AI Document Summarizer & Q&a (ollama)

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": "AI Document Summarizer & Q&A (Ollama)",
  "nodes": [
    {
      "parameters": {
        "httpMethod": "POST",
        "path": "summarize",
        "responseMode": "responseNode",
        "options": {}
      },
      "id": "webhook",
      "name": "Upload Document Webhook",
      "type": "n8n-nodes-base.webhook",
      "typeVersion": 2,
      "position": [
        240,
        300
      ]
    },
    {
      "parameters": {
        "jsCode": "// Extract text from uploaded file or body text\nconst input = $input.first().json;\nlet text = '';\n\nif (input.body && input.body.text) {\n  text = input.body.text;\n} else if (input.body && input.body.url) {\n  // Will be fetched in next node\n  return [{ json: { text: '', url: input.body.url, mode: 'url' } }];\n} else {\n  text = JSON.stringify(input.body).substring(0, 10000);\n}\n\n// Chunk long documents\nconst maxChunk = 4000;\nconst chunks = [];\nfor (let i = 0; i < text.length; i += maxChunk) {\n  chunks.push(text.substring(i, i + maxChunk));\n}\n\nreturn [{ json: { text: text.substring(0, 8000), chunks: chunks.length, mode: 'text' } }];"
      },
      "id": "extract",
      "name": "Extract & Prepare Text",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        480,
        300
      ]
    },
    {
      "parameters": {
        "url": "http://localhost:11434/api/generate",
        "sendBody": true,
        "specifyBody": "json",
        "jsonBody": "={{ JSON.stringify({ model: 'llama3:8b', prompt: 'Summarize this document concisely. Provide:\\n1. A one-paragraph executive summary\\n2. Key points (5-7 bullet points)\\n3. Action items (if any)\\n4. Key entities mentioned (people, companies, dates)\\n\\nDocument:\\n' + $json.text.substring(0, 6000), stream: false, options: { temperature: 0.3, num_predict: 1500 } }) }}",
        "options": {
          "timeout": 120000
        }
      },
      "id": "summarize",
      "name": "Summarize Document (Ollama)",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        720,
        300
      ]
    },
    {
      "parameters": {
        "url": "http://localhost:11434/api/generate",
        "sendBody": true,
        "specifyBody": "json",
        "jsonBody": "={{ JSON.stringify({ model: 'llama3:8b', prompt: 'Based on this document, generate 5 insightful questions that a reader might want answered, along with brief answers based on the document content.\\n\\nDocument:\\n' + $('Extract & Prepare Text').first().json.text.substring(0, 6000) + '\\n\\nFormat as:\\nQ1: [question]\\nA1: [answer]\\n...', stream: false, options: { temperature: 0.4, num_predict: 1500 } }) }}",
        "options": {
          "timeout": 120000
        }
      },
      "id": "qa",
      "name": "Generate Q&A (Ollama)",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        720,
        500
      ]
    },
    {
      "parameters": {
        "jsCode": "const summary = JSON.parse($('Summarize Document (Ollama)').first().json.data).response;\nconst qa = JSON.parse($('Generate Q&A (Ollama)').first().json.data).response;\n\nreturn [{\n  json: {\n    summary: summary,\n    questions_and_answers: qa,\n    document_length: $('Extract & Prepare Text').first().json.text.length,\n    chunks_processed: $('Extract & Prepare Text').first().json.chunks,\n    processed_at: new Date().toISOString()\n  }\n}];"
      },
      "id": "combine",
      "name": "Combine Results",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        960,
        400
      ]
    },
    {
      "parameters": {
        "respondWith": "json",
        "responseBody": "={{ JSON.stringify($json) }}"
      },
      "id": "respond",
      "name": "Return Results",
      "type": "n8n-nodes-base.respondToWebhook",
      "typeVersion": 1.1,
      "position": [
        1200,
        400
      ]
    }
  ],
  "connections": {
    "Upload Document Webhook": {
      "main": [
        [
          {
            "node": "Extract & Prepare Text",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract & Prepare Text": {
      "main": [
        [
          {
            "node": "Summarize Document (Ollama)",
            "type": "main",
            "index": 0
          },
          {
            "node": "Generate Q&A (Ollama)",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Summarize Document (Ollama)": {
      "main": [
        [
          {
            "node": "Combine Results",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Generate Q&A (Ollama)": {
      "main": [
        [
          {
            "node": "Combine Results",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Combine Results": {
      "main": [
        [
          {
            "node": "Return Results",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "settings": {
    "executionOrder": "v1"
  },
  "tags": [
    {
      "name": "AI"
    },
    {
      "name": "Ollama"
    },
    {
      "name": "Documents"
    },
    {
      "name": "Summarization"
    }
  ]
}

About this workflow

AI Document Summarizer & Q&A (Ollama). Uses httpRequest. Webhook trigger; 6 nodes.

Source: https://github.com/bonskari/n8n-ollama-workflows/blob/main/workflows/ai-document-summarizer.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.