# Supported Document Types Feathery Document Intelligence handles a variety of document and media types. ## PDFs Feathery leverages both the information directly embedded in the file as well as PDF metadata to return accurate information about the document. Make sure to set the `Uploaded File Type` field to `Documents or images`. [Document and Image Extractions](/platform/document-intelligence/supported-document-types/document-and-image-extractions.md) ## Images Feathery leverages computer vision and optical character analysis to analyze the context of the document. Make sure to set the `Uploaded File Type` field to `Documents or images`. [Document and Image Extractions](/platform/document-intelligence/supported-document-types/document-and-image-extractions.md) ## Word Docs Feathery leverages both the information directly embedded in the file as well as Word doc metadata to return accurate information about the document. Make sure to set the `Uploaded File Type` field to `Documents or images`. [Document and Image Extractions](/platform/document-intelligence/supported-document-types/document-and-image-extractions.md) ## CSVs and Spreadsheets Make sure to set the `Uploaded File Type` field to `CSVs or Spreadsheets`. Feathery AI can pull data from semantically relevant columns and specific cells as well. [Spreadsheet and CSV Extractions](/platform/document-intelligence/supported-document-types/spreadsheet-and-csv-extractions.md) ## Direct AI Queries Query Feathery AI directly with field data formatted into an open-ended prompt rather than read from a pre-defined medium. Set the `Uploaded File Type` field to `Free-Form Query`. [Free-form Extractions](/platform/document-intelligence/supported-document-types/free-form-extractions.md) ## Emails To have Feathery process emails directly, enable the inbox integration which will run on relevant email threads. Make sure to also toggle the relevant extraction queries that you would like to run on the email. If relevant data isn't found on the email for a given query, it will fall back to looking in the documents attached to the email thread. To extract from an email or document attached in an email, forward it to from a domain or email address enabled in the Integrations tab within the AI product.
## Voice Leverage Feathery's call integration or upload voice files directly into Feathery. Feathery extractions handle both the process of transcribing the audio and extracting semantically meaningful information out of the audio. ([Demo](https://www.loom.com/share/3247501459a543b584c74fbc58e1846c)) [Audio Extractions](/platform/document-intelligence/supported-document-types/audio-extractions.md) --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.feathery.io/platform/document-intelligence/supported-document-types.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.