递归混合RAG 1

• •Google Drive API 凭证
• •可能需要目标 API 的认证凭证
• •OpenAI API Key
• •Google Gemini API Key
• •Supabase URL 和 API Key

{
  "id": "gqPf4clVkEeEFul1",
  "meta": {
    "instanceId": "0fa2e5f9f1c8b82cfe9c3f2c5d75842c6c2d1b07596b807d7aaa439c3a697b30",
    "templateCredsSetupCompleted": true
  },
  "name": "递归混合 RAG 1",
  "tags": [],
  "nodes": [
    {
      "id": "95e00865-e2e3-4db6-a423-43488be3da42",
      "name": "Google Drive 触发器",
      "type": "n8n-nodes-base.googleDriveTrigger",
      "position": [
        -360,
        -40
      ],
      "parameters": {
        "event": "fileCreated",
        "options": {},
        "pollTimes": {
          "item": [
            {
              "mode": "everyMinute"
            }
          ]
        },
        "triggerOn": "specificFolder",
        "folderToWatch": {
          "__rl": true,
          "mode": "list",
          "value": "10c4lWGMSkqZc5JhsyDxZ-jzgBaEEItqU",
          "cachedResultUrl": "https://drive.google.com/drive/folders/10c4lWGMSkqZc5JhsyDxZ-jzgBaEEItqU",
          "cachedResultName": "OpenAI IMG Gen 1"
        }
      },
      "credentials": {
        "googleDriveOAuth2Api": {
          "id": "gLXppgYt00TU079t",
          "name": "Google Drive account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "43fe3da8-bc96-44da-a298-bb3ab59e6328",
      "name": "遍历项目",
      "type": "n8n-nodes-base.splitInBatches",
      "position": [
        -140,
        -40
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 3
    },
    {
      "id": "746c437e-ad11-4e79-995f-50d6e1211748",
      "name": "Google Drive",
      "type": "n8n-nodes-base.googleDrive",
      "position": [
        300,
        -40
      ],
      "parameters": {
        "fileId": {
          "__rl": true,
          "mode": "id",
          "value": "={{ $json.File_id }}"
        },
        "options": {
          "googleFileConversion": {
            "conversion": {
              "docsToFormat": "text/plain"
            }
          }
        },
        "operation": "download"
      },
      "credentials": {
        "googleDriveOAuth2Api": {
          "id": "gLXppgYt00TU079t",
          "name": "Google Drive account"
        }
      },
      "typeVersion": 3
    },
    {
      "id": "5ffd763b-e0f7-4ed4-8195-9a4da5b281bb",
      "name": "Switch",
      "type": "n8n-nodes-base.switch",
      "position": [
        520,
        -40
      ],
      "parameters": {
        "rules": {
          "values": [
            {
              "conditions": {
                "options": {
                  "version": 2,
                  "leftValue": "",
                  "caseSensitive": true,
                  "typeValidation": "strict"
                },
                "combinator": "and",
                "conditions": [
                  {
                    "id": "471108e8-3209-46d7-9a70-4b3ba48a5e2e",
                    "operator": {
                      "type": "string",
                      "operation": "equals"
                    },
                    "leftValue": "={{ $json.File_Type }}",
                    "rightValue": "application/pdf"
                  }
                ]
              }
            },
            {
              "conditions": {
                "options": {
                  "version": 2,
                  "leftValue": "",
                  "caseSensitive": true,
                  "typeValidation": "strict"
                },
                "combinator": "and",
                "conditions": [
                  {
                    "id": "217bb864-29af-43a0-9705-8222e095b48c",
                    "operator": {
                      "name": "filter.operator.equals",
                      "type": "string",
                      "operation": "equals"
                    },
                    "leftValue": "={{ $json.File_Type }}",
                    "rightValue": "text/plain"
                  }
                ]
              }
            }
          ]
        },
        "options": {}
      },
      "typeVersion": 3.2
    },
    {
      "id": "a5b0335e-f355-4959-9ece-7187d1dfd0eb",
      "name": "基础LLM链",
      "type": "@n8n/n8n-nodes-langchain.chainLlm",
      "position": [
        1840,
        -40
      ],
      "parameters": {
        "text": "=<document> \n{{ $('Document Data').item.json.data }}\n\n</document>  \n\nHere is the chunk we want to situate within the overall document:\n<chunk> \n{{ $json.chunks }}\n</chunk>  \n\nPlease: \n- Provide a short and succinct <<context>> to situate this chunk within the document for improved search retrieval. \n- Rather than describing numbers, terms, or phrases as provided unless a correction is necessary. \n- If the chunk contains an <<incomplete number, percentage, or entity>>, correct it using the full document. \n- If part of a sentence is cut off, reconstruct the missing words only if necessary for clarity. \n- If the chunk is part of a table, include the complete table entry to preserve data integrity \n- Do not add any additional explanations or formatting beyond the required output. \n\nFill in the following format: [succinct context]: [original chunk or corrected version if necessary]  \n\nYour response should contain only the text that replaces these placeholders, without including the placeholders, tags, or these themselves.",
        "batching": {},
        "promptType": "define"
      },
      "typeVersion": 1.7
    },
    {
      "id": "cff6ca9c-0e14-4096-8d58-d9ea332752f3",
      "name": "OpenAI 聊天模型",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        1928,
        180
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4o-mini"
        },
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "id": "N8oave6roxa4SXEA",
          "name": "OpenAi account 2"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "c60ac23d-f256-4960-a1c2-b3238f018751",
      "name": "总结",
      "type": "n8n-nodes-base.summarize",
      "position": [
        2220,
        -40
      ],
      "parameters": {
        "options": {},
        "fieldsToSummarize": {
          "values": [
            {
              "field": "text",
              "separateBy": "other",
              "aggregation": "concatenate",
              "customSeparator": "###SPLIT###"
            }
          ]
        }
      },
      "typeVersion": 1.1
    },
    {
      "id": "68beae62-7378-4ef6-a6fc-8d5f73eb5f19",
      "name": "Embeddings OpenAI",
      "type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
      "position": [
        2436,
        180
      ],
      "parameters": {
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "id": "N8oave6roxa4SXEA",
          "name": "OpenAi account 2"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "f395021c-634c-4615-9630-bb1b06020504",
      "name": "Supabase Vector Store",
      "type": "@n8n/n8n-nodes-langchain.vectorStoreSupabase",
      "position": [
        2452,
        -40
      ],
      "parameters": {
        "mode": "insert",
        "options": {},
        "tableName": {
          "__rl": true,
          "mode": "list",
          "value": "documents",
          "cachedResultName": "documents"
        }
      },
      "credentials": {
        "supabaseApi": {
          "id": "KC4GHDFxEISJGMwB",
          "name": "Supabase account 3"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "ec2fa582-cc8b-4284-90e4-4dccb4f11779",
      "name": "默认数据加载器",
      "type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
      "position": [
        2556,
        182.5
      ],
      "parameters": {
        "options": {
          "metadata": {
            "metadataValues": [
              {
                "name": "File_url",
                "value": "={{ $('File info').item.json.File_url }}"
              }
            ]
          }
        }
      },
      "typeVersion": 1
    },
    {
      "id": "e1f6953c-4fe0-43fa-bb86-77371e956d9b",
      "name": "字符文本分割器",
      "type": "@n8n/n8n-nodes-langchain.textSplitterCharacterTextSplitter",
      "position": [
        2644,
        380
      ],
      "parameters": {
        "chunkSize": 1200,
        "separator": "###SPLIT###"
      },
      "typeVersion": 1
    },
    {
      "id": "e0d17eb8-5bf9-40d1-9642-6d853598a5aa",
      "name": "AI 代理",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        1400,
        600
      ],
      "parameters": {
        "text": "question: 1a(i)\nAnswer:Ammonia\nMark scheme:Pearson Edexcel International Advanced Level in Chemistry (WCH16) Paper 01 Unit 6: Practical Skills in Chemistry II.",
        "options": {
          "systemMessage": "=You are an AI Examiner Agent with access to a Supabase database containing exam markschemes via HTTP API. Your primary role is to mark student exam answers fairly, consistently, and accurately according to the official markscheme.\n\n## Core Responsibilities\n\n1. **Mark individual or bulk student answers** against the official markscheme stored in your database\n2. **Provide detailed feedback** explaining how marks were awarded or deducted\n3. **Maintain consistency** in marking standards across all submissions\n4. **Handle various input formats** (single answers, bulk submissions with question numbers)\n\n## Database Access Instructions\n\n- Use HTTP requests to query your Supabase database for markscheme data\n- Query markschemes by question number, exam code, or other relevant identifiers\n- Always verify you have the correct markscheme before marking any answer\n\n## Marking Process\n\n### For Individual Answers:\n1. **Identify the question** from context or ask for question number if unclear\n2. **Retrieve the relevant markscheme** from database\n3. **Compare student answer** against marking criteria\n4. **Award marks** based on markscheme rubric\n5. **Provide specific feedback** citing which criteria were met/missed\n\n### For Bulk Submissions:\n1. **Parse the submission** to extract question numbers and corresponding answers\n2. **Retrieve all relevant markschemes** in batch where possible\n3. **Mark each answer systematically**\n4. **Provide summary report** with individual question breakdowns\n5. **Calculate total score** and percentage if applicable\n\n## Marking Standards\n\n- **Accuracy**: Follow markscheme exactly - do not deviate from official criteria\n- **Fairness**: Apply same standards to all students consistently  \n- **Partial Credit**: Award partial marks for partially correct answers as specified in markscheme\n- **Alternative Answers**: Accept equivalent correct answers not explicitly listed if they demonstrate same understanding\n- **Spelling/Grammar**: Only penalize if markscheme specifically addresses language accuracy\n\n## Response Format\n\n### Individual Answer Marking:\n```\n**Question [X] - [Y] marks available**\n\n**Student Answer Analysis:**\n[Brief summary of student's response]\n\n**Marking Breakdown:**\n- Criterion 1: [X/Y marks] - [Explanation]\n- Criterion 2: [X/Y marks] - [Explanation]\n- etc.\n\n**Total Score: [X/Y] marks**\n\n**Feedback:**\n[Constructive feedback on strengths and areas for improvement]\n```\n\n### Bulk Marking Summary:\n```\n**Exam Marking Summary**\n\n**Overall Score: [X/Y] marks ([Z]%)**\n\n**Question-by-Question Breakdown:**\nQ1: [X/Y] marks - [Brief comment]\nQ2: [X/Y] marks - [Brief comment]\n[etc.]\n\n**Detailed Analysis:**\n[Per question detailed breakdown using individual format above]\n\n**Overall Performance Summary:**\n[Strengths, weaknesses, grade indication if applicable]\n```\n\n## Error Handling\n\n- If question number is unclear, ask for clarification\n- If markscheme cannot be found, request exam details (exam code, subject, etc.)\n- If student answer is ambiguous, explain interpretation used for marking\n- If database access fails, inform user and request manual markscheme provision\n\n## Key Behaviors\n\n- **Be objective and impartial** in all marking decisions\n- **Explain your reasoning** clearly for all mark allocations\n- **Be constructive** in feedback while maintaining marking integrity\n- **Ask for clarification** when inputs are ambiguous\n- **Maintain professional tone** appropriate for educational assessment\n\n## Input Processing\n\nYou can handle various input formats:\n- Single question: \"Q5: [student answer]\"\n- Multiple questions: \"Q1: [answer] Q2: [answer] Q3: [answer]\" \n- Formatted submissions with clear question/answer separation\n- Requests for specific question markschemes for student review\n\nAlways confirm the question number and retrieve the correct markscheme before beginning marking.\n\nReady to begin marking. Please provide the student answer(s) along with question number(s) for assessment."
        },
        "promptType": "define"
      },
      "typeVersion": 2
    },
    {
      "id": "cc7fc092-1975-45ef-ac8c-62196b4d5796",
      "name": "便签",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -980,
        -260
      ],
      "parameters": {
        "width": 540,
        "height": 640,
        "content": "1. **文档摄取和处理**"
      },
      "typeVersion": 1
    },
    {
      "id": "7989a21e-2947-4ba4-bd42-21a169de2e70",
      "name": "便签1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        240,
        500
      ],
      "parameters": {
        "color": 4,
        "width": 380,
        "height": 420,
        "content": "**向我提问**"
      },
      "typeVersion": 1
    },
    {
      "id": "dfe4fbd8-b358-46a2-bcf9-c2c5027cca9d",
      "name": "点击\"执行工作流\"时",
      "type": "n8n-nodes-base.manualTrigger",
      "position": [
        720,
        600
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "aed9c156-dcea-4fd8-887e-cb993e50e18b",
      "name": "Google Gemini 聊天模型",
      "type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
      "position": [
        1440,
        820
      ],
      "parameters": {
        "options": {},
        "modelName": "models/gemini-2.5-flash-preview-04-17"
      },
      "credentials": {
        "googlePalmApi": {
          "id": "DWxgjfTLFzyeKnsm",
          "name": "Google Gemini(PaLM) Api account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "d9be2c8f-9f4f-475a-a30f-303389524e28",
      "name": "OpenAI",
      "type": "@n8n/n8n-nodes-langchain.openAi",
      "position": [
        1040,
        600
      ],
      "parameters": {
        "modelId": {
          "__rl": true,
          "mode": "list",
          "value": "chatgpt-4o-latest",
          "cachedResultName": "CHATGPT-4O-LATEST"
        },
        "options": {},
        "resource": "image",
        "inputType": "base64",
        "operation": "analyze"
      },
      "credentials": {
        "openAiApi": {
          "id": "N8oave6roxa4SXEA",
          "name": "OpenAi account 2"
        }
      },
      "typeVersion": 1.8
    },
    {
      "id": "803ccebd-69fe-4954-809d-9cd0b355fd6e",
      "name": "文件信息",
      "type": "n8n-nodes-base.set",
      "position": [
        80,
        -40
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "b4b888bd-827f-4721-b553-b3e1cf38e3fe",
              "name": "File_id",
              "type": "string",
              "value": "={{ $json.id }}"
            },
            {
              "id": "dcf732a3-aaf5-41a6-8bad-fc06a74e1263",
              "name": "File_Type",
              "type": "string",
              "value": "={{ $json.mimeType }}"
            },
            {
              "id": "5b9870de-94d0-470b-bb9c-e129e895feea",
              "name": "File_url",
              "type": "string",
              "value": "={{ $json.webViewLink }}"
            },
            {
              "id": "4ec5bfff-f78b-406b-a5da-ca2c81e3c41b",
              "name": "File_name",
              "type": "string",
              "value": "={{ $json.name }}"
            }
          ]
        }
      },
      "typeVersion": 3.4
    },
    {
      "id": "c1926c20-88d6-4a95-a9d4-8dd2d1665b77",
      "name": "从 PDF 提取",
      "type": "n8n-nodes-base.extractFromFile",
      "position": [
        740,
        -140
      ],
      "parameters": {
        "options": {},
        "operation": "pdf"
      },
      "typeVersion": 1
    },
    {
      "id": "e4fc2a52-e1ea-424e-861f-fee7fceaa1cc",
      "name": "从 TEXT 提取",
      "type": "n8n-nodes-base.extractFromFile",
      "position": [
        960,
        60
      ],
      "parameters": {
        "options": {},
        "operation": "text"
      },
      "typeVersion": 1
    },
    {
      "id": "09a9112a-9c72-4965-818e-2351aad7528e",
      "name": "PDF 转 DATA",
      "type": "n8n-nodes-base.set",
      "position": [
        960,
        -140
      ],
      "parameters": {
        "mode": "raw",
        "options": {},
        "jsonOutput": "={\n  \"data\":{{JSON.stringify($json.text)}}\n}\n"
      },
      "typeVersion": 3.4
    },
    {
      "id": "d4b03066-b191-439c-b1e9-f3a5b325f1fd",
      "name": "递归分割器",
      "type": "n8n-nodes-base.code",
      "position": [
        1400,
        -40
      ],
      "parameters": {
        "jsCode": "const chunkSize = 1000;\nconst chunkOverlap = 200;\nconst text = $input.item.json.data.replace(/\\n/g, '');\n\nconst chunks = [];\nlet remainingText = text;\n\nwhile (remainingText.length > 0) {\n    let splitPoint;\n    \n    // Try splitting at paragraph level first\n    splitPoint = remainingText.lastIndexOf(\"\\n\\n\", chunkSize);\n    \n    // If no paragraph split, try splitting at sentence level\n    if (splitPoint === -1) {\n        splitPoint = remainingText.lastIndexOf(\". \", chunkSize);\n    }\n    \n    // If no sentence split, try splitting at word level\n    if (splitPoint === -1) {\n        splitPoint = remainingText.lastIndexOf(\" \", chunkSize);\n    }\n    \n    // If still no split point, force split at chunkSize\n    if (splitPoint === -1 || splitPoint < chunkSize * 0.5) {\n        splitPoint = chunkSize; // Hard split if no good split point\n    }\n    \n    // Extract chunk and adjust remaining text with overlap\n    let chunk = remainingText.substring(0, splitPoint).trim();\n    chunks.push(chunk);\n    \n    // Move the pointer forward while keeping the overlap\n    remainingText = remainingText.substring(Math.max(0, splitPoint - chunkOverlap)).trim();\n    \n    // Break if remaining text is too small to form another chunk\n    if (remainingText.length < chunkSize * 0.2) {\n        chunks.push(remainingText);\n        break;\n    }\n}\n\nreturn { chunks };"
      },
      "typeVersion": 2
    },
    {
      "id": "1f9b5ef2-c719-44e2-95a5-80566739345a",
      "name": "文档数据",
      "type": "n8n-nodes-base.set",
      "position": [
        1180,
        -40
      ],
      "parameters": {
        "mode": "raw",
        "options": {},
        "jsonOutput": "={\n  \"data\":{{ JSON.stringify($json.data) }}\n}\n"
      },
      "typeVersion": 3.4
    },
    {
      "id": "ba9f2a39-e3cb-45aa-9de7-8ae9a3331150",
      "name": "分块分割",
      "type": "n8n-nodes-base.splitOut",
      "position": [
        1620,
        -40
      ],
      "parameters": {
        "options": {},
        "fieldToSplitOut": "chunks"
      },
      "typeVersion": 1
    },
    {
      "id": "46440496-6abc-46a2-843a-15988a4f717a",
      "name": "SupaBase 查询",
      "type": "n8n-nodes-base.httpRequestTool",
      "position": [
        1680,
        820
      ],
      "parameters": {
        "url": "https://etvncxazsxflierkgyge.supabase.co/functions/v1/query-DB",
        "method": "POST",
        "options": {
          "redirect": {
            "redirect": {}
          }
        },
        "sendBody": true,
        "sendHeaders": true,
        "bodyParameters": {
          "parameters": [
            {
              "name": "query",
              "value": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('parameters0_Value', ``, 'string') }}"
            }
          ]
        },
        "headerParameters": {
          "parameters": [
            {
              "name": "Authorization",
              "value": "Your Supabase Key"
            }
          ]
        }
      },
      "typeVersion": 4.2
    }
  ],
  "active": false,
  "pinData": {},
  "settings": {
    "timezone": "Asia/Dubai",
    "callerPolicy": "workflowsFromSameOwner",
    "executionOrder": "v1"
  },
  "versionId": "97fe98d5-09dc-43d7-a169-8de91c02fb37",
  "connections": {
    "OpenAI": {
      "main": [
        [
          {
            "node": "AI Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Switch": {
      "main": [
        [
          {
            "node": "Extract from PDF",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Extract from TEXT",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "File info": {
      "main": [
        [
          {
            "node": "Google Drive",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Summarize": {
      "main": [
        [
          {
            "node": "Supabase Vector Store",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "PDF to DATA": {
      "main": [
        [
          {
            "node": "Document Data",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Google Drive": {
      "main": [
        [
          {
            "node": "Switch",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Document Data": {
      "main": [
        [
          {
            "node": "Recursive Splitter",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "SupaBase Query": {
      "ai_tool": [
        [
          {
            "node": "AI Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "Basic LLM Chain": {
      "main": [
        [
          {
            "node": "Summarize",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Chunk Splitting": {
      "main": [
        [
          {
            "node": "Basic LLM Chain",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Loop Over Items": {
      "main": [
        [],
        [
          {
            "node": "File info",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract from PDF": {
      "main": [
        [
          {
            "node": "PDF to DATA",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Embeddings OpenAI": {
      "ai_embedding": [
        [
          {
            "node": "Supabase Vector Store",
            "type": "ai_embedding",
            "index": 0
          }
        ]
      ]
    },
    "Extract from TEXT": {
      "main": [
        [
          {
            "node": "Document Data",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "Basic LLM Chain",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Recursive Splitter": {
      "main": [
        [
          {
            "node": "Chunk Splitting",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Default Data Loader": {
      "ai_document": [
        [
          {
            "node": "Supabase Vector Store",
            "type": "ai_document",
            "index": 0
          }
        ]
      ]
    },
    "Google Drive Trigger": {
      "main": [
        [
          {
            "node": "Loop Over Items",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Character Text Splitter": {
      "ai_textSplitter": [
        [
          {
            "node": "Default Data Loader",
            "type": "ai_textSplitter",
            "index": 0
          }
        ]
      ]
    },
    "Google Gemini Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "AI Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "When clicking ‘Execute workflow’": {
      "main": [
        [
          {
            "node": "OpenAI",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}