This n8n workflow automates the process of researching, extracting, and documenting API schemas from multiple online sources. It begins with a manual trigger and proceeds through several stages: researching API documentation using web scraping and language models (Google Gemini), extracting API operations from documents, and generating custom API schemas. The workflow also involves storing data in Google Sheets, uploading schemas to Google Drive, and updating entries as the process progresses. It integrates with services like Apify for web scraping, Google Sheets for data management, Google Drive for storage, and LangChain-powered language models for content analysis and extraction. Practical use cases include API documentation automation for developers, consolidating insights from multiple sources, and streamlining API onboarding or auditing processes.

Node Count

>20 Nodes

Nodes Used

@n8n/n8n-nodes-langchain.documentDefaultDataLoader, @n8n/n8n-nodes-langchain.embeddingsGoogleGemini, @n8n/n8n-nodes-langchain.informationExtractor, @n8n/n8n-nodes-langchain.lmChatGoogleGemini, @n8n/n8n-nodes-langchain.textClassifier, @n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter, @n8n/n8n-nodes-langchain.vectorStoreQdrant, aggregate, code, executeWorkflow, executeWorkflowTrigger, executionData, filter, googleDrive, googleSheets, httpRequest, if, manualTrigger, removeDuplicates, set, splitInBatches, splitOut, stickyNote, switch, wait