How can all the information from a PDF, including text, tables, and images, be saved to a vector database, such as supabase vector, so that all data can be read in the future without exception?
Help me find a suitable template.
To save all information from a PDF, including text, tables, and images, to a vector database like Supabase, you can use a combination of OCR (Optical Character Recognition) for text and tables, and embeddings for images. Check out the “[Build a PDF Search System with Mistral OCR and Weaviate DB](Build a PDF search system with Mistral OCR and Weaviate DB | n8n workflow template)” template on n8n, which uses Mistral OCR for text extraction and Weaviate for vector storage. You can adapt this workflow to use Supabase instead of Weaviate by modifying the vector storage node.