This workflow automates the process of uploading and indexing course module files from Google Drive into a Pinecone vector database, enabling efficient semantic search and retrieval. When a new file is added to a specified Google Drive folder, the workflow downloads the file, splits the content into manageable chunks, generates embeddings using OpenAI’s API, and stores the resulting vectors in Pinecone for future querying. The process is optimized for handling multiple files and ensures each step is systematically executed, making it ideal for educational content management or knowledge base building.
Automated Indexing of Course Files into Pinecone
Node Count | 11 – 20 Nodes |
---|---|
Nodes Used | @n8n/n8n-nodes-langchain.documentDefaultDataLoader, @n8n/n8n-nodes-langchain.embeddingsOpenAi, @n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter, @n8n/n8n-nodes-langchain.vectorStorePinecone, googleDrive, googleDriveTrigger, splitInBatches, stickyNote |
Reviews
There are no reviews yet.