# About dat ### What is dat (data activation tool)? Moving generative AI applications to production often requires using Vector stores to provide them with relevant context. Keeping these vector stores up-to-date with changes in your data is critical for the continued performance of these applications. dat makes this possible by setting up pipelines to update your vector stores as your source data changes. ![About Dat](/files/qMa7mG3GC3UCsadcV9oi) dat is an open source ETL platform that: * Ingests diverse data from a variety of sources i.e. unstructured data (such as text files/ emails/ social media posts etc.), semi-structured data (XML, JSON etc) as well as structured data (spreadsheets/ tables etc.). * Uses pre-existing models to create embeddings. * Stores the embeddings in a vector database. \ This involves processing the input text documents by using a generator to convert them into vector embeddings and storing these embeddings and their metadata in the specified vector database. This is an important prerequisite for leveraging Large Language Models(LLMs) in delivering a variety of use cases from semantic search to conversational user interfaces such as chatbots. --- # Agent Instructions: 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: ``` GET https://docs.dat-hub.com/overview/about-dat.md?ask= ``` The question should be specific, self-contained, and written in natural language. 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.