Ingest local files to a qdrant vector DB to build a RAG baseline for chat ui in second step

[dansah]

hey folks,

I’m currently trying to get some data from a local folder on the n8n server into a vector DB. I’m using the qdrant vector db, running locally on my machine, using Ollama hosted embeddings model. I somehow can’t get the data from the read/write files from disk node to the qdrant vector node. The data folder currently only consists of 3 CSV files but it should also be able to handle pdf, doc, whatsoever in the future.

here’s the current flow:

Simple document ingestion

I have a TERRIBLY low success rate doing what should be a basic workflow - ingesting my existing documents (PDFs, DOCXs, RTFs, etc) into a Vector store, so I can later query and chat against this data source. Nothing seems to work, certainly not with any reliably to make continued use of this platform worthwhile. I am asking as last resort if I am doing this wrong, or need some extra steps? Else I will move on from this project. I have copied / tried / tested MANY existing workflows. There is …

I also shared another post here from someone who had issues with a similar setup. I somehow am not able to get the data into the db. When triggering the chat in a second step, he can’t see the data that I tried to ingest in this stage.

Here the second stage:

Hope someone can help me to explain how to move forward with this issue.