We are thrilled to introduce the Public Preview of built-in actions for document parsing and chunking in Logic Apps Standard, designed to streamline RAG-based ingestion for Generative AI applications. With these out-of-the-box operations, you can now easily ingest documents or files, including both structured and unstructured data, into AI Search without writing or managing any code!
Leverage the new support for templates based on RAG patterns to ingest documents from a variety of sources such as REST endpoints, Blobs, SharePoint, OneDrive, and more. Our new Data Operations actions, "Parse a document" and "Chunk text," transform content from formats like PDF, CSV, and Excel into tokenized strings and split them into manageable chunks based on the number of tokens. This functionality is perfect for ensuring compatibility with Azure AI Search and Azure OpenAI, which require tokenized input and have token limits.
Simplify your workflows and enhance your AI-powered applications with this powerful, low-code solution!
Read documentation here.