· Updated
.docx, .pptx, .xlsx, .csv, .tsv, .txt, and code files - formats agents encounter constantly in real-world enterprise workflows. PDF support already existed; this closes the gap for the office document formats that make up the bulk of business data.The API handles each type differently: text is extracted from Word and PowerPoint files, while spreadsheets get a special augmentation flow optimized for structured data. One limitation: embedded charts and images in non-PDF files aren't extracted - convert to PDF first if you need visual fidelity.
This significantly reduces pre-processing overhead for document-heavy agents. Pass a .docx meeting summary or an .xlsx financial report directly in your API call and let the model pull context without an intermediate extraction step.
We expanded file input types so you can now pass docx, pptx, csv, xlsx, and more directly to the Responses API. Your agents can now pull context from real-world files and generate more accurate outputs. https://t.co/brKUsSfOJy https://t.co/no5zPgWgSv
More like this
OpenAIMar 15
GeminiApr 30
ClaudeMay 7
ElevenLabsMay 7