Incorrect field name for qdrant query

[Nicola_Plain]

Workflow: n8n.io - Workflow Automation

Issue: failing to provide the correct field name to query qdrant vector store.
Is there a defalt vector_name used?

Error
{
“errorMessage”: “Bad Request”,
“errorDetails”: {},
“n8nDetails”: {
“n8nVersion”: “1.82.3 (Cloud)”,
“binaryDataMode”: “filesystem”,
“stackTrace”: [
“Error: Bad Request”,
" at Object.fun [as searchPoints] (/usr/local/lib/node_modules/n8n/node_modules/@qdrant/openapi-typescript-fetch/dist/cjs/fetcher.js:172:23)“,
" at processTicksAndRejections (node:internal/process/task_queues:95:5)”,
" at QdrantClient.search (/usr/local/lib/node_modules/n8n/node_modules/@qdrant/js-client-rest/dist/cjs/qdrant-client.js:155:26)“,
" at ExtendedQdrantVectorStore.similaritySearchVectorWithScore (/usr/local/lib/node_modules/n8n/node_modules/@langchain/qdrant/dist/vectorstores.cjs:168:25)”,
" at ExecuteContext.execute (/usr/local/lib/node_modules/n8n/node_modules/n8n/n8n-nodes-langchain/dist/nodes/vector_store/shared/createVectorStoreNode.js:247:34)“,
" at WorkflowExecute.runNode (/usr/local/lib/node_modules/n8n/node_modules/n8n-core/dist/execution-engine/workflow-execute.js:687:27)”,
" at /usr/local/lib/node_modules/n8n/node_modules/n8n-core/dist/execution-engine/workflow-execute.js:919:51",
" at /usr/local/lib/node_modules/n8n/node_modules/n8n-core/dist/execution-engine/workflow-execute.js:1252:20"
]
}
}

Describe the problem/error/question

What is the error message (if any)?

Please share your workflow

(Select the nodes on your canvas and use the keyboard shortcuts CMD+C/CTRL+C and CMD+V/CTRL+V to copy and paste the workflow.)

Share the output returned by the last node

Information on your n8n setup

• n8n version:
• Database (default: SQLite):
• n8n EXECUTIONS_PROCESS setting (default: own, main):
• Running n8n via (Docker, npm, n8n cloud, desktop app):
• Operating system:

[Dandy_Dow]

Hey Nicola,

Looks like you’re almost there, but Qdrant is being picky with the field naming during the vector search.

There’s no default field like vector_name that Qdrant expects — instead, it depends on how you created your collection and what you named your vector field** during the initial upload.

By default, when using Qdrant directly (or via LangChain), the vector field is often named "vector" — unless you set a custom name like "embedding" or something else during collection setup.

Try this:

Check what vector name was defined when the collection was created. Then, in your query payload, you’ll need to match that exact name in the vector_name or vector_field parameter (depending on the SDK you’re using — looks like this one uses LangChain’s wrapper).

If you’re unsure, and you’re using the n8n Qdrant integration:

• Open the collection config in Qdrant (via API or UI)
• Look for the actual vector field name (e.g. vector, embedding, text_vector, etc.)
• Plug that into your node or LangChain config.

Let me know what your collection setup looks like and I can help tweak the query.