Evaluation Metric Example: String Similarity

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 →

{
  "meta": {
    "templateCredsSetupCompleted": true
  },
  "nodes": [
    {
      "id": "b2a1a367-119f-4e2d-a982-ff675debf658",
      "name": "Sticky Note1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        220,
        -40
      ],
      "parameters": {
        "color": 7,
        "width": 180,
        "height": 260,
        "content": "Check how far apart the actual code is from the expected code (a score of 1 is a perfect match)"
      },
      "typeVersion": 1
    },
    {
      "id": "f5413855-20de-4b77-ba90-18610a9d9b4d",
      "name": "Sticky Note3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1300,
        40
      ],
      "parameters": {
        "width": 300,
        "height": 500,
        "content": "## How it works\nThis template shows how to calculate a workflow evaluation metric: **text similarity, measured character-by-character**.\n\nThe workflow takes images of hand-written codes, extracts the code and compares it with the expected answer from the dataset.\n\nThe images look like this:\n![image](https://storage.googleapis.com/n8n_template_data/handwriting_scans/doc20250302_08223946_001.jpg)\n\nYou can find more information on workflow evaluation [here](https://docs.n8n.io/advanced-ai/evaluations/overview), and other metric examples [here](https://docs.n8n.io/advanced-ai/evaluations/metric-based-evaluations/#2-calculate-metrics)."
      },
      "typeVersion": 1
    },
    {
      "id": "8921a4c4-cee1-44e7-8dce-55219db519d7",
      "name": "Sticky Note4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -960,
        280
      ],
      "parameters": {
        "color": 7,
        "width": 220,
        "height": 220,
        "content": "Read in [this test dataset](https://docs.google.com/spreadsheets/d/1uuPS5cHtSNZ6HNLOi75A2m8nVWZrdBZ_Ivf58osDAS8/edit?gid=1786963566#gid=1786963566) of images"
      },
      "typeVersion": 1
    },
    {
      "id": "fbf8337b-eb46-443a-8507-58a14b817be0",
      "name": "Match webhook format",
      "type": "n8n-nodes-base.set",
      "position": [
        -680,
        340
      ],
      "parameters": {
        "mode": "raw",
        "options": {},
        "jsonOutput": "=  {\n    \"headers\": {\n    },\n    \"params\": {},\n    \"query\": {\n      \"url\": {{ $json.file_url.toJsonString() }}\n    },\n    \"body\": {},\n    \"executionMode\": \"test\"\n  }"
      },
      "typeVersion": 3.4
    },
    {
      "id": "a03c9b79-d45d-4842-9325-df1af37697eb",
      "name": "Webhook",
      "type": "n8n-nodes-base.webhook",
      "position": [
        -900,
        40
      ],
      "parameters": {
        "path": "7ceb775c-b961-44f0-acfe-682a67612332",
        "options": {}
      },
      "typeVersion": 2
    },
    {
      "id": "85bd63e2-3039-4f0e-8721-bc2b843461c9",
      "name": "When fetching a dataset row",
      "type": "n8n-nodes-base.evaluationTrigger",
      "position": [
        -900,
        340
      ],
      "parameters": {
        "sheetName": {
          "__rl": true,
          "mode": "url",
          "value": "https://docs.google.com/spreadsheets/d/1uuPS5cHtSNZ6HNLOi75A2m8nVWZrdBZ_Ivf58osDAS8/edit?gid=1786963566#gid=1786963566"
        },
        "documentId": {
          "__rl": true,
          "mode": "url",
          "value": "https://docs.google.com/spreadsheets/d/1uuPS5cHtSNZ6HNLOi75A2m8nVWZrdBZ_Ivf58osDAS8/edit?gid=1786963566#gid=1786963566"
        }
      },
      "credentials": {
        "googleSheetsOAuth2Api": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 4.6
    },
    {
      "id": "4ed0b460-70af-4f1d-a7f3-97293f9b4ce0",
      "name": "Respond to Webhook",
      "type": "n8n-nodes-base.respondToWebhook",
      "position": [
        260,
        320
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 1.3
    },
    {
      "id": "f1642aa1-94c5-4002-a7aa-533566dd20eb",
      "name": "Evaluating?",
      "type": "n8n-nodes-base.evaluation",
      "position": [
        -20,
        200
      ],
      "parameters": {
        "operation": "checkIfEvaluating"
      },
      "typeVersion": 4.6
    },
    {
      "id": "15115588-b9ca-4e24-b7d8-f0aa0974b5dd",
      "name": "Set metrics",
      "type": "n8n-nodes-base.evaluation",
      "position": [
        480,
        80
      ],
      "parameters": {
        "metrics": {
          "assignments": [
            {
              "id": "0e507b06-e6d5-4ace-aa22-f06c6db5b883",
              "name": "score",
              "type": "number",
              "value": "={{ $json.score }}"
            }
          ]
        },
        "operation": "setMetrics"
      },
      "typeVersion": 4.6
    },
    {
      "id": "af028132-c866-487d-be85-e3af049bc793",
      "name": "Extract code from image",
      "type": "@n8n/n8n-nodes-langchain.openAi",
      "position": [
        -240,
        200
      ],
      "parameters": {
        "text": "=Extract ONLY the handwritten code in the top-right corner of this image.\n\nThe code MUST follow this EXACT format:\nBT/ED/[1-3 capital letters]/[1-3 capital letters]/[1-3 capital letters]/[1-3 capital letters or empty]/[single letter + number (2-4 chars total)]\n\nExamples of correct format:\nBT/ED/ABC/DE/F/G/H1\nBT/ED/A/BC/DEF/GH/I23\nBT/ED/AB/CD/EF/GH/I234\n\nDO NOT include any explanations, notes, or other text.\nDO NOT return anything if the code doesn't match the required format.\nVERIFY the extracted code matches the format before returning it.\nReturn ONLY the extracted code - nothing else.",
        "modelId": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4o",
          "cachedResultName": "GPT-4O"
        },
        "options": {},
        "resource": "image",
        "inputType": "base64",
        "operation": "analyze"
      },
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.8
    },
    {
      "id": "50a26635-078f-40a7-8944-2e43ed8cd482",
      "name": "Calc string distance",
      "type": "n8n-nodes-base.code",
      "position": [
        260,
        80
      ],
      "parameters": {
        "mode": "runOnceForEachItem",
        "jsCode": "const expected_code = $('When fetching a dataset row').item.json.expected_output\nconst actual_code = $json.content\n\nfunction levenshteinDistance(str1, str2) {\n  const m = str1.length;\n  const n = str2.length;\n  const dp = Array(m + 1).fill().map(() => Array(n + 1).fill(0));\n\n  for (let i = 0; i <= m; i++) {\n    dp[i][0] = i;\n  }\n  \n  for (let j = 0; j <= n; j++) {\n    dp[0][j] = j;\n  }\n\n  for (let i = 1; i <= m; i++) {\n    for (let j = 1; j <= n; j++) {\n      if (str1[i - 1] === str2[j - 1]) {\n        dp[i][j] = dp[i - 1][j - 1];\n      } else {\n        dp[i][j] = 1 + Math.min(\n          dp[i - 1][j],     // deletion\n          dp[i][j - 1],     // insertion\n          dp[i - 1][j - 1]  // substitution\n        );\n      }\n    }\n  }\n\n  return dp[m][n];\n}\n\nconst dist = levenshteinDistance(\n  expected_code, \n  actual_code\n)\n\nconst max_dist = Math.max(\n  expected_code.length,\n  actual_code.length\n)\n\nconsole.log('truth', expected_code)\nconsole.log('effort', actual_code)\nconsole.log('dist', dist)\nconsole.log('max_dist', max_dist)\n\n$input.item.json.score = 1 - (dist / max_dist)\n\nreturn $input.item;"
      },
      "typeVersion": 2
    },
    {
      "id": "383db4b0-9665-4608-bbf9-3dca88508bff",
      "name": "Download image",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        -460,
        200
      ],
      "parameters": {
        "url": "={{ $json.query.url }}",
        "options": {}
      },
      "typeVersion": 4.2
    }
  ],
  "connections": {
    "Webhook": {
      "main": [
        [
          {
            "node": "Download image",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Evaluating?": {
      "main": [
        [
          {
            "node": "Calc string distance",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Respond to Webhook",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Download image": {
      "main": [
        [
          {
            "node": "Extract code from image",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Calc string distance": {
      "main": [
        [
          {
            "node": "Set metrics",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Match webhook format": {
      "main": [
        [
          {
            "node": "Download image",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract code from image": {
      "main": [
        [
          {
            "node": "Evaluating?",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "When fetching a dataset row": {
      "main": [
        [
          {
            "node": "Match webhook format",
            "type": "main",
            "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.

• googleSheetsOAuth2Api
• openAiApi

About this workflow

This is a template for n8n's evaluation feature.

Source: https://n8n.io/workflows/4274/ — 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.