> ## Documentation Index > Fetch the complete documentation index at: https://docs.merchantops.ai/llms.txt > Use this file to discover all available pages before exploring further. # The Lakehouse > A shared knowledge base of product, technology, and document data that enrichment draws on. The Lakehouse is a shared knowledge base that [enrichment](/enrichment/how-it-works) reads from when filling in your products. It holds structured product data, brand technologies, and the source documents those were extracted from. Enrichment consults the Lakehouse before scraping the open web, so data your organization has already contributed — or that is shared across organizations — can complete a product without another round trip to a brand site. The Lakehouse is a *source*, not a destination for your catalog: you don't add sellable [products](/catalog/products-variants) to it directly. You contribute to it by uploading documents, and it feeds enrichment. ## What the Lakehouse holds Structured product records pulled from uploaded documents — names, brands, and attributes. Enrichment matches these against your catalog products to fill in missing values. Named brand technologies and features (materials, cushioning systems, and the like), with the source document they came from. These enrich the products that reference them. The uploaded files — spec sheets, catalogs, and similar — that products and technologies are extracted from. Each document keeps a link back to what was derived from it. ## Documents and extraction You populate the Lakehouse by uploading documents. Extraction then reads each file and proposes the products and technologies it found. Upload one or more documents and tag them with the brand and category they describe. Each upload is tracked as a [Job](/jobs/overview). MerchantOps reads each document and extracts candidate products and technologies, each with a confidence score, running as a tracked Job. For spreadsheet documents, MerchantOps proposes how each column maps to a known field and shows you a preview. You confirm, adjust, or reject the mapping before the extracted data is accepted — a human-in-the-loop review step, distinct from the automatic column mapping used when [uploading products](/data-ingestion/uploading-products). Once approved, the extracted products and technologies become available to enrichment. Low-confidence extractions can be flagged for review. Documents themselves always belong to the organization that uploaded them. Whether the *data extracted* from them is shared more broadly is controlled by your sharing settings, below. ## Per-org sharing The Lakehouse can be shared across organizations, and what you share is configurable. By default, product and technology data is shared, while MAP pricing data is kept private. Changing a sharing setting affects **future** writes only — data already contributed keeps the sharing decision it was written with. Manage this at [Lakehouse sharing settings](/settings/lakehouse-sharing). How enrichment consults the Lakehouse before the open web. The pricing data the Lakehouse can hold, kept private by default. Choose what your organization shares into the Lakehouse. Adding sellable products to your catalog, as opposed to the Lakehouse.