> For the complete documentation index, see [llms.txt](https://mariadb.com/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://mariadb.com/docs/release-notes/ai-rag-release-notes/mariadb-ai-rag-1.0.0-release-notes.md). # MariaDB AI RAG 1.0.0 Release Notes The MariaDB AI RAG API is a tech preview of an enterprise-grade Retrieval-Augmented Generation (RAG) solution that provides a simple, configurable REST API for ingesting documents and retrieving information from them. It is designed to be used as a building block for larger AI RAG systems. As a REST API with controls around visibility of documents and chunks, with options for full pipeline orchestration, it simplifies the process of implementing a RAG system compared to approaches that require users to learn and implement the ingestion, chunking, and retrieval programmatically for each application separately. We plan to do multiple releases of this tech preview to continue to improve the system and incorporate feedback from users. ## Key Features * RAG API endpoints for document ingestion and chunking * User and document management endpoints * JWT authentication for API access * Support for multiple document formats (PDF, DOCX, TXT, CSV, XLSX) * MariaDB vector index integration for efficient document search * Retrieval options include semantic search, hybrid search, and fulltext search * Support for multiple retrieval and generation models (e.g. OpenAI, Cohere, etc.) * Support for key vaults to make configuration of sensitive information easier ## Packaging * RPM, DEB, and MSI installers for RHEL, Ubuntu, and Windows are provided ## Installation * Using the platform's installer file (.msi, .rpm, or .deb) run the installer * Then follow the installation instructions in the AI RAG API documentation --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://mariadb.com/docs/release-notes/ai-rag-release-notes/mariadb-ai-rag-1.0.0-release-notes.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.