[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"blog:index::RAG":3},{"page":4,"tags":23},{"items":5,"meta":18},[6],{"id":7,"slug":8,"title":9,"excerpt":10,"tags":11,"read_minutes":16,"published_at":17},"2c6ce459-fe9d-4d84-97d3-3c489e051dd5","data-engineering-for-llms-rag-pipelines","Data Engineering for LLMs: Building Production RAG Pipelines","Every organization is bolting AI onto its products; few have infrastructure to feed enterprise data into models reliably. Parsing, chunking, metadata, and vector databases — the new ETL.",[12,13,14,15],"AI","RAG","LLM","Data Engineering",8,"2026-07-01T00:00:00Z",{"has_more":19,"limit":20,"next_offset":21,"offset":22,"total":21},false,24,1,0,[24,27,29,30,32,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,72,74,76,77,79,81,83,85,87],{"tag":25,"count":26},"Architecture",4,{"tag":12,"count":28},3,{"tag":15,"count":28},{"tag":31,"count":28},"dbt",{"tag":33,"count":34},"Airflow",2,{"tag":36,"count":21},"Analytics",{"tag":38,"count":21},"Apache Iceberg",{"tag":40,"count":21},"BigQuery",{"tag":42,"count":21},"Careers",{"tag":44,"count":21},"Cloudflare R2",{"tag":46,"count":21},"Cost",{"tag":48,"count":21},"Databricks",{"tag":50,"count":21},"Data Governance",{"tag":52,"count":21},"Data Lake",{"tag":54,"count":21},"Data Quality",{"tag":56,"count":21},"DuckDB",{"tag":58,"count":21},"FinOps",{"tag":60,"count":21},"Flink",{"tag":62,"count":21},"Go",{"tag":64,"count":21},"HLS",{"tag":66,"count":21},"Kafka",{"tag":68,"count":21},"Lakehouse",{"tag":70,"count":21},"Learning",{"tag":14,"count":21},{"tag":73,"count":21},"pgvector",{"tag":75,"count":21},"PostgreSQL",{"tag":13,"count":21},{"tag":78,"count":21},"RBAC",{"tag":80,"count":21},"SkillUp",{"tag":82,"count":21},"Snowflake",{"tag":84,"count":21},"Streaming",{"tag":86,"count":21},"Superset",{"tag":88,"count":21},"Video"]