← Back to Glossary
Indexing Pipeline
The automated data ingestion flow that loads documents, splits them into chunks, embeds them, and uploads them to a database.
Why it exists
Raw PDFs or docs cannot be searched directly; they must be structured and vectorized automatically.
How it works
ETL pipeline steps: 1) Load file, 2) Clean & parse text, 3) Chunk with overlap, 4) Generate embeddings, 5) Batch upsert to vector store.
Related terms
Where you'll use this
roadmap