> ## Documentation Index > Fetch the complete documentation index at: https://sensible.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # SenseML to spreadsheet reference ### Introduction If you're trying to convert a document, such as a PDF, into an Excel file, you often find tools that copy the document's visual layout into a spreadsheet, with no meaningful relationship between the extracted text and the underlying cells. In contrast, Sensible converts document tables, checkboxes, paragraphs, and even complex repeating section layouts into meaningfully labeled column/row pairs and linked sheets. For a list of document file types that Sensible can extract data from, see [Supported file types](/senseml-reference/concepts/file-types). This topic describes the rules Sensible uses to: * convert data extracted from one document, such as a PDF, into an Excel spreadsheet or CSV file. * combine data extracted from multiple documents into one spreadsheet Sensible extracts the data as JSON using a SenseML configuration, then applies the rules to create spreadsheet data such as tables, labeled columns, and linked sheets. ### Prerequisites To get a document's data into a spreadsheet, you must first: * Configure extractions for a document type, either by authoring an extraction configuration using Sensible, or by using Sensible's [open-source configuration library](https://app.sensible.so/library) for common document types. * Run an extraction on a target document that's in your configured document type ## CSV files To generate CSV files, Sensible uses the same rules described in the following sections, except that Sensible uses blank rows instead of tabbed sheets to separate extraction content. ## Multi-document spreadsheet Sensible combines multiple document extractions into one spreadsheet when: * You extract from a [portfolio](/layout-based-extractions/portfolio) document. * You input multiple extractions to the Generate Excel [method](/integrations/sdk-guides) or [endpoint](/api-reference/extraction/get-excel-from-documents/get-excel-extraction). To combine extractions, Sensible uses the same rules described in the following single-document spreadsheet rules. Sensible uses the following additional rules: * For all sheets other than the `` sheet, Sensible creates a new sheet for each document, and prefixes each sheet name with a zero-indexed document number, for example `doc_0` or `doc_1`. * For the ``sheet, Sensible appends data for each document in a new row. For each field ID, Sensible appends data under the same column if it finds a matching field ID from another extraction in your call to the Generate Excel method or endpoint, or under a new column if it doesn't find an matching field ID. * For portfolio extractions, Sensible adds metadata to the `` sheet, for example, the page range of the document in the portfolio. **Tips** * To avoid manually merging the similarly named columns, Sensible recommends using the same IDs for corresponding fields across different SenseML configs in a document type. For example, if document A outputs fields `car_model` and `car_year`, and document B outputs `car_model` and `manufacture_year`, Sensible creates a spreadsheet like the following: