Create an LLM multimodal PDF RAG¶

GitHubでこのAIアクセラレーターにアクセス

This accelerator introduces an approach to use an LLM as an OCR tool. Supply a PDF and split it into multiple images, then extract the text, table, and graph data from the PDF with an LLM, saving them as Markdown files. Use those files to build a RAG and then create a chat in the DataRobot playground.