Manipulate PDF with Adobe developer API
Automate complex PDF manipulations by leveraging the power of Adobe Developer APIs directly within n8n, enabling you to process documents with precision and efficiency. This workflow connects n8n to Adobe's powerful PDF services for operations like combining, splitting, or compressing PDFs, and integrates with Dropbox to retrieve and store your documents. It begins with a manual trigger or by loading a test PDF from Dropbox, then authenticates with Adobe's API to obtain a token, uploads the PDF as an asset, processes your desired query (e.g., merge, extract pages), waits for the operation to complete, and finally attempts to download the manipulated result. Businesses can utilize this for automating document workflows, such as preparing reports, archiving invoices, or customizing marketing materials, saving significant manual effort and ensuring consistent document processing. This solution eliminates the need for manual PDF software, reduces human error, and accelerates document-centric operations, freeing up valuable time and resources.
Workflow JSON
{"meta": {"instanceId": "cd478e616d2616186f4f92b70cfe0c2ed95b5b209f749f2b873b38bdc56c47c9"}, "nodes": [{"id": "f4b1bdd8-654d-4643-a004-ff1b2f32b5ae", "name": "When clicking \u2018Test workflow\u2019", "type": "n8n-nodes-base.manualTrigger", "position": [580, 1100], "parameters": {}, "typeVersion": 1}, {"id": "d6b1c410-81c3-486d-bdcb-86a4c6f7bf9e", "name": "Create Asset", "type": "n8n-nodes-base.httpRequest", "position": [1940, 580], "parameters": {"url": "https://pdf-services.adobe.io/assets", "method": "POST", "options": {"redirect": {"redirect": {}}}, "sendBody": true, "sendHeaders": true, "authentication": "genericCredentialType", "bodyParameters": {"parameters": [{"name": "mediaType", "value": "application/pdf"}]}, "genericAuthType": "httpHeaderAuth", "headerParameters": {"parameters": [{"name": "Authorization", "value": "=Bearer {{ $json.access_token }}"}]}}, "credentials": {"httpHeaderAuth": {"id": "", "name": "[Your httpHeaderAuth]"}}, "typeVersion": 4.1}, {"id": "9e900a45-d792-4dc5-938c-0d5cdfd2e647", "name": "Execute Workflow Trigger", "type": "n8n-nodes-base.executeWorkflowTrigger", "position": [1140, 440], "parameters": {}, "typeVersion": 1}, {"id": "859f369d-f36f-4c3f-a50d-a17214fef2a3", "name": "Sticky Note", "type": "n8n-nodes-base.stickyNote", "position": [20, 140], "parameters": {"color": 5, "width": 667.6107231291055, "height": 715.2927406867177, "content": "# Adobe API Wrapper\n\nSee Adobe documentation:\n- https://developer.adobe.com/document-services/docs/overview/pdf-services-api/howtos/\n- https://developer.adobe.com/document-services/docs/overview/pdf-extract-api/gettingstarted/\n\nIn short, this workflow does the following steps :\n\n- Authentication\n- Upload an asset (pdf) to adobe\n- Wait for the asset to be processed by Adobe\n- Download the result\n\n## Credential\n\nCredentials are not \"predefined\" and you'll have to create 2 custom credentials, detailed in the workflow.\n\n## Result\n\nThe result will depend on the transformation requested. It could be 1 of various files (json, zip...) accessible via download URL returned by the workflow.\n\nWorkflow can be tested with a PDF filed fetched with Dorpbox for example or any storage provider. "}, "typeVersion": 1}, {"id": "450199c5-e588-486d-81cf-eb69cf729ab1", "name": "Sticky Note1", "type": "n8n-nodes-base.stickyNote", "position": [560, 900], "parameters": {"width": 857.2064431277577, "height": 463.937514110429, "content": "## Testing for development"}, "typeVersion": 1}, {"id": "311a75d6-4fbe-4d8f-89b3-d4b0ee21f7ae", "name": "Adobe API Query", "type": "n8n-nodes-base.set", "position": [900, 1000], "parameters": {"options": {}, "assignments": {"assignments": [{"id": "62bb6466-acf4-41e5-9444-c9ef608a6822", "name": "endpoint", "type": "string", "value": "extractpdf"}, {"id": "0352f585-1434-4ab7-a704-a1e187fffa96", "name": "json_payload", "type": "object", "value": "={{ \n{\n \"renditionsToExtract\": [\n \"tables\"\n ],\n \"elementsToExtract\": [\n \"text\",\n \"tables\"\n ]\n }\n}}"}]}}, "typeVersion": 3.4}, {"id": "abf20778-db50-4787-a5f4-7af5d5c76efe", "name": "Load a test pdf file", "type": "n8n-nodes-base.dropbox", "position": [900, 1180], "parameters": {"path": "/valerian/w/prod/_freelance/ADEZIF/AI/Source data/Brochures pour GPT/Brochure 3M/3M_doc_emballage VERSION FINALE.pdf", "operation": "download", "authentication": "oAuth2"}, "credentials": {"dropboxOAuth2Api": {"id": "", "name": "[Your dropboxOAuth2Api]"}}, "typeVersion": 1}, {"id": "8bb2ae0c-df61-4110-af44-b1040b4340a2", "name": "Query + File", "type": "n8n-nodes-base.merge", "position": [1180, 1080], "parameters": {"mode": "combine", "options": {}, "combinationMode": "mergeByPosition"}, "typeVersion": 2.1}, {"id": "92afa6d6-daf8-4358-8c95-36473b810dc2", "name": "Query + File + Asset information", "type": "n8n-nodes-base.merge", "position": [2180, 580], "parameters": {"mode": "combine", "options": {}, "combinationMode": "mergeByPosition"}, "typeVersion": 2.1}, {"id": "5d88b8e4-0b0a-463a-88db-c45d5e87e823", "name": "Process Query", "type": "n8n-nodes-base.httpRequest", "position": [2640, 580], "parameters": {"url": "=https://pdf-services.adobe.io/operation/{{ $('Query + File + Asset information').item.json.endpoint }}", "method": "POST", "options": {"redirect": {"redirect": {}}, "response": {"response": {"fullResponse": true}}}, "jsonBody": "={{ \n{\n...{ \"assetID\":$('Query + File + Asset information').first().json.assetID },\n...$('Query + File + Asset information').first().json.json_payload\n}\n}}", "sendBody": true, "sendHeaders": true, "specifyBody": "json", "authentication": "genericCredentialType", "genericAuthType": "httpHeaderAuth", "headerParameters": {"parameters": [{"name": "Authorization", "value": "=Bearer {{ $('Authenticartion (get token)').first().json[\"access_token\"] }}"}]}}, "credentials": {"httpHeaderAuth": {"id": "", "name": "[Your httpHeaderAuth]"}}, "typeVersion": 4.1}, {"id": "47278b2f-dd04-4609-90ab-52f34b9a0e72", "name": "Wait 5 second", "type": "n8n-nodes-base.wait", "position": [2860, 580], "webhookId": "ed00a9a8-d599-4a98-86f8-a15176352c0a", "parameters": {"unit": "seconds", "amount": 5}, "typeVersion": 1}, {"id": "691b52ae-132a-4105-b1e4-bb7d55d0e347", "name": "Try to download the result", "type": "n8n-nodes-base.httpRequest", "position": [3080, 580], "parameters": {"url": "={{ $('Process Query').item.json[\"headers\"][\"location\"] }}", "options": {}, "sendHeaders": true, "authentication": "genericCredentialType", "genericAuthType": "httpHeaderAuth", "headerParameters": {"parameters": [{"name": "Authorization", "value": "=Bearer {{ $('Authenticartion (get token)').first().json[\"access_token\"] }}"}]}}, "credentials": {"httpHeaderAuth": {"id": "", "name": "[Your httpHeaderAuth]"}}, "typeVersion": 4.1}, {"id": "277dea14-de8d-4719-aff1-f4008d6d5c67", "name": "Switch", "type": "n8n-nodes-base.switch", "position": [3260, 580], "parameters": {"rules": {"values": [{"outputKey": "in progress", "conditions": {"options": {"leftValue": "", "caseSensitive": true, "typeValidation": "strict"}, "combinator": "and", "conditions": [{"operator": {"type": "string", "operation": "equals"}, "leftValue": "={{ $json.status }}", "rightValue": "in progress"}]}, "renameOutput": true}, {"outputKey": "failed", "conditions": {"options": {"leftValue": "", "caseSensitive": true, "typeValidation": "strict"}, "combinator": "and", "conditions": [{"id": "6d6917f6-abb9-4175-a070-a2f500d9f34f", "operator": {"name": "filter.operator.equals", "type": "string", "operation": "equals"}, "leftValue": "={{ $json.status }}", "rightValue": "failed"}]}, "renameOutput": true}]}, "options": {"fallbackOutput": "extra"}}, "typeVersion": 3}, {"id": "8f6f8273-43ed-4a44-bb27-6ce137000472", "name": "Forward response to origin workflow", "type": "n8n-nodes-base.set", "position": [3820, 600], "parameters": {"options": {}, "assignments": {"assignments": []}, "includeOtherFields": true}, "typeVersion": 3.4}, {"id": "00e2d7e3-94cd-49e5-a975-2fdc1a7a95fd", "name": "Sticky Note2", "type": "n8n-nodes-base.stickyNote", "position": [2780, 480], "parameters": {"width": 741.3069226712129, "height": 336.57433650102917, "content": "## Wait for file do be processed"}, "typeVersion": 1}, {"id": "3667b1ba-b9a6-4e1a-94b1-61b37f1e7adc", "name": "Sticky Note3", "type": "n8n-nodes-base.stickyNote", "position": [1324.6733934850213, 147.59707015795897], "parameters": {"color": 5, "width": 402.63171535688423, "height": 700.9473619571734, "content": "### 1- Credential for token request\n\nCreate a \"Custom Auth\" credential like this :\n\n```\n{\n \"headers\": {\n \"Content-Type\":\"application/x-www-form-urlencoded\"\n }, \n \"body\" : {\n \"client_id\": \"****\", \n \"client_secret\":\"****\"\n }\n}\n```"}, "typeVersion": 1}, {"id": "718bb738-8ce4-4b38-94e4-6ccac1adf9ec", "name": "Sticky Note4", "type": "n8n-nodes-base.stickyNote", "position": [1800, 152.6219700851708], "parameters": {"color": 5, "width": 1752.5923360342827, "height": 692.0175575715904, "content": "### 2- Credential for all other Queries\n\nCreate a \"Header Auth\" credential like this : \n\n```\nX-API-Key: **** (same value as client_id)\n```"}, "typeVersion": 1}, {"id": "d6bc8011-699d-4388-82f5-e5f90ba8672a", "name": "Sticky Note5", "type": "n8n-nodes-base.stickyNote", "position": [740, 140], "parameters": {"color": 5, "width": 529.7500231395039, "height": 718.8735380890446, "content": "## Workflow Input\n\n- endpoint: splitpdf, extractpdf, ...\n- json_payload : all endpoint payload except assetID which is handled in current workflow\n- **PDF Data as n8n Binary**\n\n\n### Example for **split** : \n\n```\n{\n \"endpoint\": \"splitpdf\",\n \"json_payload\": {\n \"splitoption\": \n { \"pageRanges\": [{\"start\": 1,\"end\": 2}]}\n }\n }\n}\n```\n\n### Example for **extractpdf**\n\n```\n{\n \"endpoint\": \"splitpdf\",\n \"json_payload\": {\n \"renditionsToExtract\": [\n \"tables\"\n ],\n \"elementsToExtract\": [\n \"text\",\n \"tables\"\n ]\n }\n}\n```"}, "typeVersion": 1}, {"id": "2bbf6d9d-8399-49ba-94ea-b90795ef44ba", "name": "Authenticartion (get token)", "type": "n8n-nodes-base.httpRequest", "position": [1500, 580], "parameters": {"url": "https://pdf-services.adobe.io/token", "method": "POST", "options": {}, "sendBody": true, "contentType": "form-urlencoded", "authentication": "genericCredentialType", "bodyParameters": {"parameters": [{}]}, "genericAuthType": "httpCustomAuth"}, "credentials": {"httpCustomAuth": {"id": "", "name": "[Your httpCustomAuth]"}}, "typeVersion": 4.1}, {"id": "be4e87e8-6e56-408f-b932-320023382f98", "name": "Upload PDF File (asset)", "type": "n8n-nodes-base.httpRequest", "position": [2440, 580], "parameters": {"url": "={{ $json.uploadUri }}", "method": "PUT", "options": {"redirect": {"redirect": {}}}, "sendBody": true, "sendQuery": true, "contentType": "binaryData", "queryParameters": {"parameters": [{}]}, "inputDataFieldName": "data"}, "typeVersion": 4.1}], "pinData": {}, "connections": {"Switch": {"main": [[{"node": "Wait 5 second", "type": "main", "index": 0}], [{"node": "Forward response to origin workflow", "type": "main", "index": 0}], [{"node": "Forward response to origin workflow", "type": "main", "index": 0}]]}, "Create Asset": {"main": [[{"node": "Query + File + Asset information", "type": "main", "index": 1}]]}, "Query + File": {"main": [[{"node": "Authenticartion (get token)", "type": "main", "index": 0}, {"node": "Query + File + Asset information", "type": "main", "index": 0}]]}, "Process Query": {"main": [[{"node": "Wait 5 second", "type": "main", "index": 0}]]}, "Wait 5 second": {"main": [[{"node": "Try to download the result", "type": "main", "index": 0}]]}, "Adobe API Query": {"main": [[{"node": "Query + File", "type": "main", "index": 0}]]}, "Load a test pdf file": {"main": [[{"node": "Query + File", "type": "main", "index": 1}]]}, "Upload PDF File (asset)": {"main": [[{"node": "Process Query", "type": "main", "index": 0}]]}, "Execute Workflow Trigger": {"main": [[{"node": "Authenticartion (get token)", "type": "main", "index": 0}, {"node": "Query + File + Asset information", "type": "main", "index": 0}]]}, "Try to download the result": {"main": [[{"node": "Switch", "type": "main", "index": 0}]]}, "Authenticartion (get token)": {"main": [[{"node": "Create Asset", "type": "main", "index": 0}]]}, "Query + File + Asset information": {"main": [[{"node": "Upload PDF File (asset)", "type": "main", "index": 0}]]}, "When clicking \u2018Test workflow\u2019": {"main": [[{"node": "Load a test pdf file", "type": "main", "index": 0}, {"node": "Adobe API Query", "type": "main", "index": 0}]]}}}How to Import This Workflow
- 1Copy the workflow JSON above using the Copy Workflow JSON button.
- 2Open your n8n instance and go to Workflows.
- 3Click Import from JSON and paste the copied workflow.
Don't have an n8n instance? Start your free trial at n8nautomation.cloud
Related Templates
Ask questions about a PDF using AI
Effortlessly transform your Google Drive PDFs into an interactive knowledge base with this powerful AI workflow. This n8n automation connects your Google Drive files, processes them with OpenAI embeddings, and stores them in a Pinecone vector database, allowing you to ask questions and receive intelligent answers directly from your document content. When a new PDF is uploaded to Google Drive, the workflow automatically extracts its text, splits it into manageable chunks using the Recursive Character Text Splitter, generates embeddings via OpenAI, and then inserts this structured data into Pinecone for efficient retrieval. Later, by clicking the 'Chat' button, you can engage in a natural language conversation with your document, powered by the OpenAI Chat Model and the Question and Answer Chain, which retrieves relevant information from Pinecone. This is ideal for researchers needing to quickly extract insights from large reports, legal professionals analyzing contracts, or businesses creating searchable knowledge bases from their documentation, saving countless hours of manual review and information searching.
Supabase Insertion & Upsertion & Retrieval
Efficiently manage and query your data with the Supabase Insertion & Upsertion & Retrieval workflow, a powerful solution for integrating document management with intelligent data processing. This 21-node workflow, triggered manually, connects Google Drive, Supabase, and OpenAI to automate the ingestion, updating, and retrieval of information. It allows you to upload documents from Google Drive, which are then processed by a Recursive Character Text Splitter and embedded using OpenAI Embeddings for insertion or upsertion into your Supabase vector store via the Insert Documents and Update Documents nodes. When a chat message is received, the workflow leverages OpenAI's Chat Model and a Question and Answer Chain to retrieve relevant information from Supabase using the Retrieve by Query node, providing intelligent responses based on your stored documents. This workflow is ideal for businesses and individuals who need to maintain an up-to-date knowledge base, power AI-driven chatbots with proprietary information, or automate the synchronization of document content with a searchable database, significantly reducing manual data entry and improving information accessibility.
Chat with Postgresql Database
Empower your users to interact with your PostgreSQL database using natural language by automating the process of querying and retrieving information. This workflow connects a chat interface, triggered by a new message, to an AI Agent that leverages OpenAI's powerful language model to understand user requests. The AI Agent intelligently utilizes a suite of PostgreSQL tools, including "Get Table Definition," "Execute SQL Query," and "Get DB Schema and Tables List," to dynamically fetch database schema, generate appropriate SQL queries, and execute them against your database. Chat history is maintained using an AI memory buffer, allowing for contextual conversations. This solution is ideal for support teams needing quick data lookups, business analysts exploring data without writing SQL, or developers building interactive data dashboards. It eliminates the need for manual SQL query writing, speeds up data access, and reduces the training burden for non-technical users, saving significant time and resources while improving data accessibility.