6",
      "name": "条件判断",
      "type": "n8n-nodes-base.if",
      "position": [
        -272,
        2016
      ],
      "parameters": {
        "options": {},
        "conditions": {
          "options": {
            "version": 2,
            "leftValue": "",
            "caseSensitive": true,
            "typeValidation": "strict"
          },
          "combinator": "and",
          "conditions": [
            {
              "id": "7a07aec1-fc5f-4b76-94d9-6fa8f509ac8e",
              "operator": {
                "name": "filter.operator.equals",
                "type": "string",
                "operation": "equals"
              },
              "leftValue": "={{ $json.status }}",
              "rightValue": "SUCCESS"
            }
          ]
        }
      },
      "typeVersion": 2.2
    },
    {
      "id": "28654aff-e603-4080-9e7a-e706aaee47c4",
      "name": "等待 2",
      "type": "n8n-nodes-base.wait",
      "position": [
        -48,
        2184
      ],
      "webhookId": "8da5da31-1ebd-4c82-8c6a-476d5d277cdd",
      "parameters": {
        "amount": 60
      },
      "typeVersion": 1.1
    },
    {
      "id": "ba935542-d2c0-4781-b6f9-5e1e007a9740",
      "name": "便签2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        0,
        1584
      ],
      "parameters": {
        "width": 288,
        "height": 352,
        "content": "## 规范化内容"
      },
      "typeVersion": 1
    },
    {
      "id": "45efcdf9-89a9-4638-a9ed-cac39506270f",
      "name": "便签3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -2080,
        1472
      ],
      "parameters": {
        "width": 464,
        "height": 1200,
        "content": "## 试试看！"
      },
      "typeVersion": 1
    },
    {
      "id": "34f5ba5e-7f4e-4c94-a4e8-41bfbaf163a1",
      "name": "上传到 Llama Cloud",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        -944,
        2088
      ],
      "parameters": {
        "url": "https://api.cloud.llamaindex.ai/api/v1/parsing/upload",
        "method": "POST",
        "options": {},
        "sendBody": true,
        "contentType": "multipart-form-data",
        "sendHeaders": true,
        "authentication": "genericCredentialType",
        "bodyParameters": {
          "parameters": [
            {
              "name": "file",
              "parameterType": "formBinaryData",
              "inputDataFieldName": "data"
            }
          ]
        },
        "genericAuthType": "httpBearerAuth",
        "headerParameters": {
          "parameters": [
            {
              "name": "accept",
              "value": "application/json"
            },
            {
              "name": "Content-Type",
              "value": "multipart/form-data"
            }
          ]
        }
      },
      "credentials": {
        "httpBearerAuth": {
          "id": "FlAAm17M7G6as02l",
          "name": "learnby_llama_cloud"
        }
      },
      "executeOnce": false,
      "retryOnFail": true,
      "typeVersion": 4.2,
      "alwaysOutputData": false
    },
    {
      "id": "1199e4ff-1952-4225-b655-1f63875f8903",
      "name": "检查解析状态",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        -496,
        2088
      ],
      "parameters": {
        "url": "=https://api.cloud.llamaindex.ai/api/parsing/job/{{ $('Upload to Llama Cloud').item.json.id }}",
        "options": {},
        "sendHeaders": true,
        "authentication": "genericCredentialType",
        "genericAuthType": "httpBearerAuth",
        "headerParameters": {
          "parameters": [
            {
              "name": "accept",
              "value": "application/json"
            }
          ]
        }
      },
      "credentials": {
        "httpBearerAuth": {
          "id": "FlAAm17M7G6as02l",
          "name": "learnby_llama_cloud"
        }
      },
      "retryOnFail": true,
      "typeVersion": 4.2
    },
    {
      "id": "cfaf9e10-0297-423a-b3f4-c25561c92078",
      "name": "从 Llama Cloud 提取 Markdown",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        -48,
        1968
      ],
      "parameters": {
        "url": "=https://api.cloud.llamaindex.ai/api/v1/parsing/job/{{ $json.id }}/result/markdown",
        "options": {},
        "sendHeaders": true,
        "authentication": "genericCredentialType",
        "genericAuthType": "httpBearerAuth",
        "headerParameters": {
          "parameters": [
            {
              "name": "accept",
              "value": "application/json"
            }
          ]
        }
      },
      "credentials": {
        "httpBearerAuth": {
          "id": "FlAAm17M7G6as02l",
          "name": "learnby_llama_cloud"
        }
      },
      "retryOnFail": true,
      "typeVersion": 4.2
    },
    {
      "id": "564a0930-e80b-4db6-a62a-5224248e5cd9",
      "name": "规范化文本",
      "type": "n8n-nodes-base.code",
      "position": [
        176,
        1968
      ],
      "parameters": {
        "mode": "runOnceForEachItem",
        "jsCode": "// Get the input text from the previous node\nconst input = $json.markdown || $json.text || \"\";\n\nlet text = input.replace(/Car Insurance Policy\\s*\\d+/gi, \"\");\n\n// Remove \"Page X\" markers\ntext = text.replace(/Page\\s*\\d+/gi, \"\");\n\n// Replace --- dividers with a single newline\ntext = text.replace(/-{3,}/g, \"\\n\");\n\n// Decode & cleanup artifacts\ntext = text.replace(/&/g, \"&\");   // fix HTML entities\ntext = text.replace(/[ⓤ]/g, \"-\");      // replace bullet symbols with dashes\n\n// Collapse whitespace\ntext = text.replace(/\\n{2,}/g, \"\\n\\n\"); // keep paragraph breaks\ntext = text.replace(/[ \\t]+/g, \" \");    // collapse spaces\n\n// Step 5: Trim\ntext = text.trim();\n\n// Output for next node\nreturn { json: { normalizedText: text } };\n"
      },
      "typeVersion": 2
    },
    {
      "id": "fe32694a-2cbc-4ad4-88aa-4eb3dba0256c",
      "name": "分块文本",
      "type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
      "position": [
        608,
        2400
      ],
      "parameters": {
        "options": {
          "splitCode": "markdown"
        },
        "chunkSize": 1200,
        "chunkOverlap": 150
      },
      "typeVersion": 1
    },
    {
      "id": "b399c9fa-03d7-4126-9026-674d091b9ddf",
      "name": "生成嵌入",
      "type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
      "position": [
        400,
        2192
      ],
      "parameters": {
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "id": "Yj4Rt75fspowAEru",
          "name": "nextweb-openai"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "1da27207-b77e-41d0-a249-5096ec8ac259",
      "name": "存储到 Pinecone",
      "type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
      "position": [
        432,
        1968
      ],
      "parameters": {
        "mode": "insert",
        "options": {
          "pineconeNamespace": "rag"
        },
        "pineconeIndex": {
          "__rl": true,
          "mode": "id",
          "value": "demo"
        }
      },
      "credentials": {
        "pineconeApi": {
          "id": "uo1lZDPNWTsMAeOC",
          "name": "learnby-PineconeApi-account"
        }
      },
      "notesInFlow": false,
      "typeVersion": 1.3
    },
    {
      "id": "4f65ec8b-f936-41cb-b05c-0cc710df1c9e",
      "name": "便签说明4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1568,
        1728
      ],
      "parameters": {
        "color": 6,
        "width": 464,
        "height": 640,
        "content": "## 提取数据"
      },
      "typeVersion": 1
    }
  ],
  "active": false,
  "pinData": {},
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "5ec0ee83-34cd-423d-8bd5-41400bde4a4a",
  "connections": {
    "If": {
      "main": [
        [
          {
            "node": "Extract Markdown from Llama Cloud",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Wait2",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Wait": {
      "main": [
        [
          {
            "node": "Check Parsing Status",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Wait2": {
      "main": [
        [
          {
            "node": "Check Parsing Status",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Chunk Text": {
      "ai_textSplitter": [
        [
          {
            "node": "Default Data Loader",
            "type": "ai_textSplitter",
            "index": 0
          }
        ]
      ]
    },
    "Download file": {
      "main": [
        [
          {
            "node": "Upload to Llama Cloud",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Normalize Text": {
      "main": [
        [
          {
            "node": "Store in Pinecone",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Store in Pinecone": {
      "main": [
        []
      ]
    },
    "Default Data Loader": {
      "ai_document": [
        [
          {
            "node": "Store in Pinecone",
            "type": "ai_document",
            "index": 0
          }
        ]
      ]
    },
    "Generate Embeddings": {
      "ai_embedding": [
        [
          {
            "node": "Store in Pinecone",
            "type": "ai_embedding",
            "index": 0
          }
        ]
      ]
    },
    "Check Parsing Status": {
      "main": [
        [
          {
            "node": "If",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Google Drive Trigger": {
      "main": [
        [
          {
            "node": "Download file",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Upload to Llama Cloud": {
      "main": [
        [
          {
            "node": "Wait",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract Markdown from Llama Cloud": {
      "main": [
        [
          {
            "node": "Normalize Text",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}
常见问题

如何使用这个工作流？

复制上方的 JSON 配置代码，在您的 n8n 实例中创建新工作流并选择「从 JSON 导入」，粘贴配置后根据需要修改凭证设置即可。

这个工作流适合什么场景？

高级 - AI RAG 检索增强, 多模态 AI

需要付费吗？

本工作流完全免费，您可以直接导入使用。但请注意，工作流中使用的第三方服务（如 OpenAI API）可能需要您自行付费。

相关工作流推荐

上下文混合RAG AI文案
Google Drive到Supabase上下文向量数据库同步用于RAG应用
If
Set
Code
+25
76 节点Michael Taleb
AI RAG 检索增强
使用Google Maps、GPT-4和WhatsApp自动化商业合作伙伴拓展
使用Google Maps、GPT-4和WhatsApp自动化商业合作伙伴拓展
If
Set
Code
+23
64 节点Khairul Muhtadin
AI 聊天机器人
使用Rag自动重新发布工作
基于 RAG、Jina AI 和 OpenAI 到 WordPress 的自动化职位提取与发布
If
Set
Code
+18
56 节点Khairul Muhtadin
人力资源
自动职位列表提取与发布模板
自动职位列表提取与发布模板
If
Set
Code
+14
53 节点Khairul Muhtadin
人力资源
基于网站内容和Airtable数据构建用于RAG应用的聊天机器人
基于Pinecone、Airtable和OpenAI的网站内容聊天机器人（RAG应用）
Set
Code
Markdown
+15
27 节点Alok Kumar
AI RAG 检索增强
文档摄取
使用 Google Drive、Sheets 和 OpenAI 自动化文档摄取与 RAG 系统
If
Form
Crypto
+13
28 节点Mohamed Abdelwahab
杂项
工作流信息
难度等级
高级
节点数量18
分类2
节点类型11
难度说明

适合高级用户，包含 16+ 个节点的复杂工作流

作者
Alok Kumar

Alok Kumar

@alokkumar

I am a Principal Software Engineer based in Ireland with a deep passion for AI and emerging technologies. With extensive experience in designing and implementing scalable software solutions, I focus on leveraging artificial intelligence to solve real-world problems. I enjoy exploring innovative applications of AI, from intelligent automation to data-driven insights, and I’m dedicated to building systems that are both efficient and impactful.

外部链接
在 n8n.io 查看 →

分享此工作流