This workflow follows the Documentdefaultdataloader → Google Gemini Embeddings 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": {
"jsonMode": "expressionData",
"jsonData": "={{ $json.documentation }}",
"textSplittingMode": "custom",
"options": {}
},
"id": "0a52ad6e-9c9c-415f-b1ec-f1782678cdd5",
"cid": "Ikx1Y2FzIFBleXJpbiI",
"name": "Default Data Loader",
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"creator": "Lucas Peyrin",
"position": [
1088,
656
],
"typeVersion": 1.1,
"notes": "\u00a9 2025 Lucas Peyrin"
},
{
"parameters": {
"chunkSize": 1500,
"chunkOverlap": 200,
"options": {
"splitCode": "markdown"
}
},
"id": "50480aec-7bb8-41d1-b569-62ce4c20e251",
"cid": "Ikx1Y2FzIFBleXJpbiI",
"name": "Recursive Character Text Splitter",
"type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
"creator": "Lucas Peyrin",
"position": [
1184,
864
],
"typeVersion": 1,
"notes": "\u00a9 2025 Lucas Peyrin"
},
{
"parameters": {
"operation": "removeItemsSeenInPreviousExecutions",
"dedupeValue": "={{ $json.documentation }}",
"options": {
"scope": "node",
"historySize": 10000
}
},
"id": "e388bdaa-3c42-4512-b4a3-aaaf9a801557",
"cid": "Ikx1Y2FzIFBleXJpbiI",
"name": "Remove Duplicate Documentation Content",
"type": "n8n-nodes-base.removeDuplicates",
"creator": "Lucas Peyrin",
"position": [
464,
432
],
"typeVersion": 2,
"notes": "\u00a9 2025 Lucas Peyrin"
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "5ed964a6-5200-454c-b983-f3dc7c8c7a48",
"name": "documentation",
"type": "string",
"value": "={{ $json.data.replace(/([^#\\n]+)\\s*#/g, '# $1').trim().replace(/^\\s*https?:\\/\\/\\S+\\s*/, '') }}"
}
]
},
"options": {}
},
"id": "571b1485-37b1-4e9d-9209-d28db775f36b",
"cid": "Ikx1Y2FzIFBleXJpbiI",
"name": "Clean Documentation",
"type": "n8n-nodes-base.set",
"creator": "Lucas Peyrin",
"position": [
48,
432
],
"typeVersion": 3.4,
"notes": "\u00a9 2025 Lucas Peyrin"
},
{
"parameters": {
"url": "=https://dynamic-docs.prestalife.net/{{ $json.link }}",
"options": {}
},
"id": "6b9db681-67ac-41ef-8b6e-bbd9cb1e8124",
"cid": "Ikx1Y2FzIFBleXJpbiI",
"name": "Get Documentation Page",
"type": "n8n-nodes-base.httpRequest",
"creator": "Lucas Peyrin",
"position": [
-736,
432
],
"typeVersion": 4.2,
"onError": "continueErrorOutput",
"notes": "\u00a9 2025 Lucas Peyrin"
},
{
"parameters": {
"operation": "extractHtmlContent",
"extractionValues": {
"values": [
{
"key": "data",
"cssSelector": "main.main"
}
]
},
"options": {}
},
"id": "52dd037a-b55e-49f1-bb51-8eeb2135ad54",
"cid": "Ikx1Y2FzIFBleXJpbiI",
"name": "Extract Documentation Content",
"type": "n8n-nodes-base.html",
"creator": "Lucas Peyrin",
"position": [
-432,
432
],
"typeVersion": 1.2,
"notes": "\u00a9 2025 Lucas Peyrin"
},
{
"parameters": {},
"id": "4d18a4f1-be21-4bb7-a746-b85cf4fec9b6",
"cid": "Ikx1Y2FzIFBleXJpbiI",
"name": "Gemini Chunk Embedding",
"type": "@n8n/n8n-nodes-langchain.embeddingsGoogleGemini",
"creator": "Lucas Peyrin",
"position": [
960,
656
],
"typeVersion": 1,
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
},
"notes": "\u00a9 2025 Lucas Peyrin"
},
{
"parameters": {
"content": "### Step 1.5.1: Read a Single Page\n\n**What it does:** This node takes a single URL from the loop and fetches the HTML content of that page.\n**Analogy:** The librarian opens one book to the first page.",
"height": 384,
"width": 288,
"color": 7
},
"id": "7a51c18a-0420-4dd6-a1c5-d65a83ff55a4",
"cid": "Ikx1Y2FzIFBleXJpbiI",
"name": "Sticky Note11",
"type": "n8n-nodes-base.stickyNote",
"creator": "Lucas Peyrin",
"position": [
-832,
224
],
"typeVersion": 1,
"notes": "\u00a9 2025 Lucas Peyrin"
},
{
"parameters": {
"content": "### Why Use a Sub-Workflow?\n\nThe main reason is **memory management**.\n\nProcessing a single web page, especially creating vector embeddings for all its chunks, uses a lot of memory (RAM). The n8n documentation has over 1,000 pages. If we tried to process all of them in a single, linear run, the memory usage would build up with each page and would likely crash your n8n instance.\n\nWhen a sub-workflow finishes its run for one item (one page), n8n **clears out the memory** (RAM) it used before starting the next one.\n\nBy using a sub-workflow, we process pages one-by-one in a memory-efficient loop, making the entire indexing process stable and reliable, even on a massive scale.",
"height": 528,
"width": 512,
"color": 5
},
"id": "48371192-892a-4d6d-8dfd-1f4398876d87",
"cid": "Ikx1Y2FzIFBleXJpbiI",
"name": "Sticky Note12",
"type": "n8n-nodes-base.stickyNote",
"creator": "Lucas Peyrin",
"position": [
-1360,
80
],
"typeVersion": 1,
"notes": "\u00a9 2025 Lucas Peyrin"
},
{
"parameters": {
"content": "### Step 1.5.2: Get the Good Stuff\n\n**What it does:** It extracts only the main text from the article on the page, ignoring menus, footers, and images. Then, it cleans up the formatting.\n**Analogy:** The librarian tears out only the useful pages from the book and cleans up any smudges or messy handwriting.",
"height": 384,
"width": 736,
"color": 7
},
"id": "9d378ee6-bcc6-4b44-a3b0-70cbf73752f1",
"cid": "Ikx1Y2FzIFBleXJpbiI",
"name": "Sticky Note13",
"type": "n8n-nodes-base.stickyNote",
"creator": "Lucas Peyrin",
"position": [
-528,
224
],
"typeVersion": 1,
"notes": "\u00a9 2025 Lucas Peyrin"
},
{
"parameters": {
"content": "### Step 1.5.3: Avoid Re-reading\n\n**What it does:** It checks if we have already processed this exact page content in a previous run. If so, it stops here to save time and resources.\n**Analogy:** The librarian checks their \"already read\" pile to avoid reading the same book twice.\n\n**A Powerful Feature Explained:**\n\nUsually, the \"Remove Duplicates\" node only looks at the items in the *current* execution. But here, it's set to **\"Remove items seen in previous executions.\"**\n\nThis is incredibly powerful in a sub-workflow. Even though our sub-workflow only sees one page at a time, this node has a long-term memory. It remembers every single page it has *ever* processed across all previous runs.\n\nThis makes the workflow robust. You can run the indexing process again and again to update the knowledge base with new documentation, and it will never waste resources re-processing old pages and more importantly, it won't create duplicate chunks in Supabase.",
"height": 608,
"width": 544,
"color": 5
},
"id": "fd34238e-f0eb-423d-8d0f-7a59db734219",
"cid": "Ikx1Y2FzIFBleXJpbiI",
"name": "Sticky Note14",
"type": "n8n-nodes-base.stickyNote",
"creator": "Lucas Peyrin",
"position": [
240,
0
],
"typeVersion": 1,
"notes": "\u00a9 2025 Lucas Peyrin"
},
{
"parameters": {
"content": "### Step 1.5.4: Create & Store the 'Magic Index Cards'\n\nThis is the most important step of indexing!\n\n1. **`Recursive Character Text Splitter`:** The text is broken down into small, overlapping paragraphs (\"chunks\").\n * **Analogy:** The librarian breaks the book down into small, meaningful paragraphs. This is vital for finding very specific answers later.\n\n2. **`Gemini Chunk Embedding`:** An AI model converts each chunk of text into a list of numbers (a \"vector\" or \"embedding\").\n * **Analogy:** The librarian uses a 'magic pen' to turn each paragraph into a unique set of numbers. Paragraphs with similar meanings get similar numbers.\n\n3. **`Your Supabase Vector Store (Insert)`:** The original text chunk and its new vector are saved together in your Supabase database.\n * **Analogy:** The librarian files the original paragraph along with its magic number on an index card and puts it in a special filing cabinet (your Supabase vector store).",
"height": 1040,
"width": 656,
"color": 6
},
"id": "90f31c17-f869-4a07-9ac9-ada55820d927",
"cid": "Ikx1Y2FzIFBleXJpbiI",
"name": "Sticky Note15",
"type": "n8n-nodes-base.stickyNote",
"creator": "Lucas Peyrin",
"position": [
800,
0
],
"typeVersion": 1,
"notes": "\u00a9 2025 Lucas Peyrin"
},
{
"parameters": {
"inputSource": "passthrough"
},
"id": "e28ce8a6-a2f1-4972-942a-1e9c24c37d14",
"cid": "Ikx1Y2FzIFBleXJpbiI",
"name": "Ingest Web Page",
"type": "n8n-nodes-base.executeWorkflowTrigger",
"creator": "Lucas Peyrin",
"position": [
-1040,
432
],
"typeVersion": 1.1,
"notes": "\u00a9 2025 Lucas Peyrin"
},
{
"parameters": {
"mode": "insert",
"qdrantCollection": {
"__rl": true,
"value": "dp-docs",
"mode": "id"
},
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.vectorStoreQdrant",
"typeVersion": 1.3,
"position": [
1008,
432
],
"id": "d8e0a22e-e388-4b47-b5f0-dec91b0b0e1b",
"name": "Qdrant Vector Store",
"credentials": {
"qdrantApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"workflowId": {
"__rl": true,
"value": "UxCYQUrNOlr9AKeK",
"mode": "list",
"cachedResultUrl": "/workflow/UxCYQUrNOlr9AKeK",
"cachedResultName": "Extract Text From Images"
},
"workflowInputs": {
"mappingMode": "defineBelow",
"value": {}
},
"options": {}
},
"type": "n8n-nodes-base.executeWorkflow",
"typeVersion": 1.3,
"position": [
-176,
736
],
"id": "e2e5d429-abc1-4dcb-8915-36ad25f52385",
"name": "Call 'Extract Text From Images'"
},
{
"parameters": {
"functionCode": "return [{\n\"json\": {\"link\": \"/fields.html\"}\n}]"
},
"name": "Set Init-Data",
"type": "n8n-nodes-base.function",
"typeVersion": 1,
"position": [
-1168,
752
],
"id": "5d3425e4-d5f5-4ab1-a9aa-b6f62963c8f3"
},
{
"parameters": {},
"name": "Input Data",
"type": "n8n-nodes-base.noOp",
"typeVersion": 1,
"position": [
-1024,
752
],
"id": "7f0796d2-eb05-43bd-8e58-2ff332d9ea55"
},
{
"parameters": {},
"type": "n8n-nodes-base.manualTrigger",
"typeVersion": 1,
"position": [
-1360,
752
],
"id": "84f680f0-a5cb-4a9c-9d1f-2f0bc351dee6",
"name": "When clicking \u2018Execute workflow\u2019",
"disabled": true
}
],
"connections": {
"Default Data Loader": {
"ai_document": [
[
{
"node": "Qdrant Vector Store",
"type": "ai_document",
"index": 0
}
]
]
},
"Recursive Character Text Splitter": {
"ai_textSplitter": [
[
{
"node": "Default Data Loader",
"type": "ai_textSplitter",
"index": 0
}
]
]
},
"Remove Duplicate Documentation Content": {
"main": [
[
{
"node": "Qdrant Vector Store",
"type": "main",
"index": 0
}
]
]
},
"Clean Documentation": {
"main": [
[
{
"node": "Remove Duplicate Documentation Content",
"type": "main",
"index": 0
}
]
]
},
"Get Documentation Page": {
"main": [
[
{
"node": "Extract Documentation Content",
"type": "main",
"index": 0
}
]
]
},
"Extract Documentation Content": {
"main": [
[
{
"node": "Clean Documentation",
"type": "main",
"index": 0
}
]
]
},
"Gemini Chunk Embedding": {
"ai_embedding": [
[
{
"node": "Qdrant Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Ingest Web Page": {
"main": [
[
{
"node": "Get Documentation Page",
"type": "main",
"index": 0
}
]
]
},
"Call 'Extract Text From Images'": {
"main": [
[]
]
},
"Set Init-Data": {
"main": [
[
{
"node": "Input Data",
"type": "main",
"index": 0
}
]
]
},
"Input Data": {
"main": [
[
{
"node": "Get Documentation Page",
"type": "main",
"index": 0
}
]
]
},
"When clicking \u2018Execute workflow\u2019": {
"main": [
[
{
"node": "Set Init-Data",
"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.
googlePalmApiqdrantApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Dynamic-Rag-Vector. Uses documentDefaultDataLoader, textSplitterRecursiveCharacterTextSplitter, httpRequest, embeddingsGoogleGemini. Event-driven trigger; 18 nodes.
Source: https://gist.github.com/unlocomqx/f14b322f8526f759444a95933bddf421 — 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.
Api Schema Extractor. Uses manualTrigger, httpRequest, splitOut, textSplitterRecursiveCharacterTextSplitter. Event-driven trigger; 88 nodes.
HTTP Request, Text Splitter Recursive Character Text Splitter, Document Default Data Loader +9
Wait Splitout. Uses manualTrigger, httpRequest, splitOut, textSplitterRecursiveCharacterTextSplitter. Event-driven trigger; 88 nodes.
HTTP Request, Text Splitter Recursive Character Text Splitter, Document Default Data Loader +9
This workflow automates the process of discovering and extracting APIs from various services, followed by generating custom schemas. It works in three distinct stages: research, extraction, and schema
HTTP Request, Text Splitter Recursive Character Text Splitter, Document Default Data Loader +9
Agente_Ecommerce_v3_subflujo. Uses embeddingsGoogleGemini, vectorStoreQdrant, executeWorkflowTrigger, textSplitterRecursiveCharacterTextSplitter. Event-driven trigger; 10 nodes.
Google Gemini Embeddings, Qdrant Vector Store, Execute Workflow Trigger +3
Agent IA Projet Client. Uses executeWorkflowTrigger, lmChatOpenAi, toolWorkflow, vectorStoreQdrant. Event-driven trigger; 79 nodes.
Execute Workflow Trigger, OpenAI Chat, Tool Workflow +16