What Document Formats Can DocForma Read?
DocForma features a versatile data-ingestion engine designed to process a wide range of document types, web content, and digital file formats without requiring manual file conversions. Compatibility varies slightly depending on which tool you are deploying in your workspace.
Supported Text & E-Reading Formats
The core DocForma Summarizer, Assistant, and writing tools effortlessly parse, index, and segment the following file formats:
- PDF Files (.pdf): Ingests native digital text files, unstructured layouts, and multi-page documents.
- Word Documents (.doc, .docx): Supports direct parsing of standard Microsoft Word text and files.
- Plain Text (.txt): Accepts lightweight plain text uploads and raw copy-pasted blocks.
- DRM-Free eBooks (.epub, .mobi): Reads electronic publications and books that do not carry Digital Rights Management protection.
- HTML Web Pages: Scrapes and summarizes textual content directly from live public internet URLs and website links.
Supported Image & OCR Formats (Xpound)
As a multimodal AI agent, Xpound accepts standard image inputs alongside traditional text and Word files. This allows you to pull text context, data, or source layouts directly out of visual files:
- Image Formats (.png, .jpg, .jpeg): Extracts raw text strings and layout structures directly from screenshots, digital scans, and mobile photos using background text recognition.
Future Compatibility Roadmap
Codicopia LLC is committed to continuously expanding DocForma's document processing boundaries. Upcoming platform updates will introduce native, seamless parsing support for Microsoft PowerPoint presentations (.ppt, .pptx), allowing you to slide-summarize and extract presentation bullet points instantly.
