Document upsert timeout error in Qdrant

I can’t use the self-hosted Qdrant, it returns the ConnectTimeoutError error, but I use this same Qdrant with Flowise

Information on your n8n setup
n8n version: Version 1.36.4
Database: Postgress
Running n8n via: Docker
Operating system: Ubuntu

Error detail:
n8n version: 1.36.4 (Self Hosted)

Error cause:

{
    "name":"ConnectTimeoutError",
    "code":"UND_ERR_CONNECT_TIMEOUT",
    "message":"Connect Timeout Error"
}

stack trace:
TypeError: fetch failed 
    at Object.fetch (node:internal/deps/undici/undici:11731:11) 
    at processTicksAndRejections (node:internal/process/task_queues:95:5) 
    at fetchJson (/usr/local/lib/node_modules/ n8n/node_modules/@qdrant/openapi-typescript-fetch/dist/cjs/fetcher.js:135:22) 
    at /usr/local/lib/node_modules/n8n/node_modules/@qdrant/js-client-rest/dist/ cjs/api-client.js:46:26 
    at handler (/usr/local/lib/node_modules/n8n/node_modules/@qdrant/openapi-typescript-fetch/dist/cjs/fetcher.js:156:16) 
    at / usr/local/lib/node_modules/n8n/node_modules/@qdrant/js-client-rest/dist/cjs/api-client.js:32:24 
    at handler (/usr/local/lib/node_modules/n8n/node_modules/ @qdrant/openapi-typescript-fetch/dist/cjs/fetcher.js:156:16) 
    at fetchUrl (/usr/local/lib/node_modules/n8n/node_modules/@qdrant/openapi-typescript-fetch/dist/cjs/ fetcher.js:162:22) 
    at Object.fun [as getCollections] (/usr/local/lib/node_modules/n8n/node_modules/@qdrant/openapi-typescript-fetch/dist/cjs/fetcher.js:168:20 ) 
    at QdrantClient.getCollections (/usr/local/lib/node_modules/n8n/node_modules/@qdrant/js-client-rest/dist/cjs/qdrant-client.js:826:26) 
    at QdrantVectorStore.ensureCollection (/usr/ local/lib/node_modules/n8n/node_modules/@langchain/community/dist/vectorstores/qdrant.cjs:140:26) 
    at QdrantVectorStore.addVectors (/usr/local/lib/node_modules/n8n/node_modules/@langchain/community/ dist/vectorstores/qdrant.cjs:84:9) 
    at QdrantVectorStore.addDocuments (/usr/local/lib/node_modules/n8n/node_modules/@langchain/community/dist/vectorstores/qdrant.cjs:69:9) 
    at Function. fromDocuments (/usr/local/lib/node_modules/n8n/node_modules/@langchain/community/dist/vectorstores/qdrant.cjs:191:13) 
    at Object.populateVectorStore (/usr/local/lib/node_modules/n8n/node_modules/ @n8n/n8n-nodes-langchain/dist/nodes/vector_store/VectorStoreQdrant/VectorStoreQdrant.node.js:68:9) 
    at Object.execute (/usr/local/lib/node_modules/n8n/node_modules/@n8n/n8n- nodes-langchain/dist/nodes/vector_store/shared/createVectorStoreNode.js:174:21) 
    at Workflow.runNode (/usr/local/lib/node_modules/n8n/node_modules/n8n-workflow/dist/Workflow.js:728: 19) 
    at /usr/local/lib/node_modules/n8n/node_modules/n8n-core/dist/WorkflowExecute.js:660:53 
    at /usr/local/lib/node_modules/n8n/node_modules/n8n-core/dist/WorkflowExecute .js:1062:20

It looks like your topic is missing some important information. Could you provide the following if applicable.

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

Has anyone had this problem using self-hosted Qdrant?

What caught my attention is that with Flowise I can use it without any problems

Hey @Claudio_Balbino,

I’ve never used Flowise, but qdrand self-hosted via docker work fine for me

Do you mind share your workflow?:slight_smile:

Hi @Shirobachi

The model I’m using is similar to the one you shared

I don’t know if I missed any details in my installation, but the curious thing is that I can upsert documents using Flowise, but I can’t with n8n

Could you share the Qdrant docker compose you are using?

I see you use collection by ID, if you change it to list, is there anything?
If not, can you show credentials (without api), I have http://192.168.0.99:6333 maybe you have some lading slash or sth?

Even though the credential shows that the connection was tested successfully, nothing appears in the list

I’ve already tested without an API but I wasn’t successful either.

Can you connect from n8n to the address you mentioned using an HTTP node or something similar? You mentioned using a Docker instance; is it hosted locally or in the cloud? Can n8n access this address?

Currently, I’m outside my home network where Qdrant is set up, so I can’t test it myself. However, I believe the HTTP node should be able to connect to Qdrant via a simple GET request. If you’re experiencing a timeout, it’s likely that the address is unreachable. It would be useful to have your deployment configuration for further investigation.