I’m not receiving the expectede Answer from the AI Agent Cluster node when goin though a Q&A sub-node retrieving data from Qdrant Vector Store.
I’m not receiving an error message but instead the the Q&Q node always returns “I don’t know”. eventhough the answer is clearly in the Qdrant collection.
Qdrant is returning this payload:
{
“response”: [
{
“pageContent”: “”,
“metadata”: {
“Title”: “BlackRock Tokenized Fund Used as Collateral in Derivatives Trade”,
“Date”: “2025-04-08”,
“URL”: “BlackRock Tokenized Fund Used as Collateral in Derivatives Trade - Markets Media”
},
“id”: 1744106898890
},
{
“pageContent”: “”,
“metadata”: {
“Title”: “BlackRock Tokenized Fund Used as Collateral in Derivatives Trade”,
“Date”: “2025-04-09”,
“URL”: “BlackRock Tokenized Fund Used as Collateral in Derivatives Trade - Markets Media”
},
“id”: 1744187724219
},
{
“pageContent”: “”,
“metadata”: {},
“id”: 1744106318245
},
{
“pageContent”: “”,
“metadata”: {},
“id”: 1744119645628
}
]
}
The correct points are found but pageContent remains empty. Is it supposed to be empty? My payload in Qdrant looks like this:
{
“pageContent”: “Singapore’s QCP Capital executed the first derivatives trade using BlackRock’s tokenized treasury fund (BUIDL) as collateral via partnership with Securitize Credit. BUIDL, an Ethereum-based fund holding US Treasuries, enabled yield-enhanced strategies while maintaining regulatory compliance. The trade highlights growing institutional adoption of tokenized RWAs for collateral efficiency. JPMorgan’s Onyx Digital Assets and CFTC’s GMAC have endorsed DLT’s role in non-cash collateral markets without regulatory changes. DTCC also projects 2025 expansion of tokenized funds and secondary trading.”,
“metadata”: {
“Title”: “BlackRock Tokenized Fund Used as Collateral in Derivatives Trade”,
“Date”: “2025-04-09”,
“URL”: “BlackRock Tokenized Fund Used as Collateral in Derivatives Trade - Markets Media”
}
}
I only have 19 points in this collection since I’m still testing. What xould be the issue here. I’m a bit lost and would appreciate an answer from the community that saves my day. 
Workflow:
“name”: “AMA Test”,
“nodes”: [
{
“parameters”: {
“pollTimes”: {
“item”: [
{
“mode”: “everyMinute”
}
]
},
“documentId”: {
“__rl”: true,
“value”: “1EjmQL2EE9N7gh-9p5BT2cUqi9yYNuNOqfVWU4YnHQV8”,
“mode”: “list”,
“cachedResultName”: “Testing AMA”,
“cachedResultUrl”: “https://docs.google.com/spreadsheets/d/1EjmQL2EE9N7gh-9p5BT2cUqi9yYNuNOqfVWU4YnHQV8/edit?usp=drivesdk”
},
“sheetName”: {
“__rl”: true,
“value”: “gid=0”,
“mode”: “list”,
“cachedResultName”: “Tabellenblatt1”,
“cachedResultUrl”: “https://docs.google.com/spreadsheets/d/1EjmQL2EE9N7gh-9p5BT2cUqi9yYNuNOqfVWU4YnHQV8/edit#gid=0”
},
“event”: “rowAdded”,
“options”: {}
},
“type”: “n8n-nodes-base.googleSheetsTrigger”,
“typeVersion”: 1,
“position”: [
0,
0
],
“id”: “763db981-46f6-4586-b1ce-ecc57236421c”,
“name”: “Google Sheets Trigger”,
“credentials”: {
“googleSheetsTriggerOAuth2Api”: {
“id”: “vNmLQGygtdJkJIvA”,
“name”: “Google Sheets Trigger account 2”
}
}
},
{
“parameters”: {
“assignments”: {
“assignments”: [
{
“id”: “d20485d6-cd63-4110-92c2-7abba1e8528e”,
“name”: “user”,
“value”: “=Formulate a precise search query for a vector database on RWA tokenization from the following question:\nIs BlackRock’s BUILD used as Collateral?”,
“type”: “string”
},
{
“id”: “329a93ef-0255-4a78-a8f1-505a934d4713”,
“name”: “system”,
“value”: “You are a search agent for a vector database containing information about Real World Asset (RWA) tokenization. Your task is to formulate precise search queries from user questions that are well suited for a vector query.”,
“type”: “string”
}
]
},
“options”: {}
},
“type”: “n8n-nodes-base.set”,
“typeVersion”: 3.4,
“position”: [
180,
0
],
“id”: “e0a8b5a8-259e-42de-8ddb-8032d14b556b”,
“name”: “AI Prompt”
},
{
“parameters”: {
“promptType”: “define”,
“text”: “={{ $json.user }}”,
“options”: {
“systemMessage”: “={{ $json.system }}”,
“maxIterations”: 10,
“returnIntermediateSteps”: true
}
},
“type”: “@n8n/n8n-nodes-langchain.agent”,
“typeVersion”: 1.8,
“position”: [
460,
-80
],
“id”: “1899fdca-5e08-4f77-9767-18ec6b9288a5”,
“name”: “AI Agent”
},
{
“parameters”: {
“model”: {
“__rl”: true,
“mode”: “list”,
“value”: “gpt-4o-mini”
},
“options”: {}
},
“type”: “@n8n/n8n-nodes-langchain.lmChatOpenAi”,
“typeVersion”: 1.2,
“position”: [
440,
160
],
“id”: “e22090a1-aa48-40e3-ae77-a75abe3aaa43”,
“name”: “OpenAI Chat Model”,
“credentials”: {
“openAiApi”: {
“id”: “6cyuSPvF5pfESilM”,
“name”: “OpenAi account”
}
}
},
{
“parameters”: {
“sessionIdType”: “customKey”,
“sessionKey”: “={{ $now.toMillis() }}”
},
“type”: “@n8n/n8n-nodes-langchain.memoryBufferWindow”,
“typeVersion”: 1.3,
“position”: [
540,
160
],
“id”: “59d1d36b-d138-4d92-b9c5-a4b27a78266f”,
“name”: “Simple Memory”
},
{
“parameters”: {
“name”: “RWA_Summaries”,
“description”: “Data contains summarizes articles of tokenizaed Real World Assets.”
},
“type”: “@n8n/n8n-nodes-langchain.toolVectorStore”,
“typeVersion”: 1,
“position”: [
720,
160
],
“id”: “998dea17-d3ec-4102-a202-aabf8bc241d6”,
“name”: “Answer questions with a vector store”,
“notes”: “text”
},
{
“parameters”: {
“model”: {
“__rl”: true,
“mode”: “list”,
“value”: “gpt-4o-mini”
},
“options”: {}
},
“type”: “@n8n/n8n-nodes-langchain.lmChatOpenAi”,
“typeVersion”: 1.2,
“position”: [
860,
340
],
“id”: “1de448f7-d880-402a-9729-3a0a3c907f97”,
“name”: “OpenAI Chat Model1”,
“credentials”: {
“openAiApi”: {
“id”: “6cyuSPvF5pfESilM”,
“name”: “OpenAi account”
}
}
},
{
“parameters”: {
“qdrantCollection”: {
“__rl”: true,
“value”: “RWA_DB”,
“mode”: “list”,
“cachedResultName”: “RWA_DB”
},
“options”: {}
},
“type”: “@n8n/n8n-nodes-langchain.vectorStoreQdrant”,
“typeVersion”: 1.1,
“position”: [
520,
340
],
“id”: “b2d7ff8c-2538-46eb-a6ad-6fdea65fc12f”,
“name”: “Qdrant Vector Store”,
“credentials”: {
“qdrantApi”: {
“id”: “c7Ag9KRfexx6ESE1”,
“name”: “QdrantApi account”
}
},
“notes”: “text”
},
{
“parameters”: {
“model”: “text-embedding-ada-002”,
“options”: {}
},
“type”: “@n8n/n8n-nodes-langchain.embeddingsOpenAi”,
“typeVersion”: 1.2,
“position”: [
420,
520
],
“id”: “d3218baa-4caf-430a-be63-b1cf469b8476”,
“name”: “Embeddings OpenAI1”,
“credentials”: {
“openAiApi”: {
“id”: “6cyuSPvF5pfESilM”,
“name”: “OpenAi account”
}
}
}
],
“pinData”: {
“Google Sheets Trigger”: [
{
“json”: {
“Question”: “Summarize BlackRock’s role in Real World Asset tokenization”,
“Answer”: “”
}
}
]
},
“connections”: {
“Google Sheets Trigger”: {
“main”: [
[
{
“node”: “AI Prompt”,
“type”: “main”,
“index”: 0
}
]
]
},
“AI Prompt”: {
“main”: [
[
{
“node”: “AI Agent”,
“type”: “main”,
“index”: 0
}
]
]
},
“OpenAI Chat Model”: {
“ai_languageModel”: [
[
{
“node”: “AI Agent”,
“type”: “ai_languageModel”,
“index”: 0
}
]
]
},
“Simple Memory”: {
“ai_memory”: [
[
{
“node”: “AI Agent”,
“type”: “ai_memory”,
“index”: 0
}
]
]
},
“Answer questions with a vector store”: {
“ai_tool”: [
[
{
“node”: “AI Agent”,
“type”: “ai_tool”,
“index”: 0
}
]
]
},
“OpenAI Chat Model1”: {
“ai_languageModel”: [
[
{
“node”: “Answer questions with a vector store”,
“type”: “ai_languageModel”,
“index”: 0
}
]
]
},
“Qdrant Vector Store”: {
“ai_vectorStore”: [
[
{
“node”: “Answer questions with a vector store”,
“type”: “ai_vectorStore”,
“index”: 0
}
]
]
},
“Embeddings OpenAI1”: {
“ai_embedding”: [
[
{
“node”: “Qdrant Vector Store”,
“type”: “ai_embedding”,
“index”: 0
}
]
]
}
},
“active”: false,
“settings”: {
“executionOrder”: “v1”
},
“versionId”: “b0a45fa0-e01c-4110-bcee-7fe880e45c2c”,
“meta”: {
“templateCredsSetupCompleted”: true,
“instanceId”: “13f99051d0e89dfe60d6c923fffd068e764ed2715354cb529f8ad91a32faa19a”
},
“id”: “6cCIqvYFu8bybRBc”,
“tags”:
}
- n8n version: 1.86.0 → Cloud
- Database: qdrant Cloud:
- n8n EXECUTIONS_PROCESS setting (default: own, main):
- Running n8n via (Docker, npm, n8n cloud, desktop app): Cloud
- Operating system: Windows