Curated

(5/5)

API Schema Extractor

Stage 1 - Research for API Documentation - Fetch a list of services pending research from Database (Google Sheet) - Uses a search engine (Google) to find API Documentation for each service - Uses Webscraper (Apify) to read the contents of search results to filter irrelevant pages - Stores webpage contents and metadata into Vector Store (Qdrant)

Integrations Used (12)

HTTP Request

Textsplitterrecursivecharactertextsplitter

Documentdefaultdataloader

Executeworkflow

Executiondata

Lmchatgooglegemini

Embeddingsgooglegemini

Workflow Structure (82 nodes)

100%

Manual Trigger

When clicking ‘Test workflow’

Google Sheets

Get All Research

All Research Done?

Split In Batches

For Each Research...

Google Sheets

Research Pending

Set

Research Event

Execute Workflow

Research

Google Sheets

Research Result

Google Sheets

Research Error

Google Sheets

Get All Extract

Wait

All Extract Done?

Split In Batches

For Each Extract...

Google Sheets

Extract Pending

Set

Extract Event

Execute Workflow

Extract

Google Sheets

Extract Result

Google Sheets

Extract Error

Google Sheets

Get All Generate

Wait

Wait1

All Generate Done?

Split In Batches

For Each Generate...

Google Sheets

Generate Pending

Set

Generate Event

Execute Workflow

Generate

Google Sheets

Generate Error

Google Sheets

Generate Result

Wait

Wait2

Execute Workflow Trigger

Execution Data

Switch

EventRouter

Http Request

Web Search For API Schema

Set

Query Templates

Google Sheets

Get API Operations

Has Results?

Split Out

Template to List

Code

Contruct JSON Schema

Split Out

Results to List

Set

Response Empty

Split In Batches

For Each Template...

Set

Set Upload Fields

Filter

Filter Results

Google Drive

Upload to Drive

Langchain.embeddings Google Gemini

Embeddings Google Gemini1

Langchain.vector Store Qdrant

Search in Relevant Docs

Langchain.lm Chat Google Gemini

Google Gemini Chat Model2

Langchain.information Extractor

Identify Service Products

Remove Duplicates

Remove Dupes

Set

Response OK2

Http Request

Scrape Webpage Contents

Aggregate

Combine Docs

Filter

Successful Runs

Set

Query & Docs

Set

Extract API Templates

Has Results?1

Split In Batches

For Each Template...1

Langchain.lm Chat Google Gemini

Google Gemini Chat Model

Langchain.text Classifier

Has API Documentation?

Set

Response Scrape Error

Langchain.lm Chat Google Gemini

Google Gemini Chat Model1

Langchain.information Extractor

Extract API Operations

Langchain.embeddings Google Gemini

Embeddings Google Gemini2

Langchain.vector Store Qdrant

Search in Relevant Docs1

Has Results?3

Aggregate

Combine Docs1

Code

Merge Lists

Set

Set Embedding Variables

Set

Response No API Docs

Set

Query & Docs1

Has Operations?

Split In Batches

For Each Document...

Remove Duplicates

Set

Response Empty1

Set

Content Chunking @ 50k Chars

Set

Response OK

Google Sheets

Append Row

Split Out

Split Out Chunks

Set

Response OK1

Langchain.embeddings Google Gemini

Embeddings Google Gemini

Langchain.vector Store Qdrant

Store Document Embeddings

Langchain.text Splitter Recursive Character Text Splitter

Recursive Character Text Splitter1

Langchain.document Default Data Loader

Default Data Loader

Node Types:

trigger

http

logic

transform

default

action

code

Requires credentials

Prerequisites

Required Credentials (1)

Google Sheets

Used by: Get All Research

Docs

Complexity

Advanced

Expert level. Custom code, complex logic, many integrations.

Setup time: ~40 min

Score: 80/100

Custom Code

Conditional Logic

Loops

10 Integrations

When to Use This Workflow

Automated Reporting

Automatically collect and organize data into spreadsheets for analysis.

Spend less time on data entry and more time on insights.

Real-time Response

React instantly when events happen - new orders, form submissions, or API calls.

Zero delay between trigger and action for time-sensitive workflows.

Error Reduction

Eliminate human error from routine processes with consistent automation.

Improve accuracy and reliability across your workflows.

workflow.json

{
  "nodes": [
    {
      "id": "2498bb93-176f-458c-acee-f541859df770",
      "name": "When clicking ‘Test workflow’",
      "type": "n8n-nodes-base.manualTrigger",
      "position": [
        2460,
        2820
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "c08bcf84-9336-44f9-b452-0c9469f18f48",
      "name": "Web Search For API Schema",
      "type": "n8n-nodes-base.httpRequest",
      "onError": "continueRegularOutput",
      "position": [
        3100,
...