# Build hybrid RAG search over PDFs with Qdrant and Ollama: n8n workflow

> Started by someone opening a chat with it, and works across Qdrant. 20 steps, 1 branch: a working afternoon to understand properly.

Source: https://millionrounds.com/workflow/build-hybrid-rag-search-over-pdfs-with-qdrant-and-ollama (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [Integrations](https://millionrounds.com/workflows?category=Integrations#library)

# Build hybrid RAG search over PDFs with Qdrant and Ollama

Started by someone opening a chat with it, and works across Qdrant. 20 steps, 1 branch: a working afternoon to understand properly.

Medium Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fbuild-hybrid-rag-search-over-pdfs-with-qdrant-and-ollama)

**20 steps** Medium: a working afternoon

**1** Branch: places the flow splits

**0** Loops or waits

**1** Service it connects to

## The flow

Starts it 2 Model 4 Logic 6 Service 8

The steps in the order they run, from what starts it.

- 1 **When clicking ‘Execute workflow’** Manual trigger *Starts it*
- 2 **Embeddings Ollama** Embeddings Ollama *Model*
- 3 **Recursive Character Text Splitter** Text Splitter Recursive Character Text Splitter *Model*
- 4 **When chat message received** Chat trigger *Starts it*
- 5 **Extract sparse from Qdrant** Code *Logic*
- 6 **Read/Write Files from Disk** Read Write File *Service*
- 7 **Qdrant Vector Store** Vector Store Qdrant *Model*
- 8 **Default Data Loader** Document Default Data Loader *Model*
- 9 **Generate the embeddings of the query** Http Request *Service*
- 10 **Extract from File** Extract From File *Service*
- 11 **Get All Points** Qdrant *Service*
- 12 **Query Points (using the embeddings)** Qdrant *Service*
- 13 **Check If Collection Exists** Qdrant *Service*
- 14 **Merge** Merge *Logic*
- 15 **Split Out** Split Out *Logic*
- 16 **If** If *Logic*
- 17 **Edit Fields** Set *Logic*
- 18 **Create Collection** Qdrant *Service*
- 19 **Aggregate** Aggregate *Logic*
- 20 **Update Vectors** Qdrant *Service*

## How it's built

- **Starts on:** Someone opening a chat with it
- **Steps:** 20, with 1 branch
- **Size:** Medium: a working afternoon
- **Connects to:** Qdrant
- **Model:** None. This is plumbing, not judgement
- **Retrieval:** Answers are drawn from documents you supply, not from the model alone

## Questions

What does it need to run?

An n8n account, plus your own Qdrant account. You connect your own accounts after importing it; none are included.

What starts it?

It starts on someone opening a chat with it.

Does it use AI?

No. Every step is fixed logic or a call to a service, so it does the same thing every time.

How long does it take to set up?

Plan an afternoon. 20 steps is enough that you should read each one before running it.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

**Before you run it**

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 20 steps before you point it at anything that matters.

## Run it in n8n

- **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n)
- **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fbuild-hybrid-rag-search-over-pdfs-with-qdrant-and-ollama)
- **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts.

Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind.

## Connects to

Each opens the other workflows that use it.

[Qdrant](https://millionrounds.com/workflows?service=Qdrant#library)