Build a PDF search system with Mistral OCR and Weaviate DB
Ready for 3.0Ready for 3.0. This template uses no nodes that n8n 3.0 removes. No removed nodes, versions or helpers found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 10 nodes and runs when an MCP client calls one of its tools (plus 1 other trigger). Along the way it connects Embeddings Cohere, Reranker Cohere and Weaviate Vector Store.
How it runs
Trigger: When an MCP client calls one of its tools (plus 1 other trigger).
- Extract Text from PDF (Mistral AI): uses Mistral AI
- Prepare Document Data (Edit Fields (Set)): sets 4 fields: filename, content, source…
- Store in Vector Database (Weaviate Vector Store): stores documents in the Weaviate vector store, with embeddings: Cohere Embeddings; document loader: Document Loader
Services it uses
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 (9)
- Embeddings Cohere
@n8n/n8n-nodes-langchain.embeddingsCohere - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Reranker Cohere
@n8n/n8n-nodes-langchain.rerankerCohere - MCP Server Trigger
@n8n/n8n-nodes-langchain.mcpTrigger - Weaviate Vector Store
@n8n/n8n-nodes-langchain.vectorStoreWeaviate - Recursive Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter - n8n Form Trigger
n8n-nodes-base.formTrigger - Mistral AI
n8n-nodes-base.mistralAi - Edit Fields (Set)
n8n-nodes-base.set
From the author
Build a PDF to Vector RAG System: Mistral OCR, Weaviate Database and MCP Server A comprehensive RAG (Retrieval-Augmented Generation) workflow that transforms PDF documents into searchable vector embeddings using advanced AI technologies. 🚀 Features - PDF…