Document Q&a System with Openai Gpt, Pinecone Vector Db & Google Drive…

The workflow JSON

Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →

{
  "id": "UVMlpwIIsDBBFclU",
  "meta": {
    "templateCredsSetupCompleted": true
  },
  "name": "AI-Powered Document QA System using Webhook, Pinecone + OpenAI + n8n",
  "tags": [
    {
      "id": "Bv4R1pgV3YCnUGME",
      "name": "webhook",
      "createdAt": "2025-07-04T05:26:19.837Z",
      "updatedAt": "2025-07-04T05:26:19.837Z"
    },
    {
      "id": "lTpSGA7vnSvUGQs6",
      "name": "lovable",
      "createdAt": "2025-07-04T05:26:29.453Z",
      "updatedAt": "2025-07-04T05:26:29.453Z"
    },
    {
      "id": "oKGIn6U0wpeHShTN",
      "name": "working flow",
      "createdAt": "2025-06-02T06:27:44.762Z",
      "updatedAt": "2025-06-02T06:27:44.762Z"
    }
  ],
  "nodes": [
    {
      "id": "784badb8-0cf6-434d-9d5d-1670757b548b",
      "name": "When clicking \u2018Execute workflow\u2019",
      "type": "n8n-nodes-base.manualTrigger",
      "position": [
        -300,
        -40
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "26b93e8c-0a72-4491-90fe-55b5f5da02a0",
      "name": "Google Drive",
      "type": "n8n-nodes-base.googleDrive",
      "position": [
        -80,
        -40
      ],
      "parameters": {
        "filter": {
          "folderId": {
            "__rl": true,
            "mode": "list",
            "value": "1NgITWoqBgLAVof9bxF0jIrVToQ9c919u",
            "cachedResultUrl": "https://drive.google.com/drive/folders/1NgITWoqBgLAVof9bxF0jIrVToQ9c919u",
            "cachedResultName": "contract document"
          }
        },
        "options": {},
        "resource": "fileFolder"
      },
      "credentials": {
        "googleDriveOAuth2Api": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 3
    },
    {
      "id": "21174f84-5f7b-45bc-944b-0f0a7c2ffd49",
      "name": "Google Drive1",
      "type": "n8n-nodes-base.googleDrive",
      "position": [
        140,
        -40
      ],
      "parameters": {
        "fileId": {
          "__rl": true,
          "mode": "id",
          "value": "={{ $json.id }}"
        },
        "options": {},
        "operation": "download"
      },
      "credentials": {
        "googleDriveOAuth2Api": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 3
    },
    {
      "id": "d84e6051-cc04-4f51-b9c3-0e69e2193571",
      "name": "Pinecone Vector Store",
      "type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
      "position": [
        360,
        -40
      ],
      "parameters": {
        "mode": "insert",
        "options": {},
        "pineconeIndex": {
          "__rl": true,
          "mode": "list",
          "value": "package1536",
          "cachedResultName": "package1536"
        }
      },
      "credentials": {
        "pineconeApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.3
    },
    {
      "id": "3185a781-28af-4ee0-be7b-2183b80ce0e3",
      "name": "Embeddings OpenAI",
      "type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
      "position": [
        300,
        160
      ],
      "parameters": {
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "8eccc3bb-654f-4a92-8074-9d2418afae12",
      "name": "Default Data Loader",
      "type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
      "position": [
        500,
        180
      ],
      "parameters": {
        "options": {},
        "dataType": "binary",
        "textSplittingMode": "custom"
      },
      "typeVersion": 1.1
    },
    {
      "id": "9a6a4542-81f0-4fa6-b0fa-6fbfcf5fb3d3",
      "name": "Recursive Character Text Splitter",
      "type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
      "position": [
        600,
        400
      ],
      "parameters": {
        "options": {},
        "chunkOverlap": 100
      },
      "typeVersion": 1
    },
    {
      "id": "60485603-13aa-46c8-9824-011b75d368bd",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -420,
        -180
      ],
      "parameters": {
        "width": 1300,
        "height": 980,
        "content": "## Document Loading \n1. Connect to Google Drive folder to access Contract Agreement Documents\n2. Download and Vectorize the Data using Vector Embedding \n3. Store in Pinecone Database"
      },
      "typeVersion": 1
    },
    {
      "id": "349466bc-c0c7-4e4e-9e9c-78554a3123ae",
      "name": "Sticky Note1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -420,
        940
      ],
      "parameters": {
        "width": 1300,
        "height": 720,
        "content": "## Query Document via Chat (for testing)"
      },
      "typeVersion": 1
    },
    {
      "id": "id",
      "name": "When chat message received",
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "position": [
        -100,
        980
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 1.1
    },
    {
      "id": "4240e62e-0b44-4dbd-9cff-87a404a496bd",
      "name": "AI Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        120,
        980
      ],
      "parameters": {
        "options": {
          "systemMessage": "*Role*\nYou are a highly experienced contracting, commercial and legal adviser who thoroughly understands the contract related to shipping, clearing and forwarding agreements and advise and reply to chat queries looking into the pinecone vector database and respond accordingly. \n\n**Instructions**\nyou will receive chat query to which you have to reply back in chat\nyou will only look for information in the pinecone vector databse\nyou will not create your own reply if you don't get the answer from the database\n\nNote:\nbe polite and professional in your response\ncan use emojis where it is appropriate\n"
        }
      },
      "typeVersion": 2
    },
    {
      "id": "34d9e834-3aba-4c80-8c4d-4206fcdbfac3",
      "name": "OpenAI Chat Model",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        80,
        1200
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4.1-mini"
        },
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "784924f6-d197-4666-9a05-e36020021ae2",
      "name": "Simple Memory",
      "type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
      "position": [
        200,
        1200
      ],
      "parameters": {},
      "typeVersion": 1.3
    },
    {
      "id": "00b70c8d-5940-4eef-84c4-b87d69df3ab9",
      "name": "Answer questions with a vector store",
      "type": "@n8n/n8n-nodes-langchain.toolVectorStore",
      "position": [
        380,
        1200
      ],
      "parameters": {
        "description": "When ever there is a query from chat, use this pinecone vector database to analyse and construct the response. "
      },
      "typeVersion": 1.1
    },
    {
      "id": "dfefbee7-5125-42da-b696-f343dc89573c",
      "name": "Pinecone Vector Store1",
      "type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
      "position": [
        180,
        1360
      ],
      "parameters": {
        "options": {},
        "pineconeIndex": {
          "__rl": true,
          "mode": "list",
          "value": "package1536",
          "cachedResultName": "package1536"
        }
      },
      "credentials": {
        "pineconeApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.3
    },
    {
      "id": "8a0e2476-661e-4702-8563-ec0b12033884",
      "name": "Embeddings OpenAI1",
      "type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
      "position": [
        200,
        1500
      ],
      "parameters": {
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "31a4456c-4a35-4beb-9c4b-de49e460e492",
      "name": "OpenAI Chat Model1",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        520,
        1420
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4.1-mini"
        },
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "7aa47a91-19f9-4a0e-b1b2-5867cf4982ef",
      "name": "Sticky Note2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1660,
        -160
      ],
      "parameters": {
        "width": 1200,
        "height": 980,
        "content": "## Query document from a user interface connectied via Webhook\n"
      },
      "typeVersion": 1
    },
    {
      "id": "c9da6a17-a0aa-4d3c-844a-1c3785a956eb",
      "name": "Webhook",
      "type": "n8n-nodes-base.webhook",
      "position": [
        1900,
        0
      ],
      "parameters": {
        "path": "12b44ee5-c43e-430c-a1d4-4fc5ff5e45c4",
        "options": {},
        "httpMethod": "POST",
        "responseMode": "responseNode"
      },
      "typeVersion": 2
    },
    {
      "id": "b1e8830f-8cfe-40ef-b611-76e70cd9184b",
      "name": "AI Agent1",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        2120,
        0
      ],
      "parameters": {
        "text": "=the query: {{ $json.body.query }}",
        "options": {
          "systemMessage": "*Role*\nYou are a highly experienced contracting, commercial and legal adviser who thoroughly understands the contract related to shipping, clearing and forwarding agreements and advise and reply to chat queries looking into the pinecone vector database and respond accordingly. \n\n**Instructions**\nyou will receive chat query to which you have to reply back in chat\nyou will only look for information in the pinecone vector databse\nyou will not create your own reply if you don't get the answer from the database\n\nNote:\nbe polite and professional in your response\ncan use emojis where it is appropriate\n"
        },
        "promptType": "define"
      },
      "typeVersion": 2
    },
    {
      "id": "87db20d4-7a7c-48a6-a29a-2fd089f93a43",
      "name": "OpenAI Chat Model2",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        2020,
        220
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4.1-mini"
        },
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "2454b5ff-e53e-41c5-9844-f171d63ee2d4",
      "name": "Simple Memory1",
      "type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
      "disabled": true,
      "position": [
        2180,
        220
      ],
      "parameters": {},
      "typeVersion": 1.3
    },
    {
      "id": "e33b7eff-0166-43b2-ab7e-5f53063164a9",
      "name": "Answer questions with a vector store1",
      "type": "@n8n/n8n-nodes-langchain.toolVectorStore",
      "position": [
        2380,
        220
      ],
      "parameters": {
        "description": "When ever there is a query from chat, use this pinecone vector database to analyse and construct the response. "
      },
      "typeVersion": 1.1
    },
    {
      "id": "e223bcf1-7085-433a-a51d-708b0c36a2e4",
      "name": "Pinecone Vector Store2",
      "type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
      "position": [
        2180,
        380
      ],
      "parameters": {
        "options": {},
        "pineconeIndex": {
          "__rl": true,
          "mode": "list",
          "value": "package1536",
          "cachedResultName": "package1536"
        }
      },
      "credentials": {
        "pineconeApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.3
    },
    {
      "id": "9e3f06a1-900b-427e-8775-dad8ddc1de80",
      "name": "Embeddings OpenAI2",
      "type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
      "position": [
        2200,
        520
      ],
      "parameters": {
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "df06efec-1f75-4309-923b-044e1c1991f3",
      "name": "OpenAI Chat Model3",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        2520,
        440
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4.1-mini"
        },
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "01b59805-abdd-49ff-a553-0dddf3ed1450",
      "name": "Respond to Webhook",
      "type": "n8n-nodes-base.respondToWebhook",
      "position": [
        2480,
        0
      ],
      "parameters": {
        "options": {
          "responseKey": "={{ $json.output }}"
        }
      },
      "typeVersion": 1.4
    },
    {
      "id": "05fd0853-0ebd-4a99-9345-982c9e664e27",
      "name": "Sticky Note3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1000,
        -180
      ],
      "parameters": {
        "color": 4,
        "width": 560,
        "height": 980,
        "content": "This project demonstrates how to build a Retrieval-Augmented Generation (RAG) system using n8n, which:\n\ud83e\uddfe Downloads any pdf file format documents from Google Drive\n\ud83d\udcda Converts them into vector embeddings using OpenAI\n\ud83d\udd0d Stores and searches them in Pinecone Vector DB\n\ud83d\udcac Allows natural language querying of contracts using AI Agents\n\n## Document Loading & RAG Setup\nThis flow automates:\nReading documents from a Google Drive folder\nVectorizing using text-embedding-3-small\nUploading vectors into Pinecone for later semantic search\n\n### \ud83e\uddf1 Workflow Structure\nA [Manual Trigger] --> B[Google Drive Search]\nB --> C[Google Drive Download]\nC --> D[Pinecone Vector Store]\nD --> E[Default Data Loader]\nE --> F[Recursive Character Text Splitter]\nE --> G[OpenAI Embedding]\n\n### \ud83e\ude9c Steps\nManual Trigger: Kickstarts the workflow on demand for loading new documents.\nGoogle Drive Search & Download\nNode: Google Drive (Search: file/folder), Credentials required to access google drive folders and files\nDownloads PDF documents from the google drive\n\n#### Recursive Text Splitter to Break long documents into overlapping chunks\nSettings:\nChunk Size: 1000\nChunk Overlap: 100\n\n#### OpenAI Embedding\nModel: text-embedding-3-small\nUsed for creating document vectors\n\n#### Pinecone Vector Store\nIndex: package1536\nBatch Size: 200\nSettings:\nType: Dense\nRegion: us-east-1\nMode: Insert Documents\n\n\n"
      },
      "typeVersion": 1
    },
    {
      "id": "7f1cc5b2-104e-4571-a838-29c71c79bd08",
      "name": "Sticky Note4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1000,
        940
      ],
      "parameters": {
        "color": 4,
        "width": 560,
        "height": 720,
        "content": "## Quyerying the Documetn via Chat \nThis flow enables chat-style querying of stored documents using OpenAI-powered agents with vector memory.\n\n### \ud83e\uddf1 Workflow Diagram\n  A[Webhook (chat message)] --> B[AI Agent]\n  B --> C[OpenAI Chat Model]\n  B --> D[Simple Memory]\n  B --> E[Answer with Vector Store]\n  E --> F[Pinecone Vector Store]\n  F --> G[Embeddings OpenAI]\n### \ud83e\ude9c Components\nChat Trigger\nAI Agent Node\n\nHandles query flow using:\nChat Model: OpenAI GPT\nMemory: Simple Memory\nTool: Question Answer with Vector Store\nPinecone Vector Store\nConnected via same embedding index as Flow 1 Embeddings\nEnsures document chunks are retrievable using vector similarity\nResponse Node\nReturns final AI response to user via chat response\n\n"
      },
      "typeVersion": 1
    },
    {
      "id": "e11b8fbd-c24b-469f-a196-1e507a6d3e75",
      "name": "Sticky Note5",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1080,
        -160
      ],
      "parameters": {
        "color": 4,
        "width": 560,
        "height": 980,
        "content": "## \ud83c\udf10 Flow 3: UI-Based Query with webhook connecting to Lovable\nThis flow uses a web UI built using Lovable to query contracts directly from a form interface.\n\n### \ud83d\udce5 Webhook Setup for Lovable\nWebhook Node\nMethod: POST\nURL: your webhook url\nResponse: Using 'Respond to Webhook' Node\n\n### \ud83e\uddf1 Workflow Logic\n  A[Webhook (Lovable Form)] --> B[AI Agent]\n  B --> C[OpenAI Chat Model]\n  B --> D[Simple Memory]\n  B --> E[Answer with Vector Store]\n  E --> F[Pinecone Vector Store]\n  F --> G[Embeddings OpenAI]\n  B --> H[Respond to Webhook]\n\n### \ud83d\udca1 Lovable UI\nUsers can submit:\nFull Name\nEmail\nDepartment\nFreeform Query\n\nData is sent via webhook to n8n and responded with the answer from contract content.\n\n### \ud83d\udd0d Use Cases\nContract Querying for Legal/HR teams\nProcurement & Vendor Agreement QA\nCustomer Support Automation (based on terms)\nRAG Systems for private document knowledge\n\n\u2699\ufe0f Tools & Tech Stack\nComponent\tTool Used\nAI Embedding\tOpenAI text-embedding-3-small\nVector DB\tPinecone\nChunking\tRecursive Text Splitter\nAI Agent\tOpenAI GPT Chat\nAutomation\tn8n\nUI Integration\tLovable (form-based)\n\n\n\n"
      },
      "typeVersion": 1
    }
  ],
  "active": false,
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "460c7740-a2d1-41f7-92d5-fc9113152663",
  "connections": {
    "Webhook": {
      "main": [
        [
          {
            "node": "AI Agent1",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "AI Agent1": {
      "main": [
        [
          {
            "node": "Respond to Webhook",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Google Drive": {
      "main": [
        [
          {
            "node": "Google Drive1",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Google Drive1": {
      "main": [
        [
          {
            "node": "Pinecone Vector Store",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Simple Memory": {
      "ai_memory": [
        [
          {
            "node": "AI Agent",
            "type": "ai_memory",
            "index": 0
          }
        ]
      ]
    },
    "Simple Memory1": {
      "ai_memory": [
        [
          {
            "node": "AI Agent1",
            "type": "ai_memory",
            "index": 0
          }
        ]
      ]
    },
    "Embeddings OpenAI": {
      "ai_embedding": [
        [
          {
            "node": "Pinecone Vector Store",
            "type": "ai_embedding",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "AI Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Embeddings OpenAI1": {
      "ai_embedding": [
        [
          {
            "node": "Pinecone Vector Store1",
            "type": "ai_embedding",
            "index": 0
          }
        ]
      ]
    },
    "Embeddings OpenAI2": {
      "ai_embedding": [
        [
          {
            "node": "Pinecone Vector Store2",
            "type": "ai_embedding",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Chat Model1": {
      "ai_languageModel": [
        [
          {
            "node": "Answer questions with a vector store",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Chat Model2": {
      "ai_languageModel": [
        [
          {
            "node": "AI Agent1",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Chat Model3": {
      "ai_languageModel": [
        [
          {
            "node": "Answer questions with a vector store1",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Default Data Loader": {
      "ai_document": [
        [
          {
            "node": "Pinecone Vector Store",
            "type": "ai_document",
            "index": 0
          }
        ]
      ]
    },
    "Pinecone Vector Store1": {
      "ai_vectorStore": [
        [
          {
            "node": "Answer questions with a vector store",
            "type": "ai_vectorStore",
            "index": 0
          }
        ]
      ]
    },
    "Pinecone Vector Store2": {
      "ai_vectorStore": [
        [
          {
            "node": "Answer questions with a vector store1",
            "type": "ai_vectorStore",
            "index": 0
          }
        ]
      ]
    },
    "When chat message received": {
      "main": [
        [
          {
            "node": "AI Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Recursive Character Text Splitter": {
      "ai_textSplitter": [
        [
          {
            "node": "Default Data Loader",
            "type": "ai_textSplitter",
            "index": 0
          }
        ]
      ]
    },
    "Answer questions with a vector store": {
      "ai_tool": [
        [
          {
            "node": "AI Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "When clicking \u2018Execute workflow\u2019": {
      "main": [
        [
          {
            "node": "Google Drive",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Answer questions with a vector store1": {
      "ai_tool": [
        [
          {
            "node": "AI Agent1",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    }
  }
}

Credentials you'll need

Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.

• googleDriveOAuth2Api
• openAiApi
• pineconeApi

About this workflow

This workflow contains community nodes that are only compatible with the self-hosted version of n8n.

Source: https://n8n.io/workflows/5807/ — original creator credit. Request a take-down →

More AI & RAG workflows → · Browse all categories →

Related workflows

Workflows that share integrations, category, or trigger type with this one. All free to copy and import.