fetch source image and split out results only and filter score 0 9
Configured with Edit Image, Elasticsearch, Filter, HTTP Request, and additional nodes. Review the connections and setup before adapting this template.
Node categories in this workflow
- Trigger
- Web / API
- Transform
- Routing
- Files / media
- Data store
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.
| Node | Category | Type | Operation |
|---|---|---|---|
| When clicking "Test workflow" | Trigger | Manual Trigger | See node parameters |
| Fetch Source Image | Web / API | HTTP Request | See node parameters |
| Split Out Results Only | Transform | Split Out | See node parameters |
| Filter Score >= 0.9 | Routing | Filter | See node parameters |
| Crop Object From Image | Files / media | Edit Image | crop |
| Set Variables | Transform | Edit Fields | See node parameters |
| Use Detr-Resnet-50 Object Classification | Web / API | HTTP Request | POST |
| Upload to Cloudinary | Web / API | HTTP Request | POST |
| Create Docs In Elasticsearch | Data store | Elasticsearch | create |
| Fetch Source Image Again | Web / API | HTTP Request | 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
cloudflareApielasticsearchApihttpQueryAuth
Workflow notes
1. Get Source Image
1. Get Source Image
Read more about setting variables for your workflow
For this demo, we'll manually define an image to process. In production however, this image can come from a variety of sources such as drives, webhooks and more.
2. Use Detr-Resnet-50 Object Classification
2. Use Detr-Resnet-50 Object Classification
Learn more about Cloudflare Workers AI
Not all AI workflows need an LLM! As in this example, we're using a non-LLM vision model to parse the source image and return what objects are contained within. The image search feature we're building will be based on the objects in the image making for a much more granular search via object association.
We'll use the Cloudflare Workers AI service which conveniently provides this model via API use.
3. Crop Objects Out of Source Image
3. Crop Objects Out of Source Image
Read more about Editing Images in n8n
With our objects identified by their bounding boxes, we can "cut" them out of the source image as separate images.
4. Index Object Images In ElasticSearch
4. Index Object Images In ElasticSearch
Read more about using ElasticSearch
By storing the newly created object images externally and indexing them in Elasticsearch, we now have a foundation for our Image Search service which queries by object association.
Sticky Note4
Fig 1. Result of Classification
Try It Out!
Try It Out!
This workflow does the following:
- Downloads an image
- Uses an object classification AI model to identify objects in the image.
- Crops the objects out from the original image into new image files.
- Indexes the image's object in an Elasticsearch Database to enable image search.
Need Help?
Join the Discord or ask in the Forum!
Happy Hacking!
Sticky Note5
🚨Required
- Set your variables here first!
fetch source image and split out results only and filter score 0 9
fetch source image and split out results only and filter score 0 9
Purpose and structure
This folder contains the fetch source image and split out results only and filter score 0 9 workflow. Its executable nodes use editImage, elasticsearch, filter, httpRequest, manualTrigger, set, splitOut. 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/Splitout/1425_Splitout_Elasticsearch_Create_Webhook.json MIT; preserve source notices.