This workflow automates the process of ingesting PDF documents into a semantic database using n8n. It begins with a webhook trigger for file uploads, where users submit PDF files through a form. The workflow then extracts document data, generates embeddings via Ollama, and stores the information in a Qdrant vector database. Additionally, it integrates a MCP Server trigger for advanced retrieval and interaction. This setup enables seamless, automated management of large document sets, ideal for knowledge management, AI-powered search, or content-driven applications.
Automated Document Ingestion for Semantic Search
| Node Count | 6 – 10 Nodes |
|---|---|
| Nodes Used | @n8n/n8n-nodes-langchain.documentDefaultDataLoader, @n8n/n8n-nodes-langchain.embeddingsOllama, @n8n/n8n-nodes-langchain.mcpTrigger, @n8n/n8n-nodes-langchain.vectorStoreQdrant, formTrigger, stickyNote |
Be the first to review “Automated Document Ingestion for Semantic Search”
Reviews
There are no reviews yet.