基于动态提示etBaserowdeAIdonnéesextraction

Avancé

Ceci est unAIworkflow d'automatisation du domainecontenant 45 nœuds.Utilise principalement des nœuds comme Set, Code, Filter, Switch, Webhook, combinant la technologie d'intelligence artificielle pour une automatisation intelligente. 基于动态提示etBaserowdeAIdonnéesextraction

Prérequis
  • Point de terminaison HTTP Webhook (généré automatiquement par n8n)
  • Peut nécessiter les informations d'identification d'authentification de l'API cible
  • Clé API OpenAI
Aperçu du workflow
Visualisation des connexions entre les nœuds, avec support du zoom et du déplacement
Exporter le workflow
Copiez la configuration JSON suivante dans n8n pour importer et utiliser ce workflow
{
  "nodes": [
    {
      "id": "065d7ec9-edc5-46f6-b8ac-d62ed0e5c8e3",
      "name": "Baserow Event",
      "type": "n8n-nodes-base.webhook",
      "position": [
        -1180,
        -140
      ],
      "webhookId": "267ea500-e2cd-4604-a31f-f0773f27317c",
      "parameters": {
        "path": "267ea500-e2cd-4604-a31f-f0773f27317c",
        "options": {},
        "httpMethod": "POST"
      },
      "typeVersion": 2
    },
    {
      "id": "ac1403b4-9d45-404d-9892-0bed39b9ec82",
      "name": "Event Type",
      "type": "n8n-nodes-base.switch",
      "position": [
        -220,
        -140
      ],
      "parameters": {
        "rules": {
          "values": [
            {
              "outputKey": "rows.updated",
              "conditions": {
                "options": {
                  "version": 2,
                  "leftValue": "",
                  "caseSensitive": true,
                  "typeValidation": "strict"
                },
                "combinator": "and",
                "conditions": [
                  {
                    "id": "2162daf8-d23d-4b8f-8257-bdfc5400a3a8",
                    "operator": {
                      "name": "filter.operator.equals",
                      "type": "string",
                      "operation": "equals"
                    },
                    "leftValue": "={{ $json.event_type }}",
                    "rightValue": "rows.updated"
                  }
                ]
              },
              "renameOutput": true
            },
            {
              "outputKey": "field.created",
              "conditions": {
                "options": {
                  "version": 2,
                  "leftValue": "",
                  "caseSensitive": true,
                  "typeValidation": "strict"
                },
                "combinator": "and",
                "conditions": [
                  {
                    "id": "48e112f6-afe8-40bf-b673-b37446934a62",
                    "operator": {
                      "name": "filter.operator.equals",
                      "type": "string",
                      "operation": "equals"
                    },
                    "leftValue": "={{ $json.event_type }}",
                    "rightValue": "field.created"
                  }
                ]
              },
              "renameOutput": true
            },
            {
              "outputKey": "field.updated",
              "conditions": {
                "options": {
                  "version": 2,
                  "leftValue": "",
                  "caseSensitive": true,
                  "typeValidation": "strict"
                },
                "combinator": "and",
                "conditions": [
                  {
                    "id": "5aa258cd-15c2-4156-a32d-afeed662a38e",
                    "operator": {
                      "name": "filter.operator.equals",
                      "type": "string",
                      "operation": "equals"
                    },
                    "leftValue": "={{ $json.event_type }}",
                    "rightValue": "field.updated"
                  }
                ]
              },
              "renameOutput": true
            }
          ]
        },
        "options": {}
      },
      "typeVersion": 3.2
    },
    {
      "id": "c501042d-f9e7-4c1a-b01d-b11392b1a804",
      "name": "Table Fields API",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        -900,
        -140
      ],
      "parameters": {
        "url": "=https://api.baserow.io/api/database/fields/table/{{ $json.body.table_id }}/",
        "options": {},
        "sendQuery": true,
        "authentication": "genericCredentialType",
        "genericAuthType": "httpHeaderAuth",
        "queryParameters": {
          "parameters": [
            {
              "name": "user_field_names",
              "value": "true"
            }
          ]
        }
      },
      "credentials": {
        "httpHeaderAuth": {
          "id": "F28aPWK5NooSHAg0",
          "name": "Baserow (n8n-local)"
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "af6c3b7f-bb8b-4037-8e3b-337d81ca5632",
      "name": "Get Prompt Fields",
      "type": "n8n-nodes-base.code",
      "position": [
        -720,
        -140
      ],
      "parameters": {
        "jsCode": "const fields = $input.all()\n    .filter(item => item.json.description)\n    .map(item => ({\n      id: item.json.id,\n      order: item.json.order,\n      name: item.json.name,\n      description: item.json.description,\n    }));\n\nreturn { json: { fields } };"
      },
      "typeVersion": 2
    },
    {
      "id": "e1f8f740-c784-4f07-9265-76db518f3ebc",
      "name": "Get Event Body",
      "type": "n8n-nodes-base.set",
      "position": [
        -380,
        -140
      ],
      "parameters": {
        "mode": "raw",
        "options": {},
        "jsonOutput": "={{ $('Baserow Event').first().json.body }}"
      },
      "typeVersion": 3.4
    },
    {
      "id": "e303b7c3-639a-4136-8aa4-074eedeb273f",
      "name": "List Table API",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        480,
        220
      ],
      "parameters": {
        "url": "=https://api.baserow.io/api/database/rows/table/{{ $json.table_id }}/",
        "options": {
          "pagination": {
            "pagination": {
              "nextURL": "={{ $response.body.next || `https://api.baserow.io/api/database/rows/table/${$json.table_id}/?user_field_names=true&size=20&page=9999` }}",
              "maxRequests": 3,
              "paginationMode": "responseContainsNextURL",
              "requestInterval": 1000,
              "limitPagesFetched": true,
              "completeExpression": "={{ $response.body.isEmpty() || $response.statusCode >= 400 }}",
              "paginationCompleteWhen": "other"
            }
          }
        },
        "sendQuery": true,
        "authentication": "genericCredentialType",
        "genericAuthType": "httpHeaderAuth",
        "queryParameters": {
          "parameters": [
            {
              "name": "user_field_names",
              "value": "true"
            },
            {
              "name": "size",
              "value": "20"
            },
            {
              "name": "include",
              "value": "id,order,_id,name,created_at,last_modified_at"
            },
            {
              "name": "filters",
              "value": "{\"filter_type\":\"AND\",\"filters\":[{\"type\":\"not_empty\",\"field\":\"File\",\"value\":\"\"}],\"groups\":[]}"
            }
          ]
        }
      },
      "credentials": {
        "httpHeaderAuth": {
          "id": "F28aPWK5NooSHAg0",
          "name": "Baserow (n8n-local)"
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "9ad2e0c8-c92d-460d-be7a-237ce29b34c2",
      "name": "Get Valid Rows",
      "type": "n8n-nodes-base.code",
      "position": [
        640,
        220
      ],
      "parameters": {
        "jsCode": "return $input.all()\n  .filter(item => item.json.results?.length)\n  .flatMap(item => item.json.results);"
      },
      "typeVersion": 2
    },
    {
      "id": "72b137e9-2e87-4580-9282-0ab7c5147f68",
      "name": "Get File Data",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        1320,
        320
      ],
      "parameters": {
        "url": "={{ $json.File[0].url }}",
        "options": {}
      },
      "typeVersion": 4.2
    },
    {
      "id": "d479ee4e-4a87-4a0e-b9ca-4aa54afdc67a",
      "name": "Extract from File",
      "type": "n8n-nodes-base.extractFromFile",
      "position": [
        1480,
        320
      ],
      "parameters": {
        "options": {},
        "operation": "pdf"
      },
      "typeVersion": 1
    },
    {
      "id": "717e36f8-7dd7-44a6-bcef-9f20735853d2",
      "name": "Update Row",
      "type": "n8n-nodes-base.httpRequest",
      "notes": "Execute Once",
      "onError": "continueRegularOutput",
      "maxTries": 2,
      "position": [
        2280,
        380
      ],
      "parameters": {
        "url": "=https://api.baserow.io/api/database/rows/table/{{ $('Event Ref').first().json.table_id }}/{{ $('Row Reference').item.json.id }}/",
        "method": "PATCH",
        "options": {},
        "jsonBody": "={{\n{\n  ...$input.all()\n    .reduce((acc, item) => ({\n      ...acc,\n      [item.json.field]: item.json.value\n    }), {})\n}\n}}",
        "sendBody": true,
        "sendQuery": true,
        "specifyBody": "json",
        "authentication": "genericCredentialType",
        "genericAuthType": "httpHeaderAuth",
        "queryParameters": {
          "parameters": [
            {
              "name": "user_field_names",
              "value": "true"
            }
          ]
        }
      },
      "credentials": {
        "httpHeaderAuth": {
          "id": "F28aPWK5NooSHAg0",
          "name": "Baserow (n8n-local)"
        }
      },
      "executeOnce": true,
      "notesInFlow": true,
      "retryOnFail": false,
      "typeVersion": 4.2,
      "waitBetweenTries": 3000
    },
    {
      "id": "b807a9c0-2334-491c-a259-1e0e266f89df",
      "name": "Get Result",
      "type": "n8n-nodes-base.set",
      "position": [
        2100,
        380
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "3ad72567-1d17-4910-b916-4c34a43b1060",
              "name": "field",
              "type": "string",
              "value": "={{ $('Event Ref').first().json.field.name }}"
            },
            {
              "id": "e376ba60-8692-4962-9af7-466b6a3f44a2",
              "name": "value",
              "type": "string",
              "value": "={{ $json.text.trim() }}"
            }
          ]
        }
      },
      "typeVersion": 3.4
    },
    {
      "id": "d29a58db-f547-4a4b-bc20-10e14529e474",
      "name": "Boucler sur les éléments",
      "type": "n8n-nodes-base.splitInBatches",
      "position": [
        900,
        220
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 3
    },
    {
      "id": "233b2e96-7873-42f0-989f-c3df5a8e4542",
      "name": "Row Reference",
      "type": "n8n-nodes-base.noOp",
      "position": [
        1080,
        320
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "396eb9c0-dcde-4735-9e15-bf6350def086",
      "name": "Generate Field Value",
      "type": "@n8n/n8n-nodes-langchain.chainLlm",
      "position": [
        1640,
        320
      ],
      "parameters": {
        "text": "=<file>\n{{ $json.text }}\n</file>\n\nData to extract: {{ $('Event Ref').first().json.field.description }}\noutput format is: {{ $('Event Ref').first().json.field.type }}",
        "messages": {
          "messageValues": [
            {
              "message": "=You assist the user in extracting the required data from the given file.\n* Keep you answer short.\n* If you cannot extract the requested data, give you response as \"n/a\"."
            }
          ]
        },
        "promptType": "define"
      },
      "typeVersion": 1.5
    },
    {
      "id": "4be0a9e5-e77e-4cea-9dd3-bc6e7de7a72b",
      "name": "Get Row",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        640,
        -420
      ],
      "parameters": {
        "url": "=https://api.baserow.io/api/database/rows/table/{{ $('Event Ref1').first().json.table_id }}/{{ $json.id }}/",
        "options": {},
        "sendQuery": true,
        "authentication": "genericCredentialType",
        "genericAuthType": "httpHeaderAuth",
        "queryParameters": {
          "parameters": [
            {
              "name": "user_field_names",
              "value": "true"
            }
          ]
        }
      },
      "credentials": {
        "httpHeaderAuth": {
          "id": "F28aPWK5NooSHAg0",
          "name": "Baserow (n8n-local)"
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "40fc77b8-a986-40ab-a78c-da05a3f171c2",
      "name": "Rows to List",
      "type": "n8n-nodes-base.splitOut",
      "position": [
        320,
        -420
      ],
      "parameters": {
        "options": {},
        "fieldToSplitOut": "items"
      },
      "typeVersion": 1
    },
    {
      "id": "4c5bc9c8-1bcb-48b1-82d0-5cf04535108c",
      "name": "Fields to Update",
      "type": "n8n-nodes-base.code",
      "position": [
        1640,
        -300
      ],
      "parameters": {
        "jsCode": "const row = $('Row Ref').first().json;\nconst fields = $('Get Prompt Fields').first().json.fields;\nconst missingFields = fields\n  .filter(field => field.description && !row[field.name]);\n\nreturn missingFields;"
      },
      "typeVersion": 2
    },
    {
      "id": "85d5c817-e5f8-45ea-bf7f-efc7913f542c",
      "name": "Boucler sur les éléments1",
      "type": "n8n-nodes-base.splitInBatches",
      "position": [
        900,
        -420
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 3
    },
    {
      "id": "69005b35-9c66-4c14-80a9-ef8e945dab30",
      "name": "Row Ref",
      "type": "n8n-nodes-base.noOp",
      "position": [
        1080,
        -300
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "1b0e14da-13a8-4023-9006-464578bf0ff5",
      "name": "Get File Data1",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        1320,
        -300
      ],
      "parameters": {
        "url": "={{ $('Row Ref').item.json.File[0].url }}",
        "options": {}
      },
      "typeVersion": 4.2
    },
    {
      "id": "47cf67bc-a3e2-4796-b5a7-4f6a6aef3e90",
      "name": "Extract from File1",
      "type": "n8n-nodes-base.extractFromFile",
      "position": [
        1480,
        -300
      ],
      "parameters": {
        "options": {},
        "operation": "pdf"
      },
      "typeVersion": 1
    },
    {
      "id": "3dc743cc-0dde-4349-975c-fa453d99dbaf",
      "name": "Update Row1",
      "type": "n8n-nodes-base.httpRequest",
      "notes": "Execute Once",
      "onError": "continueRegularOutput",
      "maxTries": 2,
      "position": [
        2440,
        -260
      ],
      "parameters": {
        "url": "=https://api.baserow.io/api/database/rows/table/{{ $('Event Ref1').first().json.table_id }}/{{ $('Row Ref').first().json.id }}/",
        "method": "PATCH",
        "options": {},
        "jsonBody": "={{\n{\n  ...$input.all()\n    .reduce((acc, item) => ({\n      ...acc,\n      [item.json.field]: item.json.value\n    }), {})\n}\n}}",
        "sendBody": true,
        "sendQuery": true,
        "specifyBody": "json",
        "authentication": "genericCredentialType",
        "genericAuthType": "httpHeaderAuth",
        "queryParameters": {
          "parameters": [
            {
              "name": "user_field_names",
              "value": "true"
            }
          ]
        }
      },
      "credentials": {
        "httpHeaderAuth": {
          "id": "F28aPWK5NooSHAg0",
          "name": "Baserow (n8n-local)"
        }
      },
      "executeOnce": true,
      "notesInFlow": true,
      "retryOnFail": false,
      "typeVersion": 4.2,
      "waitBetweenTries": 3000
    },
    {
      "id": "49c53281-d323-4794-919a-d807d7ccc25e",
      "name": "Get Result1",
      "type": "n8n-nodes-base.set",
      "position": [
        2260,
        -260
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "3ad72567-1d17-4910-b916-4c34a43b1060",
              "name": "field",
              "type": "string",
              "value": "={{ $('Fields to Update').item.json.name }}"
            },
            {
              "id": "e376ba60-8692-4962-9af7-466b6a3f44a2",
              "name": "value",
              "type": "string",
              "value": "={{ $json.text.trim() }}"
            }
          ]
        }
      },
      "typeVersion": 3.4
    },
    {
      "id": "bc23708a-b177-47db-8a30-4330198710e0",
      "name": "Generate Field Value1",
      "type": "@n8n/n8n-nodes-langchain.chainLlm",
      "position": [
        1800,
        -300
      ],
      "parameters": {
        "text": "=<file>\n{{ $('Extract from File1').first().json.text }}\n</file>\n\nData to extract: {{ $json.description }}\noutput format is: {{ $json.type }}",
        "messages": {
          "messageValues": [
            {
              "message": "=You assist the user in extracting the required data from the given file.\n* Keep you answer short.\n* If you cannot extract the requested data, give you response as \"n/a\" followed by \"(reason)\" where reason is replaced with reason why data could not be extracted."
            }
          ]
        },
        "promptType": "define"
      },
      "typeVersion": 1.5
    },
    {
      "id": "c0297c19-04b8-4d56-9ce0-320b399f73bd",
      "name": "Filtrer Valid Rows",
      "type": "n8n-nodes-base.filter",
      "position": [
        480,
        -420
      ],
      "parameters": {
        "options": {},
        "conditions": {
          "options": {
            "version": 2,
            "leftValue": "",
            "caseSensitive": true,
            "typeValidation": "strict"
          },
          "combinator": "and",
          "conditions": [
            {
              "id": "7ad58f0b-0354-49a9-ab2f-557652d7b416",
              "operator": {
                "type": "string",
                "operation": "notEmpty",
                "singleValue": true
              },
              "leftValue": "={{ $json.File[0].url }}",
              "rightValue": ""
            }
          ]
        }
      },
      "typeVersion": 2.2
    },
    {
      "id": "5aab6971-1d6f-4b82-a218-4e25c7b28052",
      "name": "Filtrer Valid Fields",
      "type": "n8n-nodes-base.filter",
      "position": [
        320,
        220
      ],
      "parameters": {
        "options": {},
        "conditions": {
          "options": {
            "version": 2,
            "leftValue": "",
            "caseSensitive": true,
            "typeValidation": "strict"
          },
          "combinator": "and",
          "conditions": [
            {
              "id": "5b4a7393-788c-42dc-ac1f-e76f833f8534",
              "operator": {
                "type": "string",
                "operation": "notEmpty",
                "singleValue": true
              },
              "leftValue": "={{ $json.field.description }}",
              "rightValue": ""
            }
          ]
        }
      },
      "typeVersion": 2.2
    },
    {
      "id": "bc144115-f3a2-4e99-a35c-4a780754d0fb",
      "name": "Event Ref",
      "type": "n8n-nodes-base.noOp",
      "position": [
        160,
        220
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "13fd10c0-d4eb-463a-a8b6-5471380f3710",
      "name": "Event Ref1",
      "type": "n8n-nodes-base.noOp",
      "position": [
        160,
        -420
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "e07053a4-a130-41b0-85d3-dfa3983b1547",
      "name": "Note adhésive",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1000,
        -340
      ],
      "parameters": {
        "color": 7,
        "width": 480,
        "height": 440,
        "content": "### 1. Get Table Schema\n[Learn more about the HTTP node](https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-base.httprequest)\n\nFor this operation, we'll have to use the Baserow API rather than the built-in node. However, this way does allow for more flexibility with query parameters.\n"
      },
      "typeVersion": 1
    },
    {
      "id": "675b9d6a-1ba6-49ce-b569-38cc0ba04dcb",
      "name": "Note adhésive1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -260,
        -440
      ],
      "parameters": {
        "color": 5,
        "width": 330,
        "height": 80,
        "content": "### 2a. Updates Minimal Number of Rows\nThis branch updates only the rows impacted."
      },
      "typeVersion": 1
    },
    {
      "id": "021d51f9-7a5b-4f93-baad-707144aeb7ba",
      "name": "Note adhésive2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -320,
        140
      ],
      "parameters": {
        "color": 5,
        "width": 390,
        "height": 120,
        "content": "### 2b. Update Every Row under the Field\nThis branch updates all applicable rows under field when the field/column is created or changed. Watch out - if you have 1000s of rows, this could take a while!"
      },
      "typeVersion": 1
    },
    {
      "id": "ae49cfb0-ac83-4501-bc01-d98be32798f0",
      "name": "Note adhésive3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1780,
        -1060
      ],
      "parameters": {
        "width": 520,
        "height": 1160,
        "content": "## Try It Out!\n### This n8n template powers a \"dynamic\" or \"user-defined\" prompts with PDF workflow pattern for a [Baserow](https://baserow.io) table. Simply put, it allows users to populate a spreadsheet using prompts without touching the underlying template.\n\n**Check out the video demo I did for n8n Studio**: https://www.youtube.com/watch?v=_fNAD1u8BZw\n\nThis template is intended to be used as a webhook source for Baserow. **Looking for a Airtable version? [Click here](https://n8n.io/workflows/2771-ai-data-extraction-with-dynamic-prompts-and-airtable/)**\n\n## How it works\n* Each Baserow.io tables offers integration feature whereby changes to the table can be sent as events to any accessible webhook. This allows for a reactive trigger pattern which makes this type of workflow possible. For our usecase, we capture the vents of `row_updated`, `field_created` and `field_updated`.\n* Next, we'll need an \"input\" column in our Baserow.io table. This column will be where our context lives for evaluating the prompts against. In this example, our \"input\" column name is \"file\" and it's where we'll upload our PDFs. Note, this \"input\" field is human-controlled and never updated from this template.\n* Now for the columns (aka \"fields\" in Baserow). Each field allows us to define a name, type and description and together form the schema. The first 2 are self-explaintory but the \"description\" will be for users to provide their prompts ie. what data should the field to contain.\n* In this template, a webhook trigger waits for when a row or column is updated. The incoming event comes with lots of details such as the table, row and/or column Ids that were impacted.\n* We use this information to fetch the table's schema in order to get the column's descriptions (aka dynamic prompts).\n* For each triggered event, we download our input ie. the PDF and ready it for our AI/LLM. By iterating through the available columns and feeding the dynamic prompts, our LLM can run those prompts against the PDF and thus generating a value response for each cell.\n* These values are then collected and used to update the Baserow Table.\n\n## How to use\n* You'll need to publish this workflow and make it accessible to our Baserow instance. Good to note, you only really need to do this once and can reuse for many Baserow Tables.\n* Configure your Baserow Table to send `row_updated`, `field_created` and `field_updated` events to this n8n workflow.\n* This workflow should work with both cloud-hosted and self-hosted versions of Baserow.\n\n\n### Need Help?\nJoin the [Discord](https://discord.com/invite/XPKeKXeB7d) or ask in the [Forum](https://community.n8n.io/)!\n\nHappy Flowgramming!"
      },
      "typeVersion": 1
    },
    {
      "id": "23ea63f5-e1ad-4326-95a4-945bf98d03f4",
      "name": "Note adhésive4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -500,
        -340
      ],
      "parameters": {
        "color": 7,
        "width": 580,
        "height": 440,
        "content": "### 2. Event Router Pattern\n[Learn more about the Switch node](https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-base.switch/)\n\nA simple switch node can be used to determine which event to handle. The difference between our row and field events is that row event affect a single row whereas field events affect all rows. \n"
      },
      "typeVersion": 1
    },
    {
      "id": "179f9459-43d0-4342-ab94-e248730182a5",
      "name": "Note adhésive5",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        100,
        -620
      ],
      "parameters": {
        "color": 7,
        "width": 700,
        "height": 400,
        "content": "### 3. Filter Only Rows with Valid Input\n[Learn more about the Split Out node](https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-base.splitout/)\n\nThis step handles one or more updated rows where \"updated\" means the \"input\" column (ie. \"file\" in our example) for these rows were changed. For each affected row, we'll get the full row to figure out only the columns we need to update - this is an optimisation to avoid redundant work ie. generating values for columns which already have a value."
      },
      "typeVersion": 1
    },
    {
      "id": "7124a8c0-549e-4b82-8e1f-c6428d2bfb44",
      "name": "Note adhésive7",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        2140,
        -480
      ],
      "parameters": {
        "color": 7,
        "width": 520,
        "height": 440,
        "content": "### 6. Update the Baserow Table Row\n[Learn more about the Edit Fields node](https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-base.set/)\n\nFinally, we can collect the LLM responses and combine them to build an API request to update our Baserow Table row - the Id of which we got from initial webhook. After this is done, we can move onto the next row and repeat the process.\n"
      },
      "typeVersion": 1
    },
    {
      "id": "c55ce945-10ba-440b-a444-81cb4ed63539",
      "name": "Note adhésive8",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1260,
        -580
      ],
      "parameters": {
        "color": 7,
        "width": 860,
        "height": 580,
        "content": "### 5. PDFs, LLMs and Dynamic Prompts? Oh My!\n[Learn more about the Basic LLM node](https://docs.n8n.io/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.chainllm/)\n\nThis step is where it all comes together! In short, we give our LLM the PDF contents as the context and loop through our dynamic prompts (from the schema we pulled earlier) for our row. At the end, our LLM should have produced a value for each column requested.\n\n**Note**: There's definitely a optimisation which could be done for caching PDFs but it beyond the scope of this demonstration.\n"
      },
      "typeVersion": 1
    },
    {
      "id": "1a0ff82e-64aa-479e-8dec-c29b512b0686",
      "name": "Note adhésive9",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        820,
        -580
      ],
      "parameters": {
        "color": 7,
        "width": 420,
        "height": 460,
        "content": "### 4. Using an Items Loop\n[Learn more about the Split in Batches node](https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-base.splitinbatches/)\n\nA split in batches node is used here to update a row at a time however, this is a preference for user experience - changes are seen in the Baserow quicker.\n"
      },
      "typeVersion": 1
    },
    {
      "id": "f4562d44-4fc0-4c59-ba90-8b65f1162aac",
      "name": "Note adhésive10",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        100,
        40
      ],
      "parameters": {
        "color": 7,
        "width": 680,
        "height": 360,
        "content": "### 7. Listing All Rows Under The Column\n[Learn more about the Code node](https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-base.code)\n\nWe can use Baserow's List API and the HTTP node's pagination feature to fetch all applicable rows under the affected field - the filter query on the API is helpful here.\n"
      },
      "typeVersion": 1
    },
    {
      "id": "979983e9-1002-444c-a018-50ce525ef02a",
      "name": "Note adhésive11",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1260,
        140
      ],
      "parameters": {
        "color": 7,
        "width": 700,
        "height": 500,
        "content": "### 9. Generating Value using LLM\n[Learn more about the Extract From File node](https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-base.extractfromfile/)\n\nPretty much identical to Step 5 but instead of updating every field/column, we only need to generate a value for one. \n"
      },
      "typeVersion": 1
    },
    {
      "id": "f38aa7a3-479b-4876-87bf-769ada3089f2",
      "name": "Modèle de chat OpenAI",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        1800,
        -140
      ],
      "parameters": {
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "id": "8gccIjcuf3gvaoEr",
          "name": "OpenAi account"
        }
      },
      "typeVersion": 1.1
    },
    {
      "id": "a5061210-2e6b-4b62-994f-594fc10a0ac6",
      "name": "Note adhésive12",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        820,
        40
      ],
      "parameters": {
        "color": 7,
        "width": 420,
        "height": 460,
        "content": "### 8. Using an Items Loop\n[Learn more about the Split in Batches node](https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-base.splitinbatches/)\n\nSimilar to Step 4, the Split in Batches node is a preference for user experience - changes are seen in the Baserow quicker.\n"
      },
      "typeVersion": 1
    },
    {
      "id": "e47e36d4-bf6d-48d3-9e52-d8bbac06c4b4",
      "name": "Modèle de chat OpenAI1",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        1640,
        500
      ],
      "parameters": {
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "id": "8gccIjcuf3gvaoEr",
          "name": "OpenAi account"
        }
      },
      "typeVersion": 1.1
    },
    {
      "id": "52501eab-861e-4de9-837d-65879cd43e5b",
      "name": "Note adhésive13",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1980,
        200
      ],
      "parameters": {
        "color": 7,
        "width": 500,
        "height": 380,
        "content": "### 10. Update the Baserow Table Row\n[Learn more about the Edit Fields node](https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-base.set/)\n\nAs with Step 6, the LLM response is used to update the row however only under the field that was created/changed. Once complete, the loop continues and the next row is processed.\n"
      },
      "typeVersion": 1
    },
    {
      "id": "6d9fb2e9-6aca-4276-b9b3-d409be24e40e",
      "name": "Note adhésive6",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1780,
        -1200
      ],
      "parameters": {
        "color": 7,
        "height": 120,
        "content": "![baserow.io](https://res.cloudinary.com/daglih2g8/image/upload/f_auto,q_auto/v1/n8n-workflows/baserow_logo)"
      },
      "typeVersion": 1
    },
    {
      "id": "bccfc32b-fd18-4de7-88d5-0aeb02ab7954",
      "name": "Note adhésive14",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1200,
        -1280
      ],
      "parameters": {
        "color": 5,
        "width": 820,
        "height": 800,
        "content": "## ⭐️ Creating Baserow Webhooks\nBaserow webhooks are created via the UI and the option can be accessed by clicking on the 3 dots button in the toolbar.\n\n* Create a POST webhook for your n8n webhook URL found in this template.\n* Select the \"use fields names instead of IDs\" option.\n* Select \"let me choose individual events\"\n* The events to choose are \"row updated\", \"field created\" and \"field updated\".\n* For the \"row updated\" event, be sure to specify the input field - in this case, \"File\".\n\n![](https://res.cloudinary.com/daglih2g8/image/upload/f_auto,q_auto/v1/n8n-workflows/jfhvavdpnf3krloc6iaz)"
      },
      "typeVersion": 1
    }
  ],
  "pinData": {},
  "connections": {
    "4be0a9e5-e77e-4cea-9dd3-bc6e7de7a72b": {
      "main": [
        [
          {
            "node": "Loop Over Items1",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "69005b35-9c66-4c14-80a9-ef8e945dab30": {
      "main": [
        [
          {
            "node": "1b0e14da-13a8-4023-9006-464578bf0ff5",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "bc144115-f3a2-4e99-a35c-4a780754d0fb": {
      "main": [
        [
          {
            "node": "Filter Valid Fields",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "13fd10c0-d4eb-463a-a8b6-5471380f3710": {
      "main": [
        [
          {
            "node": "40fc77b8-a986-40ab-a78c-da05a3f171c2",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "ac1403b4-9d45-404d-9892-0bed39b9ec82": {
      "main": [
        [
          {
            "node": "13fd10c0-d4eb-463a-a8b6-5471380f3710",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "bc144115-f3a2-4e99-a35c-4a780754d0fb",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "bc144115-f3a2-4e99-a35c-4a780754d0fb",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "b807a9c0-2334-491c-a259-1e0e266f89df": {
      "main": [
        [
          {
            "node": "717e36f8-7dd7-44a6-bcef-9f20735853d2",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "717e36f8-7dd7-44a6-bcef-9f20735853d2": {
      "main": [
        [
          {
            "node": "Loop Over Items",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "49c53281-d323-4794-919a-d807d7ccc25e": {
      "main": [
        [
          {
            "node": "3dc743cc-0dde-4349-975c-fa453d99dbaf",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "3dc743cc-0dde-4349-975c-fa453d99dbaf": {
      "main": [
        [
          {
            "node": "Loop Over Items1",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "40fc77b8-a986-40ab-a78c-da05a3f171c2": {
      "main": [
        [
          {
            "node": "Filter Valid Rows",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "065d7ec9-edc5-46f6-b8ac-d62ed0e5c8e3": {
      "main": [
        [
          {
            "node": "c501042d-f9e7-4c1a-b01d-b11392b1a804",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "72b137e9-2e87-4580-9282-0ab7c5147f68": {
      "main": [
        [
          {
            "node": "d479ee4e-4a87-4a0e-b9ca-4aa54afdc67a",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "233b2e96-7873-42f0-989f-c3df5a8e4542": {
      "main": [
        [
          {
            "node": "72b137e9-2e87-4580-9282-0ab7c5147f68",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "e1f8f740-c784-4f07-9265-76db518f3ebc": {
      "main": [
        [
          {
            "node": "ac1403b4-9d45-404d-9892-0bed39b9ec82",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "1b0e14da-13a8-4023-9006-464578bf0ff5": {
      "main": [
        [
          {
            "node": "47cf67bc-a3e2-4796-b5a7-4f6a6aef3e90",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "9ad2e0c8-c92d-460d-be7a-237ce29b34c2": {
      "main": [
        [
          {
            "node": "Loop Over Items",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "e303b7c3-639a-4136-8aa4-074eedeb273f": {
      "main": [
        [
          {
            "node": "9ad2e0c8-c92d-460d-be7a-237ce29b34c2",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Loop Over Items": {
      "main": [
        [],
        [
          {
            "node": "233b2e96-7873-42f0-989f-c3df5a8e4542",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "4c5bc9c8-1bcb-48b1-82d0-5cf04535108c": {
      "main": [
        [
          {
            "node": "bc23708a-b177-47db-8a30-4330198710e0",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Loop Over Items1": {
      "main": [
        [],
        [
          {
            "node": "69005b35-9c66-4c14-80a9-ef8e945dab30",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "c501042d-f9e7-4c1a-b01d-b11392b1a804": {
      "main": [
        [
          {
            "node": "af6c3b7f-bb8b-4037-8e3b-337d81ca5632",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "d479ee4e-4a87-4a0e-b9ca-4aa54afdc67a": {
      "main": [
        [
          {
            "node": "396eb9c0-dcde-4735-9e15-bf6350def086",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Filter Valid Rows": {
      "main": [
        [
          {
            "node": "4be0a9e5-e77e-4cea-9dd3-bc6e7de7a72b",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "af6c3b7f-bb8b-4037-8e3b-337d81ca5632": {
      "main": [
        [
          {
            "node": "e1f8f740-c784-4f07-9265-76db518f3ebc",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "bc23708a-b177-47db-8a30-4330198710e0",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "47cf67bc-a3e2-4796-b5a7-4f6a6aef3e90": {
      "main": [
        [
          {
            "node": "4c5bc9c8-1bcb-48b1-82d0-5cf04535108c",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Chat Model1": {
      "ai_languageModel": [
        [
          {
            "node": "396eb9c0-dcde-4735-9e15-bf6350def086",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Filter Valid Fields": {
      "main": [
        [
          {
            "node": "e303b7c3-639a-4136-8aa4-074eedeb273f",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "396eb9c0-dcde-4735-9e15-bf6350def086": {
      "main": [
        [
          {
            "node": "b807a9c0-2334-491c-a259-1e0e266f89df",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "bc23708a-b177-47db-8a30-4330198710e0": {
      "main": [
        [
          {
            "node": "49c53281-d323-4794-919a-d807d7ccc25e",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}
Foire aux questions

Comment utiliser ce workflow ?

Copiez le code de configuration JSON ci-dessus, créez un nouveau workflow dans votre instance n8n et sélectionnez "Importer depuis le JSON", collez la configuration et modifiez les paramètres d'authentification selon vos besoins.

Dans quelles scénarios ce workflow est-il adapté ?

Avancé - Intelligence Artificielle

Est-ce payant ?

Ce workflow est entièrement gratuit et peut être utilisé directement. Veuillez noter que les services tiers utilisés dans le workflow (comme l'API OpenAI) peuvent nécessiter un paiement de votre part.

Informations sur le workflow
Niveau de difficulté
Avancé
Nombre de nœuds45
Catégorie1
Types de nœuds13
Description de la difficulté

Adapté aux utilisateurs avancés, avec des workflows complexes contenant 16+ nœuds

Auteur
Jimleuk

Jimleuk

@jimleuk

Freelance consultant based in the UK specialising in AI-powered automations. I work with select clients tackling their most challenging projects. For business enquiries, send me an email at hello@jimle.uk LinkedIn: https://www.linkedin.com/in/jimleuk/ X/Twitter: https://x.com/jimle_uk

Liens externes
Voir sur n8n.io

Partager ce workflow

Catégories

Catégories: 34