Video Upload & AI Analysis Workflow

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 →

{
  "name": "video-stages",
  "nodes": [
    {
      "parameters": {
        "method": "POST",
        "url": "https://us-central1-poetic-analog-460707-i9.cloudfunctions.net/process-video-workflow",
        "sendHeaders": true,
        "headerParameters": {
          "parameters": [
            {
              "name": "Content-Type",
              "value": "application/json"
            }
          ]
        },
        "sendBody": true,
        "bodyParameters": {
          "parameters": [
            {
              "name": "video_gcs_uri",
              "value": "={{ $('Upload Video').item.json.URL }}"
            }
          ]
        },
        "options": {}
      },
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        820,
        -210
      ],
      "id": "e9f3b393-bbe4-4c51-815d-90692ef0b40e",
      "name": "HTTP Request"
    },
    {
      "parameters": {
        "conditions": {
          "options": {
            "caseSensitive": true,
            "leftValue": "",
            "typeValidation": "strict",
            "version": 2
          },
          "conditions": [
            {
              "id": "40f10007-6309-46e1-9662-1d9db5bee855",
              "leftValue": "={{ $json.result }}",
              "rightValue": "",
              "operator": {
                "type": "boolean",
                "operation": "true",
                "singleValue": true
              }
            }
          ],
          "combinator": "and"
        },
        "options": {}
      },
      "type": "n8n-nodes-base.if",
      "typeVersion": 2.2,
      "position": [
        600,
        -110
      ],
      "id": "7e246d8b-6d31-4bb9-aae3-ef3532c83a10",
      "name": "If"
    },
    {
      "parameters": {},
      "type": "n8n-nodes-base.noOp",
      "typeVersion": 1,
      "position": [
        820,
        -10
      ],
      "id": "33923bf3-a4de-4538-bb50-743718685c72",
      "name": "No Operation, do nothing"
    },
    {
      "parameters": {
        "content": "**What this code does:**\n\n* It looks at the video input URL provided.\n* It checks if the web address starts with \"gs://.\n* Then, it tells you \"TRUE\" or \"FALSE\" for each URL's validation.",
        "height": 340,
        "width": 300,
        "color": 7
      },
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        280,
        -290
      ],
      "id": "4939f6f9-72aa-4b5d-afff-dacfe6ca2802",
      "name": "Sticky Note",
      "disabled": true
    },
    {
      "parameters": {
        "formTitle": "Provide GSUTIL URL",
        "formDescription": "Provide the GSUTIL URL of the video file stored in Google Cloud Bucket.",
        "formFields": {
          "values": [
            {
              "fieldLabel": "URL",
              "requiredField": true
            }
          ]
        },
        "options": {}
      },
      "type": "n8n-nodes-base.formTrigger",
      "typeVersion": 2.2,
      "position": [
        160,
        -110
      ],
      "id": "1fb764c6-c56d-4478-8f3d-42094d5ea9e6",
      "name": "Upload Video"
    },
    {
      "parameters": {
        "content": "---\n### **Video Process Analysis (Cloud Function)**\n\nThis is a **Google Cloud Function** that automatically analyzes videos. It uses advanced **AI** to break down complex processes into easy-to-understand stages and steps.\n\n* **Cloud Function:** It's an automated program running in Google Cloud. Just give it a video link, and it gets to work.\n* **AI Power (Vertex AI):** It uses **Gemini 2.0 Flash**, a powerful AI model from Google's Vertex AI platform, to \"watch\" and understand the video's content.\n* **Video Input:** You provide the function with a link to your video (typically stored in Google Cloud Storage).\n* **Process Breakdown:** The AI identifies the main **stages** of the activity and lists all the individual **steps** within each stage, then provides this analysis in a structured format.\n\n---",
        "height": 400,
        "width": 520
      },
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        660,
        -620
      ],
      "id": "94f28a5b-12cf-4cda-acee-178deebce190",
      "name": "Sticky Note1"
    },
    {
      "parameters": {
        "jsCode": "const items = $input.all();\nconst cleanedItems = items.map((item) => {\n  let jsonString = item?.json?.data;\n  jsonString = jsonString.replace(/json|\\\\n|```/g, \"\");\n  try {\n    const parsedJson = JSON.parse(jsonString);\n    return { json: parsedJson };\n  } catch (error) {\n    console.log(\"Error parsing JSON string:\", error);\n    return null;\n  }\n});\nreturn cleanedItems.filter((item) => item !== null);\n"
      },
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        1040,
        -210
      ],
      "id": "eb89e1af-c3b8-4c84-b2ee-1f0d55c46436",
      "name": "Structured Output JSON Parser"
    },
    {
      "parameters": {
        "jsCode": "const items = $input.all();\nconst result = items.map((item) => {\n  return { result: item?.json?.URL.startsWith(\"gs://\") };\n});\nreturn result;\n"
      },
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        380,
        -110
      ],
      "id": "6a0f3121-a6d0-4af1-a380-02ea8cee4411",
      "name": "Validate URL"
    },
    {
      "parameters": {
        "promptType": "define",
        "text": "=You are an expert in process visualization and Mermaid.js syntax. Your task is to convert the provided JSON process analysis into a Mermaid.js flowchart.\n\nInstructions:\nAnalyze the JSON: Carefully read the stages and steps within each stage.\nGenerate a Flowchart: Create a Mermaid.js flowchart using graph TD (top-down) for clear sequential flow.\nRepresent Stages as Nodes:\nEach stage should have a short, simple, alphanumeric ID (e.g., S1, S2, S3).\nThe visible label for each node must be enclosed in square brackets and double quotes, allowing for multi-line content (e.g., NodeID[\"Visible Name<br>Key Step 1<br>Key Step 2\"]).\nRepresent Flow with Arrows: Use --> to show the sequential flow from one node to the next.\nInclude Key Steps in Node Descriptions: For clarity, include the stage_name on the first line, followed by the first 1-2 key steps from each stage's steps list on subsequent lines within the node's label. Use <br> for line breaks within the quoted node label.\nStart and End Nodes: Add a clear \"Start\" and \"End\" node to delineate the process boundaries. These should also follow the NodeID[\"Label\"] format (e.g., Start[\"Start\"]).\nOutput Format: Provide only the Mermaid.js code block, enclosed in markdown code fences (```mermaid ... ```). Do not include any additional text or explanations outside of the Mermaid code block.\n\nJSON is : {{$json.stages.map(stage => `${stage.stage_name}:\\n  - ${stage.steps.slice(0, 2).join('\\n  - ')}${stage.steps.length > 2 ? '\\n  ...' : ''}`).join('\\n\\n') }}",
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.agent",
      "typeVersion": 2,
      "position": [
        1340,
        -60
      ],
      "id": "14011a89-dbfb-481b-b341-51ab74de3e95",
      "name": "AI Agent"
    },
    {
      "parameters": {
        "modelName": "models/gemini-1.5-flash",
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
      "typeVersion": 1,
      "position": [
        1340,
        160
      ],
      "id": "4498b48c-92b9-447e-80ef-9af2ae35dc54",
      "name": "Google Gemini Chat Model",
      "credentials": {
        "googlePalmApi": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "jsCode": "const items = $input.all();\nconst cleanedItems = items.map((item) => {\n  let output = item?.json?.output;\n  output = output.replace(/```/g, \"\");\n  output = output.replace(/mermaid/g, \"\");\n  return { ...item.json, output };\n});\nreturn cleanedItems;\n"
      },
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        1720,
        -60
      ],
      "id": "80f60d60-ea60-4766-9a8d-b07912749714",
      "name": "Output Parser"
    },
    {
      "parameters": {
        "operation": "completion",
        "respondWith": "showText",
        "responseText": "={{ $json.output }}"
      },
      "type": "n8n-nodes-base.form",
      "typeVersion": 1,
      "position": [
        1980,
        -60
      ],
      "id": "a9f511cd-1b58-4939-a183-abda6c78cf23",
      "name": "Display Mermaid JS Code"
    },
    {
      "parameters": {
        "content": "## Mermaid code Generation\n\n* For the generated stages from the cloud function, the LLM here converts the data to mermaid JS code.\n* Next it parses the output into a clean code.\n* It then display the Mermaid code on a display page.",
        "height": 540,
        "width": 560,
        "color": 6
      },
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        1300,
        -240
      ],
      "id": "33fa398c-72c6-4b24-b841-01b050a7657d",
      "name": "Sticky Note2"
    },
    {
      "parameters": {
        "jsCode": "const items = $input.all();\n\nconst formattedOutput = items.map(item => {\n    // --- Adjust this line based on your actual input JSON path ---\n    // Example for Scenario A: If your JSON is directly in item.json\n    const fullProcessData = item.json; \n\n    // Example for Scenario B: If your JSON is in item.json.myProcessData\n    // const fullProcessData = item.json.myProcessData; \n\n    // Example if your full JSON is an array (like the one you pasted)\n    // and the main process object is the first element\n    // const fullProcessData = item.json; // Assuming the array is directly in item.json\n    // const processData = fullProcessData[0]; // Then access the first element\n    // Replace 'fullProcessData' with 'processData' in the rest of the code.\n\n\n    if (!fullProcessData || fullProcessData.length === 0) { // Check if fullProcessData is valid\n        return { json: { formattedStagesMarkdown: \"Error: Input data is empty or invalid.\" } };\n    }\n\n    // This line assumes fullProcessData is an array and your main process object is the first element.\n    // If fullProcessData is *already* the main process object, remove '[0]'\n    const processData = Array.isArray(fullProcessData) ? fullProcessData[0] : fullProcessData; \n\n    if (!processData || !Array.isArray(processData.stages)) {\n        return { json: { formattedStagesMarkdown: \"Error: 'stages' array not found in process data or processData is not an object.\" } };\n    }\n\n    let markdownOutput = `# Process: ${processData.process_title || 'Untitled Process'}\\n\\n`;\n    markdownOutput += \"## Stages and Steps Overview\\n\\n\";\n\n    processData.stages.forEach(stage => {\n        markdownOutput += `### ${stage.stage_number}. **${stage.stage_name}**\\n`;\n        if (stage.stage_description) {\n            markdownOutput += `*Description*: ${stage.stage_description}\\n`;\n        }\n        if (Array.isArray(stage.steps) && stage.steps.length > 0) {\n            stage.steps.forEach(step => {\n                markdownOutput += `* ${step}\\n`;\n            });\n        } else {\n            markdownOutput += \"*No steps listed for this stage.*\\n\";\n        }\n        markdownOutput += \"\\n\"; \n    });\n\n    if (processData.completeness_check) {\n        markdownOutput += `---\\n## Completeness Check\\n${processData.completeness_check}\\n`;\n    }\n\n    item.json.formattedStagesMarkdown = markdownOutput;\n\n    return item;\n});\n\nreturn formattedOutput;"
      },
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        1360,
        -560
      ],
      "id": "d4c95ef4-2900-44df-b259-20bd7ee9f9cd",
      "name": "Code"
    },
    {
      "parameters": {
        "assignments": {
          "assignments": [
            {
              "id": "958f91b1-57b7-4aea-8405-879a920bf4cb",
              "name": "formattedStagesMarkdown",
              "value": "={{ $json.formattedStagesMarkdown }}",
              "type": "string"
            }
          ]
        },
        "options": {}
      },
      "type": "n8n-nodes-base.set",
      "typeVersion": 3.4,
      "position": [
        1620,
        -560
      ],
      "id": "324b73bf-ae79-49c5-924f-83fb3701a550",
      "name": "Edit Fields"
    },
    {
      "parameters": {
        "mode": "markdownToHtml",
        "markdown": "={{ $json.formattedStagesMarkdown }}",
        "options": {}
      },
      "type": "n8n-nodes-base.markdown",
      "typeVersion": 1,
      "position": [
        1860,
        -560
      ],
      "id": "72d5fb60-fc1c-4635-b56e-24e261d83dc9",
      "name": "Markdown"
    },
    {
      "parameters": {
        "content": "## Markdown Code Generation\n\n* For the generated stages from the cloud function, the code here converts the json into a markdown code.\n* Then convert the markdown into html to display stages on screen.",
        "height": 300,
        "width": 760,
        "color": 6
      },
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        1260,
        -700
      ],
      "id": "6fa530fc-17f4-4724-8c36-036f641a2ca7",
      "name": "Sticky Note3"
    },
    {
      "parameters": {
        "operation": "completion",
        "respondWith": "showText",
        "responseText": "={{ $json.data }}"
      },
      "type": "n8n-nodes-base.form",
      "typeVersion": 1,
      "position": [
        2100,
        -560
      ],
      "id": "add13c3f-7ea6-4db3-9aee-04253c412f8b",
      "name": "Display Markdown Code"
    }
  ],
  "connections": {
    "If": {
      "main": [
        [
          {
            "node": "HTTP Request",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "No Operation, do nothing",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Upload Video": {
      "main": [
        [
          {
            "node": "Validate URL",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "HTTP Request": {
      "main": [
        [
          {
            "node": "Structured Output JSON Parser",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Validate URL": {
      "main": [
        [
          {
            "node": "If",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Structured Output JSON Parser": {
      "main": [
        [
          {
            "node": "AI Agent",
            "type": "main",
            "index": 0
          },
          {
            "node": "Code",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Google Gemini Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "AI Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "AI Agent": {
      "main": [
        [
          {
            "node": "Output Parser",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Output Parser": {
      "main": [
        [
          {
            "node": "Display Mermaid JS Code",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Display Mermaid JS Code": {
      "main": [
        []
      ]
    },
    "Code": {
      "main": [
        [
          {
            "node": "Edit Fields",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Edit Fields": {
      "main": [
        [
          {
            "node": "Markdown",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Markdown": {
      "main": [
        [
          {
            "node": "Display Markdown Code",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Display Markdown Code": {
      "main": [
        []
      ]
    }
  },
  "active": false,
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "d012ba69-15c4-408f-8b6d-3affe16d0480",
  "meta": {
    "templateCredsSetupCompleted": true
  },
  "id": "vUJCUfGpdbuznn9a",
  "tags": []
}

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.

• googlePalmApi

About this workflow

video-stages. Uses httpRequest, formTrigger, agent, lmChatGoogleGemini. Event-driven trigger; 18 nodes.

Source: https://github.com/Varun2480/Process_Mining/blob/be88ace69f488e96981094dc3b0e65013e0c8cf6/n8n/video_stages.json — 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.