Api schema extractor
Ready for 3.0What this workflow does
This AI workflow has 82 nodes and runs manually, when you click “Execute workflow” (plus 1 other trigger). Along the way it connects Google Gemini Chat Model, Embeddings Google Gemini, Qdrant Vector Store and Google Sheets and 1 more. It also calls api.apify.com over HTTP.
How it runs
Trigger: Manually, when you click “Execute workflow” (plus 1 other trigger).
- Get All Research (Google Sheets): uses Google Sheets
- Execution Data: uses Execution Data
- All Research Done? (If): checks a condition and branches into true / false
- EventRouter (Switch): routes items into 3 branches
- Get All Extract (Google Sheets): uses Google Sheets
- For Each Research... (Loop Over Items (Split in Batches)): loops over the items in batches
- Web Search For API Schema (HTTP Request): calls api.apify.com (POST)
- Query Templates (Edit Fields (Set)): sets 1 field: queries
- Get API Operations (Google Sheets): uses Google Sheets
- All Extract Done? (If): checks a condition and branches into true / false
…plus 62 more steps. See the full node list below.
Services it uses
HTTP calls to: api.apify.com
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (24)
- Manual Trigger
n8n-nodes-base.manualTrigger - HTTP Request
n8n-nodes-base.httpRequest - Split Out
n8n-nodes-base.splitOut - Recursive Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter - Edit Fields (Set)
n8n-nodes-base.set - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Execute Workflow Trigger
n8n-nodes-base.executeWorkflowTrigger - Execution Data
n8n-nodes-base.executionData - Switch
n8n-nodes-base.switch - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - Filter
n8n-nodes-base.filter - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - Embeddings Google Gemini
@n8n/n8n-nodes-langchain.embeddingsGoogleGemini - Text Classifier
@n8n/n8n-nodes-langchain.textClassifier - Qdrant Vector Store
@n8n/n8n-nodes-langchain.vectorStoreQdrant - Information Extractor
@n8n/n8n-nodes-langchain.informationExtractor - Wait
n8n-nodes-base.wait - Remove Duplicates
n8n-nodes-base.removeDuplicates - Execute Sub-workflow
n8n-nodes-base.executeWorkflow - If
n8n-nodes-base.if - Aggregate
n8n-nodes-base.aggregate - Code
n8n-nodes-base.code - Google Sheets
n8n-nodes-base.googleSheets - Google Drive
n8n-nodes-base.googleDrive
From the author
This workflow automates the process of discovering and extracting APIs from various services, followed by generating custom schemas. It works in three distinct stages: research, extraction, and schema generation, with each stage tracking progress in a Google…