This workflow follows the Chainllm → Execute Workflow Trigger recipe pattern — see all workflows that pair these two integrations.
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 →
{
"nodes": [
{
"parameters": {
"operation": "text",
"options": {}
},
"id": "71f88351-3536-4555-82ee-49895154c8d5",
"name": "Extract Document Text",
"type": "n8n-nodes-base.extractFromFile",
"typeVersion": 1,
"position": [
-768,
768
],
"alwaysOutputData": true
},
{
"parameters": {
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "loose",
"version": 2
},
"conditions": [
{
"id": "has-schema-condition",
"leftValue": "={{ $('Modify File & Input').first().json.extraction?.field_schemas?.length > 0 }}",
"rightValue": true,
"operator": {
"type": "boolean",
"operation": "equals"
}
}
],
"combinator": "and"
},
"options": {}
},
"id": "a1b2c3d4-has-schema-if",
"name": "Has Schema?",
"type": "n8n-nodes-base.if",
"typeVersion": 2.2,
"position": [
-416,
416
]
},
{
"parameters": {
"promptType": "define",
"text": "={{ $json.text || $json.data || (typeof $json.concatenated_data === 'string' ? $json.concatenated_data : JSON.stringify($json)) }}",
"hasOutputParser": true,
"messages": {
"messageValues": [
{
"message": "=You are a Document Data Extractor. Given extracted text from a document, organize the information into a structured JSON object.\n\n**Output Requirements:**\n- Respond with ONLY the JSON object. No explanations or other text.\n- If no readable content exists, respond with: {}\n\n**Classification (REQUIRED):**\nAlways include these two fields:\n- content_class: \"primary_document\" (text-heavy document needing storage: invoices, receipts, contracts, letters) | \"style_element\" (logos, signatures, banners, decorative images) | \"unclassified\" (doesn't fit either)\n- class_confidence: 0.0 to 1.0 (your confidence in the classification)\n\n{{ (() => { const e = $('Input Validator').first().json.extraction || {}; let ctx = ''; if (e.type) ctx += `Document type: ${e.type}\\n`; if (e.focus_fields?.length) ctx += `Priority fields: ${e.focus_fields.join(', ')}\\n`; if (e.instructions) ctx += `Instructions: ${e.instructions}\\n`; return ctx ? '**Caller Context:**\\n' + ctx + '\\n' : ''; })() }}**Key Naming Rules:**\n1. Use `snake_case` in English\n2. Derive keys from visible labels (e.g., \"Invoice #:\" \u2192 `invoice_number`, \"Date:\" \u2192 `date`)\n3. For unlabeled data, create descriptive `snake_case` keys\n4. Prefix uncertain mappings with `uncertain_`\n5. Omit keys for missing information\u2014never invent data"
}
]
}
},
"id": "b2c3d4e5-text-to-structured",
"name": "Text-to-Structured",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
-336,
640
],
"typeVersion": 1.4
},
{
"parameters": {
"model": "openai/gpt-oss-120b",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatGroq",
"typeVersion": 1,
"position": [
-352,
800
],
"id": "c3d4e5f6-text-language-model",
"name": "Groq Chat Model",
"credentials": {
"groqApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"schemaType": "manual",
"inputSchema": "={{ JSON.stringify($('Modify File & Input').first().json.output_schema) }}"
},
"id": "d4e5f6g7-text-output-schema",
"name": "Text Output Schema",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
-192,
800
],
"typeVersion": 1.2
},
{
"parameters": {
"operation": "pdf",
"options": {}
},
"id": "6bf5eca2-8555-4ea8-b2f1-594af5563299",
"name": "Extract PDF Text",
"type": "n8n-nodes-base.extractFromFile",
"typeVersion": 1,
"position": [
-736,
416
]
},
{
"parameters": {
"aggregate": "aggregateAllItemData",
"options": {}
},
"id": "3bcc35ca-5a3d-4f1a-9669-30a65862f297",
"name": "Aggregate",
"type": "n8n-nodes-base.aggregate",
"typeVersion": 1,
"position": [
-544,
912
]
},
{
"parameters": {
"fieldsToSummarize": {
"values": [
{
"aggregation": "concatenate",
"field": "data"
}
]
},
"options": {}
},
"id": "21bdece4-27c7-4d06-979d-9e0e41c2adc6",
"name": "Summarize",
"type": "n8n-nodes-base.summarize",
"typeVersion": 1,
"position": [
-544,
768
]
},
{
"parameters": {
"rules": {
"values": [
{
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 1
},
"conditions": [
{
"id": "e3a4d243-5c9e-4363-aeda-4afe1afab79e",
"leftValue": "={{ $binary.values()[0].mimeType }}",
"rightValue": "image",
"operator": {
"type": "string",
"operation": "startsWith"
}
}
],
"combinator": "and"
}
},
{
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 1
},
"conditions": [
{
"leftValue": "={{ $binary.values()[0].mimeType }}",
"rightValue": "application/pdf",
"operator": {
"type": "string",
"operation": "contains"
},
"id": "59677ac7-7038-4f77-94a3-69df1b6544a2"
}
],
"combinator": "and"
}
},
{
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 1
},
"conditions": [
{
"id": "d7c8331d-3ac1-43cb-9774-9f18cda2abc4",
"leftValue": "={{ $binary.values()[0].mimeType }}",
"rightValue": "application/json",
"operator": {
"type": "string",
"operation": "equals",
"name": "filter.operator.equals"
}
}
],
"combinator": "and"
}
},
{
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 1
},
"conditions": [
{
"id": "2ae7faa7-a936-4621-a680-60c512163034",
"leftValue": "={{ $binary.values()[0].mimeType }}",
"rightValue": "application/vnd.ms-excel",
"operator": {
"type": "string",
"operation": "equals",
"name": "filter.operator.equals"
}
}
],
"combinator": "and"
}
},
{
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 1
},
"conditions": [
{
"id": "fc193b06-363b-4699-a97d-e5a850138b0e",
"leftValue": "={{ $binary.values()[0].mimeType }}",
"rightValue": "=application/vnd.google-apps.spreadsheet",
"operator": {
"type": "string",
"operation": "equals",
"name": "filter.operator.equals"
}
}
],
"combinator": "and"
}
},
{
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 1
},
"conditions": [
{
"id": "b69f5605-0179-4b02-9a32-e34bb085f82d",
"leftValue": "={{ $binary.values()[0].mimeType }}",
"rightValue": "application/vnd.google-apps.document",
"operator": {
"type": "string",
"operation": "equals",
"name": "filter.operator.equals"
}
}
],
"combinator": "and"
}
},
{
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 1
},
"conditions": [
{
"id": "f30330d4-a83c-4e9e-9a0b-7de8a1767dc2",
"leftValue": "={{ $binary.data.mimeType }}",
"rightValue": "text/csv",
"operator": {
"type": "string",
"operation": "equals",
"name": "filter.operator.equals"
}
}
],
"combinator": "and"
}
},
{
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 1
},
"conditions": [
{
"id": "url-route-condition",
"leftValue": "={{ $binary.data.mimeType }}",
"rightValue": "text/x-url",
"operator": {
"type": "string",
"operation": "equals",
"name": "filter.operator.equals"
}
}
],
"combinator": "and"
}
}
]
},
"options": {
"fallbackOutput": "extra"
}
},
"id": "aa494995-2e49-4f04-a519-e7f56eb34171",
"name": "Switch",
"type": "n8n-nodes-base.switch",
"typeVersion": 3,
"position": [
-992,
400
]
},
{
"parameters": {
"operation": "xlsx",
"options": {}
},
"id": "2d60a23a-1abc-4e7b-8ed8-8da1593cfacf",
"name": "Extract from Excel",
"type": "n8n-nodes-base.extractFromFile",
"typeVersion": 1,
"position": [
-768,
1056
]
},
{
"parameters": {
"options": {}
},
"type": "n8n-nodes-base.extractFromFile",
"typeVersion": 1,
"position": [
-768,
912
],
"id": "13d15b17-7094-43b5-a3a6-c3bfa3ec2fb1",
"name": "Extract from CSV"
},
{
"parameters": {
"inputSource": "jsonExample",
"jsonExample": "{\n \"binary_files\": {\n \"attachment_0\": {\"mimeType\": \"...\", \"data\": \"...\", \"fileName\": \"...\"}\n },\n \"extraction\": {\n \"type\": \"document_analysis\",\n \"focus_fields\": [\"vendor_name\", \"invoice_number\"],\n \"instructions\": \"Extract priority fields with these exact key names\"\n }\n}"
},
"type": "n8n-nodes-base.executeWorkflowTrigger",
"typeVersion": 1.1,
"position": [
-1456,
400
],
"id": "348208e4-d9e9-492d-be7a-f388bf8ab45d",
"name": "When Executed by Another Workflow"
},
{
"parameters": {
"operation": "download",
"fileId": {
"__rl": true,
"value": "https://drive.google.com/file/d/1V4ZuvFi_c1X7jn6fGmRlZ6q_5CYTQ9G7/view?usp=drive_link",
"mode": "url"
},
"options": {}
},
"id": "cb19ad57-5345-4bb1-8ba4-fb56ba5632c4",
"name": "Download File1",
"type": "n8n-nodes-base.googleDrive",
"typeVersion": 3,
"position": [
-1456,
608
],
"executeOnce": true,
"disabled": true
},
{
"parameters": {
"content": "## Any\u2011file to JSON converter\n\n### How it works\n1. Another workflow triggers this sub\u2011workflow and sends binary files and an optional `extraction` object.\n2. The Input Validator defaults `extraction`, then a code node flattens each attachment into its own item.\n3. A Switch node examines the MIME type of each file and routes it:\n - Images \u2192 editImage \u2192 Gemini OCR prompt \u2192 structured JSON.\n - PDFs \u2192 PDF text extractor.\n - JSON files \u2192 direct JSON extraction.\n - CSV/Excel \u2192 text extraction, aggregation, and summarization.\n4. Each branch normalises the extracted text, runs an optional LLM summarizer, and returns a JSON object with `content_class` and `class_confidence`.\n5. Unsupported types are caught by the Unresolved Handler and marked for manual review.\n\n### Setup\n- [ ] Connect a Google Gemini (PaLM) credential for the image\u2011to\u2011text model.\n- [ ] Ensure the calling workflow sends binary files with proper MIME types.\n- [ ] Verify the Output Schema node matches your desired JSON fields.\n- [ ] Test each file type (image, PDF, JSON, CSV, Excel) to confirm routing.\n- [ ] Adjust the Switch rules if you need to support additional MIME types.\n- [ ] Deploy the workflow and reference its ID in the parent workflow.",
"height": 796,
"width": 460
},
"id": "f3f9259a-b29f-4ad5-874a-ff91c74d795d",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
-2112,
368
],
"typeVersion": 1
},
{
"parameters": {
"promptType": "define",
"text": "Extract all data from this document.",
"hasOutputParser": true,
"messages": {
"messageValues": [
{
"message": "=You are a Document Data Extractor. Given a document image, extract all visible information into a structured JSON object.\n\n**Output Requirements:**\n- Respond with ONLY the JSON object. No explanations or other text.\n- If no readable content exists, respond with: {}\n\n**Classification (REQUIRED):**\nAlways include these two fields:\n- content_class: \"primary_document\" (text-heavy document needing storage: invoices, receipts, contracts, letters) | \"style_element\" (logos, signatures, banners, decorative images) | \"unclassified\" (doesn't fit either)\n- class_confidence: 0.0 to 1.0 (your confidence in the classification)\n\n{{ (() => { const e = $('Input Validator').first().json.extraction || {}; let ctx = ''; if (e.type) ctx += `Document type: ${e.type}\\n`; if (e.focus_fields?.length) ctx += `Priority fields: ${e.focus_fields.join(', ')}\\n`; if (e.instructions) ctx += `Instructions: ${e.instructions}\\n`; return ctx ? '**Caller Context:**\\n' + ctx + '\\n' : ''; })() }}**Key Naming Rules:**\n1. Use `snake_case` in English\n2. Derive keys from visible labels (e.g., \"Invoice #:\" \u2192 `invoice_number`, \"Date:\" \u2192 `date`)\n3. For unlabeled data, create descriptive `snake_case` keys\n4. Prefix uncertain mappings with `uncertain_`\n5. Omit keys for missing information\u2014never invent data"
},
{
"type": "HumanMessagePromptTemplate",
"messageType": "imageBinary"
}
]
}
},
"id": "94b72956-776f-4410-8a9c-1b494eed1c67",
"name": "Image-to-text",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
-688,
80
],
"typeVersion": 1.4
},
{
"parameters": {
"borderWidth": 1,
"borderHeight": 1,
"options": {
"fileName": "data"
}
},
"id": "52e8cb62-4f10-46a7-9736-d1f66109b0d2",
"name": "conversion",
"type": "n8n-nodes-base.editImage",
"position": [
-832,
80
],
"typeVersion": 1
},
{
"parameters": {
"jsCode": "const items = $input.all();\nconst extraction = items[0]?.json?.extraction || {};\nconst fieldSchemas = extraction.field_schemas || [];\n\nconst schema = {\n type: 'object',\n properties: {\n content_class: { type: 'string', enum: ['primary_document', 'style_element', 'unclassified'] },\n class_confidence: { type: 'number' }\n },\n required: ['content_class', 'class_confidence'],\n additionalProperties: true\n};\n\nfor (const field of fieldSchemas) {\n const prop = {};\n if (field.type === 'int') prop.type = 'number';\n else if (field.type === 'list') { prop.type = 'array'; prop.items = { type: 'string' }; }\n else if (field.type === 'class' && field.classes) { prop.type = 'string'; prop.enum = field.classes.split(',').map(c => c.trim()); }\n else prop.type = 'string';\n schema.properties[field.name] = prop;\n schema.required.push(field.name);\n}\n\nreturn items.flatMap(item => {\n const url = item.json.url || item.json.source_url || null;\n const isUrl = url && /^https?:\\/\\/.+/.test(url) && !item.binary;\n if (isUrl) {\n return [{ json: { ...item.json, output_schema: schema, _inputType: 'url', _jinaUrl: 'https://r.jina.ai/' + url }, binary: { data: { mimeType: 'text/x-url', data: '', fileName: url } } }];\n }\n return item.binary ? Object.keys(item.binary).map(key => ({ json: { ...item.json, output_schema: schema }, binary: { data: item.binary[key] } })) : [{ json: { ...item.json, output_schema: schema } }];\n});"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
-1136,
400
],
"id": "29d01b4b-ec16-496e-9b9f-d551ae815bff",
"name": "Modify File & Input"
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "input-validator-extraction",
"name": "extraction",
"value": "={{ $json.extraction || {} }}",
"type": "object"
}
]
},
"includeOtherFields": true,
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
-1296,
400
],
"id": "d444e35f-ccad-417d-a758-4649749c7fc9",
"name": "Input Validator",
"notes": "Pin test data here. See Testing sticky note for examples."
},
{
"parameters": {},
"type": "n8n-nodes-base.manualTrigger",
"typeVersion": 1,
"position": [
-1616,
608
],
"id": "51196187-9710-4710-a4d2-938a24171d35",
"name": "Testing n8n sub-workflow",
"disabled": true
},
{
"parameters": {
"content": "\n\n\n\nThis node requires an LLM API which accpets images. Google works nicely, leave this model if possible.",
"height": 96,
"width": 400
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
-832,
288
],
"id": "bab52de7-f2e4-4a6d-92cf-eac15d094a58",
"name": "Sticky Note15"
},
{
"parameters": {
"content": "## Any-file2json converter\n# \u00b7 Image Understanding\nOCR, captioning, object detection, and structured extraction\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n```\n```\n# \u00b7 pdf\n\n\n\n\n\n```\n```\n# \u00b7 json\n\n\n```\n```\n# \u00b7 csv / excel / etc.\n\n\n\n\n\n",
"height": 1384,
"width": 432,
"color": 7
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
-848,
-16
],
"id": "f3ce7b26-f00a-402a-8ae0-9a00c77dfcb8",
"name": "Sticky Note"
},
{
"parameters": {
"content": "**Optional:** LLM confidence scoring via `class_confidence` field. See `docs/observability-through-llm-confidence-estimate.md`",
"height": 80,
"width": 300
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
-336,
336
],
"id": "b0c8696a-178c-4d7c-b0be-0c15b9e81a9d",
"name": "Confidence Note"
},
{
"parameters": {
"operation": "fromJson",
"binaryPropertyName": "=data",
"destinationKey": "data.unpacked",
"options": {}
},
"type": "n8n-nodes-base.extractFromFile",
"typeVersion": 1,
"position": [
-736,
576
],
"id": "95d8a1ac-ede3-4c64-b6c6-cf2534192287",
"name": "Extract from JSON",
"alwaysOutputData": true
},
{
"parameters": {
"schemaType": "manual",
"inputSchema": "={{ JSON.stringify($('Modify File & Input').first().json.output_schema) }}"
},
"id": "eb1fbc57-1ab1-4776-934d-5a7a3124ee0c",
"name": "Output Schema",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
-592,
208
],
"typeVersion": 1.2
},
{
"parameters": {
"modelName": "models/gemini-3-flash-preview",
"options": {}
},
"id": "e23fb0ad-c743-4e0a-9cf4-fba0736730a7",
"name": "image-language-model",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
-752,
208
],
"typeVersion": 1,
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "uh-status",
"name": "status",
"value": "unresolved",
"type": "string"
},
{
"id": "uh-error-code",
"name": "error_code",
"value": "UNSUPPORTED_MIME_TYPE",
"type": "string"
},
{
"id": "uh-mime-type",
"name": "mimeType",
"value": "={{ $binary.data?.mimeType || 'unknown' }}",
"type": "string"
},
{
"id": "uh-file-name",
"name": "fileName",
"value": "={{ $binary.data?.fileName || 'unknown' }}",
"type": "string"
},
{
"id": "uh-file-size",
"name": "fileSize",
"value": "={{ $binary.data?.fileSize || 'unknown' }}",
"type": "string"
},
{
"id": "uh-original-item",
"name": "originalItem",
"value": "={{ $json }}",
"type": "object"
},
{
"id": "uh-resolver-hint",
"name": "resolver_hint",
"value": "Unsupported file type. Route to resolver workflow for AI interpretation or human review.",
"type": "string"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
-992,
784
],
"id": "49859284-724f-4d50-b952-27fbe38e9696",
"name": "Unresolved Handler"
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "d783b0b2-3058-49db-a543-0a405c5d815e",
"name": "data.text",
"value": "={{ typeof $json.text === 'string' ? $json.text : JSON.stringify($json.output || $json) }}",
"type": "string"
},
{
"id": "a1b2c3d4-content-class",
"name": "data.content_class",
"value": "={{ $json.output?.content_class || $json.content_class || 'UNK' }}",
"type": "string"
},
{
"id": "a1b2c3d4-class-confidence",
"name": "data.class_confidence",
"value": "={{ $json.output?.class_confidence ?? $json.class_confidence ?? 'UNK' }}",
"type": "string"
},
{
"id": "return-status",
"name": "status",
"value": "={{ $json.status || 'resolved' }}",
"type": "string"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
-192,
416
],
"id": "1c9206c0-5927-4c4a-a124-72c9726e3668",
"name": "Return node"
},
{
"parameters": {
"url": "={{ $json._jinaUrl }}",
"options": {
"response": {
"response": {
"responseFormat": "text"
}
}
}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
-544,
1152
],
"id": "d3b152ce-fb60-4814-a242-74b10eb6153b",
"name": "Fetch URL (Jina)"
},
{
"parameters": {
"content": "## Testing\n\n\n\n\n\n\n\n\n\n\n\n\nPin data to **Input Validator** node:\n\n**URL Input:**\n```json\n{\"url\": \"https://en.wikipedia.org/wiki/N8n\"}\n```\n\n**Binary Input:**\n```json\n{\n \"binary_files\": {\n \"attachment_0\": {\n \"mimeType\": \"image/jpeg\",\n \"data\": \"base64...\",\n \"fileName\": \"test.jpg\"\n }\n }\n}\n```",
"height": 504,
"width": 460,
"color": 7
},
"id": "676adb44-466e-4f7d-829a-2eb5996ab366",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1632,
560
],
"typeVersion": 1
},
{
"parameters": {
"content": "## Use case",
"height": 188,
"width": 460,
"color": 7
},
"id": "48900309-8646-43ad-9567-c1237f5df371",
"name": "Sticky Note5",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1632,
368
],
"typeVersion": 1
}
],
"connections": {
"Extract Document Text": {
"main": [
[
{
"node": "Has Schema?",
"type": "main",
"index": 0
}
]
]
},
"Extract PDF Text": {
"main": [
[
{
"node": "Has Schema?",
"type": "main",
"index": 0
}
]
]
},
"Aggregate": {
"main": [
[
{
"node": "Summarize",
"type": "main",
"index": 0
}
]
]
},
"Summarize": {
"main": [
[
{
"node": "Has Schema?",
"type": "main",
"index": 0
}
]
]
},
"Switch": {
"main": [
[
{
"node": "conversion",
"type": "main",
"index": 0
}
],
[
{
"node": "Extract PDF Text",
"type": "main",
"index": 0
}
],
[
{
"node": "Extract from JSON",
"type": "main",
"index": 0
}
],
[
{
"node": "Extract from Excel",
"type": "main",
"index": 0
}
],
[
{
"node": "Extract from CSV",
"type": "main",
"index": 0
}
],
[
{
"node": "Extract Document Text",
"type": "main",
"index": 0
}
],
[
{
"node": "Extract from CSV",
"type": "main",
"index": 0
}
],
[
{
"node": "Fetch URL (Jina)",
"type": "main",
"index": 0
}
],
[
{
"node": "Unresolved Handler",
"type": "main",
"index": 0
}
]
]
},
"Extract from Excel": {
"main": [
[
{
"node": "Aggregate",
"type": "main",
"index": 0
}
]
]
},
"Extract from CSV": {
"main": [
[
{
"node": "Aggregate",
"type": "main",
"index": 0
}
]
]
},
"When Executed by Another Workflow": {
"main": [
[
{
"node": "Input Validator",
"type": "main",
"index": 0
}
]
]
},
"Download File1": {
"main": [
[
{
"node": "Input Validator",
"type": "main",
"index": 0
}
]
]
},
"Image-to-text": {
"main": [
[
{
"node": "Return node",
"type": "main",
"index": 0
}
]
]
},
"conversion": {
"main": [
[
{
"node": "Image-to-text",
"type": "main",
"index": 0
}
]
]
},
"Modify File & Input": {
"main": [
[
{
"node": "Switch",
"type": "main",
"index": 0
}
]
]
},
"Input Validator": {
"main": [
[
{
"node": "Modify File & Input",
"type": "main",
"index": 0
}
]
]
},
"Testing n8n sub-workflow": {
"main": [
[
{
"node": "Download File1",
"type": "main",
"index": 0
}
]
]
},
"Extract from JSON": {
"main": [
[
{
"node": "Has Schema?",
"type": "main",
"index": 0
}
]
]
},
"Output Schema": {
"ai_outputParser": [
[
{
"node": "Image-to-text",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"image-language-model": {
"ai_languageModel": [
[
{
"node": "Image-to-text",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Unresolved Handler": {
"main": [
[
{
"node": "Return node",
"type": "main",
"index": 0
}
]
]
},
"Fetch URL (Jina)": {
"main": [
[
{
"node": "Has Schema?",
"type": "main",
"index": 0
}
]
]
},
"Has Schema?": {
"main": [
[
{
"node": "Text-to-Structured",
"type": "main",
"index": 0
}
],
[
{
"node": "Return node",
"type": "main",
"index": 0
}
]
]
},
"Text-to-Structured": {
"main": [
[
{
"node": "Return node",
"type": "main",
"index": 0
}
]
]
},
"Groq Chat Model": {
"ai_languageModel": [
[
{
"node": "Text-to-Structured",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Text Output Schema": {
"ai_outputParser": [
[
{
"node": "Text-to-Structured",
"type": "ai_outputParser",
"index": 0
}
]
]
}
},
"meta": {
"templateCredsSetupCompleted": true
}
}
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.
googlePalmApigroqApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Any-File2Json-Converter. Uses chainLlm, lmChatGroq, outputParserStructured, executeWorkflowTrigger. Event-driven trigger; 30 nodes.
Source: https://github.com/runfish5/micro-services/blob/main/projects/n8n/03_any-file2json-converter/workflows/any-file2json-converter.json — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
The best content automation template in the market is now even better—with “deep research” on time-sensitive topics\! Unlike most n8n content automation templates that are mainly for “demo purposes,”
OpenAI, HTTP Request, XML +11
My workflow 53. Uses formTrigger, httpRequest, lmChatOpenAi, form. Event-driven trigger; 74 nodes.
Form Trigger, HTTP Request, OpenAI Chat +15
ugc-prototipal copy. Uses openAi, chainLlm, outputParserStructured, httpRequest. Event-driven trigger; 28 nodes.
OpenAI, Chain Llm, Output Parser Structured +5
This n8n template demonstrates how to automatically generate authentic User-Generated Content (UGC) style marketing videos for eCommerce products using AI. Simply upload a product image, and the workf
Form Trigger, OpenAI, Chain Llm +5
The Recap AI - eCommerce UGC Video Generator. Uses formTrigger, openAi, chainLlm, outputParserStructured. Event-driven trigger; 24 nodes.
Form Trigger, OpenAI, Chain Llm +5