AI & researchDocument Default Data LoaderEmbeddings Open AiFtpManual TriggerLoop Over Items

Qdrant Vector Database Embedding Pipeline

Configured with Document Default Data Loader, Embeddings Open Ai, Ftp, Loop Over Items, and additional nodes. Review the connections and setup before adapting this template.

Download workflow JSON View files on GitHub ↗8 nodes · MIT

Workflow preview

Node categories in this workflow

Data store
Trigger
AI & models
Files / media
Transform
Routing

Icons describe general node roles, inferred from node types. Inspect the parameters for the configured action.

Drag to pan; use + and − to zoom. Reconstructed from the exported node positions; nothing runs here. Dashed lines represent non-main connections. Full node names and notes appear below.

How it works

The exported workflow contains the following configured nodes. Their connections are shown above; inspect the JSON for the complete logic, expressions, and external actions.

Workflow node names, types, and operations
Node	Category	Type	Operation
Qdrant Vector Store	Data store	Vector Store Qdrant	See node parameters
When clicking ‘Test workflow’	Trigger	Manual Trigger	See node parameters
Embeddings OpenAI	AI & models	Embeddings Open Ai	See node parameters
Default Data Loader	Files / media	Document Default Data Loader	See node parameters
Character Text Splitter	Transform	Text Splitter Character Text Splitter	See node parameters
List all the files	Files / media	Ftp	list
Loop over one item	Routing	Loop Over Items	See node parameters
Downloading item	Files / media	Ftp	See node parameters

Setup

Download the JSON and import it into an isolated n8n instance. Leave the workflow inactive.
Connect your own credentials through n8n’s credential store. Replace REPLACE_WITH_* values with your resource identifiers.
Inspect API destinations, Code nodes, database queries, file paths, and outbound actions.
Run with synthetic data and harmless destinations. Enable triggers only after checking the actual outputs.

Requirements

An n8n instance with the listed node types and compatible versions. Service-connected workflows may require accounts, credentials, or paid APIs.

Credential types declared in the source

ftp
openAiApi
qdrantApi

Workflow notes

Fetch JSON File List

Node: FTP (all files) Operation: List Path:

Recursively lists all .json files prepared for embedding.

Iterate Over Files

Node: Loop Over Items

Batches each file path individually for processing.

Download Each File

Node: FTP (1 file download)

Downloads the current file in binary form using:

Path = file_path/{{ $json.name }}

Parse JSON Document (Default Data Loader)

Node: Default Data Loader Loader Type: binary

Converts JSON structure into a document format compatible with embedding.

Split into Smaller Chunks

Node: Character Text Splitter Split by: "chunk_id" or custom logic based on chunk formatting

Optional node if chunk size normalization is required before embedding.

Store in Vector DB

Node: Qdrant Vector Store Batch Size: 100

Collection: <collection_name> Sends cleaned text chunks to OpenAI to get embeddings (1536 dim for text-embedding-ada-002)

collection settings in Qdrant cluster

PUT /collections/{collection_name}
{
    "vectors": {
      "size": 1536,
      "distance": "Cosine"
    }
}

Embed Chunks Node: Embeddings OpenAI Pushes the embedded chunks (with metadata) into Qdrant for semantic retrieval.

Qdrant Vector Database Embedding Pipeline

Purpose and structure

This folder contains the Qdrant Vector Database Embedding Pipeline workflow. Its executable nodes use documentDefaultDataLoader, embeddingsOpenAi, ftp, manualTrigger, splitInBatches, textSplitterCharacterTextSplitter, vectorStoreQdrant. The table and connection map below are derived from the JSON, not an inferred guarantee of behavior.

Setup

Import inactive. Configure your own credentials and replace REPLACE_WITH_* values. Review external destinations and Code nodes before running.

Entry points

When clicking ‘Test workflow’

Verification

Sanitized source candidate; not runtime-tested. This overview is generated from node metadata. Read the folder README for the connection map, credential types, and license.

Attribution

https://github.com/Zie619/n8n-workflows/blob/94007c1445d9258a7da116646b79473e7c7c3282/workflows/Manual/1776_Manual_Ftp_Automation_Triggered.json MIT; preserve source notices.

More in AI & research

"Hey Siri, Ask Agent" workflow #️⃣Nostr #damus AI Powered Reporting + Gmail + Telegram (G) - Email Classification