This workflow follows the Agent → Documentdefaultdataloader 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 →
{
"name": "Larry Llama",
"nodes": [
{
"parameters": {
"promptType": "define",
"text": "={{ $json.body.chatInput ?? \"No Prompt\" }}",
"options": {
"systemMessage": "You are a helpful assistant"
}
},
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 1.9,
"position": [
-220,
-60
],
"id": "26112864-b277-417d-b63a-6dce4a45d4c8",
"name": "AI Agent"
},
{
"parameters": {
"model": "llama3.1:8b",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOllama",
"typeVersion": 1,
"position": [
-260,
160
],
"id": "31dca842-e582-44a6-ab53-45a5c7f06b96",
"name": "Ollama Chat Model",
"credentials": {
"ollamaApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"sessionIdType": "customKey",
"sessionKey": "={{ $json.body.sessionId }}"
},
"type": "@n8n/n8n-nodes-langchain.memoryPostgresChat",
"typeVersion": 1.3,
"position": [
-140,
160
],
"id": "beb69e5b-fa18-452a-a9cf-644ed71ca77a",
"name": "Postgres Chat Memory",
"credentials": {
"postgres": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"httpMethod": "POST",
"path": "larry-llama",
"responseMode": "responseNode",
"options": {}
},
"type": "n8n-nodes-base.webhook",
"typeVersion": 2,
"position": [
-480,
140
],
"id": "85d28a01-f94f-4d17-b56b-2edddd19699a",
"name": "Webhook"
},
{
"parameters": {
"respondWith": "allIncomingItems",
"options": {}
},
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1.2,
"position": [
1140,
160
],
"id": "b9fdd657-30cf-4eac-b567-75bdf33641bc",
"name": "Respond to Webhook"
},
{
"parameters": {
"model": "nomic-embed-text:latest"
},
"type": "@n8n/n8n-nodes-langchain.embeddingsOllama",
"typeVersion": 1,
"position": [
68,
360
],
"id": "59db52c3-9998-4722-a65b-968a0ee16183",
"name": "Embeddings Ollama",
"credentials": {
"ollamaApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"mode": "retrieve-as-tool",
"toolName": "personal_knowledgebase",
"toolDescription": "Work with data in personal knowledgebase",
"qdrantCollection": {
"__rl": true,
"value": "knowledge_base",
"mode": "list",
"cachedResultName": "knowledge_base"
},
"topK": 5,
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.vectorStoreQdrant",
"typeVersion": 1.1,
"position": [
-20,
160
],
"id": "0015f1fe-0367-4b64-8b21-2ad5ae6d2a12",
"name": "Personal KB Retrieval",
"credentials": {
"qdrantApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"triggerOn": "folder",
"path": "/data/personal_knowledge_base",
"events": [
"change",
"add"
],
"options": {}
},
"type": "n8n-nodes-base.localFileTrigger",
"typeVersion": 1,
"position": [
-680,
720
],
"id": "392a432c-e0d5-4ecb-aa76-be4457be33c1",
"name": "Local File Trigger"
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "6187692d-1c25-4b79-95f4-ee8c37d28a7f",
"name": "fileId",
"value": "= {{ $json.path }}",
"type": "string"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
-460,
720
],
"id": "2b31725a-add1-44bc-b91e-e539692ab9a9",
"name": "set fileId"
},
{
"parameters": {
"jsCode": "const { OllamaEmbeddings } = require(\"@langchain/ollama\");\nconst { QdrantVectorStore } = require(\"@langchain/qdrant\");\n\nconst embeddings = new OllamaEmbeddings({\n model: \"nomic-embed-text\",\n baseUrl: \"http://host.docker.internals:11434\"\n});\n\nconst vectorStore = await QdrantVectorStore.fromExistingCollection(\n embeddings,\n {\n url: \"http://qdrant:6333\",\n collectionName: \"knowledge_base\",\n }\n);\n\nconst fileIdToDelete = $json.fileId\n\nconst filter = {\n must: [\n {\n key: \"metadata.fileId\",\n match: {\n value: fileIdToDelete,\n },\n },\n ],\n }\n\nvectorStore.client.delete(\"knowledge_base\", {\n filter\n});\n\nreturn [ {json: { file_id: fileIdToDelete } } ];\n\n"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
-240,
720
],
"id": "423bb69f-b715-49ef-8d3a-807c38dff67b",
"name": "Delete Previous Vectors For File"
},
{
"parameters": {
"jsCode": "const fetch = require('node-fetch');\nconst cheerio = require('cheerio');\n\nconst binaryProp = Object.keys(items[0].binary)[0];\nconst b64 = items[0].binary[binaryProp].data;\nconst mimeType = items[0].binary[binaryProp].mimeType;\n\n// 3. Decode and send to Tika\nconst buffer = Buffer.from(b64, 'base64');\n\nconst res = await fetch('http://tika:9998/tika', {\n method: 'PUT',\n headers: { 'Content-Type': mimeType || 'application/octet-stream' },\n body: buffer,\n});\n\nconst extractedText = await res.text();\n\nconst $ = cheerio.load(extractedText);\n\nconst fullText = $('body').text().trim();\n\n// 4. Return in the shape n8n expects\nreturn [{\n json: {\n ...items[0].json,\n // Flowise Default Data Loader by default looks for `text`\n text: fullText,\n // carry along any IDs or metadata you need downstream\n fileName: items[0].json.fileName,\n fileId: items[0].json.fileId,\n }\n}];"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
260,
720
],
"id": "6d9a74ea-0c09-444a-b4aa-4acaac5af7da",
"name": "Extract Text Fa Sho"
},
{
"parameters": {
"fileSelector": "={{ $json.file_id.trim() }}",
"options": {}
},
"type": "n8n-nodes-base.readWriteFile",
"typeVersion": 1,
"position": [
20,
720
],
"id": "c4bf8dd6-f7dc-48d6-9946-ded8407b4088",
"name": "Read/Write Files from Disk"
},
{
"parameters": {
"mode": "insert",
"qdrantCollection": {
"__rl": true,
"value": "knowledge_base",
"mode": "list",
"cachedResultName": "knowledge_base"
},
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.vectorStoreQdrant",
"typeVersion": 1.1,
"position": [
760,
720
],
"id": "6f7fe530-539a-4d06-b915-f0c90c80535e",
"name": "Qdrant Vector Store",
"credentials": {
"qdrantApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"model": "nomic-embed-text:latest"
},
"type": "@n8n/n8n-nodes-langchain.embeddingsOllama",
"typeVersion": 1,
"position": [
560,
940
],
"id": "800c4a1c-e1a3-4a71-940e-67bf34085fed",
"name": "Embeddings Ollama1",
"credentials": {
"ollamaApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"jsonMode": "expressionData",
"jsonData": "={{ $json.text }}",
"options": {
"metadata": {
"metadataValues": [
{
"name": "fileId",
"value": "={{ $('set fileId').item.json.fileId }}"
}
]
}
}
},
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"typeVersion": 1,
"position": [
780,
960
],
"id": "08aa02ee-989f-4568-ba2d-04c3ab56543c",
"name": "Default Data Loader"
},
{
"parameters": {
"chunkSize": 500,
"chunkOverlap": 50
},
"type": "@n8n/n8n-nodes-langchain.textSplitterTokenSplitter",
"typeVersion": 1,
"position": [
820,
1160
],
"id": "42b0c8d6-38ea-4d1b-8142-2ef6ae261119",
"name": "Token Splitter"
},
{
"parameters": {
"mode": "runOnceForEachItem",
"jsCode": "return { output: $json.output };"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
640,
160
],
"id": "911f8bfa-f40c-4c8f-bb10-c9d08e14ba83",
"name": "Prepare Response"
}
],
"connections": {
"Ollama Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Postgres Chat Memory": {
"ai_memory": [
[
{
"node": "AI Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"Webhook": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"AI Agent": {
"main": [
[
{
"node": "Prepare Response",
"type": "main",
"index": 0
}
]
]
},
"Embeddings Ollama": {
"ai_embedding": [
[
{
"node": "Personal KB Retrieval",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Personal KB Retrieval": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Local File Trigger": {
"main": [
[
{
"node": "set fileId",
"type": "main",
"index": 0
}
]
]
},
"set fileId": {
"main": [
[
{
"node": "Delete Previous Vectors For File",
"type": "main",
"index": 0
}
]
]
},
"Delete Previous Vectors For File": {
"main": [
[
{
"node": "Read/Write Files from Disk",
"type": "main",
"index": 0
}
]
]
},
"Read/Write Files from Disk": {
"main": [
[
{
"node": "Extract Text Fa Sho",
"type": "main",
"index": 0
}
]
]
},
"Extract Text Fa Sho": {
"main": [
[
{
"node": "Qdrant Vector Store",
"type": "main",
"index": 0
}
]
]
},
"Embeddings Ollama1": {
"ai_embedding": [
[
{
"node": "Qdrant Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Default Data Loader": {
"ai_document": [
[
{
"node": "Qdrant Vector Store",
"type": "ai_document",
"index": 0
}
]
]
},
"Token Splitter": {
"ai_textSplitter": [
[
{
"node": "Default Data Loader",
"type": "ai_textSplitter",
"index": 0
}
]
]
},
"Prepare Response": {
"main": [
[
{
"node": "Respond to Webhook",
"type": "main",
"index": 0
}
]
]
}
},
"active": true,
"settings": {
"executionOrder": "v1"
},
"versionId": "58445405-df9a-40bd-a085-a9af321ce2d0",
"meta": {
"templateCredsSetupCompleted": true
},
"id": "o26FVxqbbGZ4SHid",
"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.
ollamaApipostgresqdrantApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Larry Llama. Uses agent, lmChatOllama, memoryPostgresChat, embeddingsOllama. Webhook trigger; 17 nodes.
Source: https://github.com/jarmentor/larry-llama/blob/e6a2df44f0eb17050f46315bf8c2a87f4344fdde/workflows/Larry_Llama_v1.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.
V3 Local Agentic RAG AI Agent. Uses documentDefaultDataLoader, memoryPostgresChat, chatTrigger, agent. Webhook trigger; 41 nodes.
Document Default Data Loader, Memory Postgres Chat, Chat Trigger +9
Author: Jadai kongolo
Document Default Data Loader, Memory Postgres Chat, Chat Trigger +9
Homerag. Uses documentDefaultDataLoader, memoryPostgresChat, chatTrigger, agent. Webhook trigger; 41 nodes.
Document Default Data Loader, Memory Postgres Chat, Chat Trigger +9
Local RAG AI Agent. Uses memoryPostgresChat, lmChatOllama, lmOllama, toolVectorStore. Event-driven trigger; 24 nodes.
Memory Postgres Chat, Ollama Chat, Lm Ollama +9
V1 ocal RAG AI Agent. Uses memoryPostgresChat, lmChatOllama, lmOllama, toolVectorStore. Event-driven trigger; 24 nodes.
Memory Postgres Chat, Ollama Chat, Lm Ollama +9