A set of data processing elements connected in series, where the output of one element is the input of the next one.
Data Pipelines automate the extraction, transformation, and loading (ETL) of raw data into usable formats. In AI systems, they continuously ingest PDFs, remove PII, generate vector embeddings, and update the Vector Database, so the RAG system works from current enterprise knowledge.
See also Vector Database, Data Mobilization and Data Lakehouse.