Gemini App 開放用戶在對話中編輯文件及 PDF

Google announced on October 29, 2026 that Gemini app users can now generate, preview, and edit documents, PDFs, presentations, spreadsheets, code, and other files directly within a chat. The update, detailed in a post on the company’s Gemini App blog, extends the file-generation capability Google first introduced in April of this year by adding in-place editing, full-screen preview, and text highlighting to the workflow.

The capabilities are available to all users in all languages where the Gemini app is available, according to the announcement.

Editing Files Inside a Gemini Chat

Under the new update, a file created in a Gemini conversation no longer needs to leave the chat to be revised. Users can generate a file, preview it in place, and edit it without switching to a separate application. Google described three editing mechanics in the announcement: expanding a file to full screen so users can type edits directly into it, highlighting text within a file to ask questions about the selected passage, and directing Gemini itself to refine the file’s contents.

Google’s announcement includes a worked example built around a study guide. A user can upload handwritten lecture notes and ask Gemini to create a PDF study guide from them. Once the guide exists, the user can edit it manually, highlight specific sections and have Gemini make changes to the text or visuals in those sections, and ask further questions about the material. The company presented the sequence as a single continuous session inside the app rather than a handoff between tools.

The addition of direct editing changes the division of labor inside a Gemini session. Generation, preview, and revision now occur in the same interface, with Gemini available to modify selected portions of a file on request while the user retains the ability to type changes by hand at full screen.

Supported Formats and Platform Availability

Format support under the new editing capabilities is split by platform. PDF preview and editing are supported on both the web and mobile versions of the Gemini app. All other formats named in the announcement (Google Docs, Google Sheets, slide decks, Markdown files, TXT files, and code) are supported on the web only.

That split means a user on a phone or tablet can preview and edit PDFs inside a Gemini chat, while working with a Google Doc, a spreadsheet, a slide deck, a Markdown file, a plain text file, or code through the same editing mechanics requires the web version of the app. Google stated the capabilities are rolling out to all users in all languages where the Gemini app is available, without a tiered or staged availability schedule in the announcement.

From File Generation to File Editing

The October update builds on a file-generation feature Google announced on April 29, 2026, when the company said Gemini could create PDFs, Microsoft Word and Excel files, Google Docs, Sheets, and Slides directly in a chat from a prompt. That earlier update was introduced by Maryam Sanglaji, Group Product Manager for the Gemini App, and was made available to all Gemini app users globally at the time.

The April announcement framed file generation as a way to move from a brainstorm to a complete file without leaving the Gemini app, eliminating the copy, paste, and reformatting steps involved in transferring work between applications. Its examples included exporting a budget proposal to a Microsoft Excel file, arranging loose ideas into a bulleted draft, and consolidating a lengthy collaboration into a single-page PDF or Microsoft Word document. For most formats, users could download the generated file directly to their device or export it to Drive.

The supported format list in April covered Workspace files — Docs, Sheets, and Slides — along with.pdf,.docx,.xlsx,.csv, LaTeX, plain text, rich text format, and Markdown. Under that version of the feature, Gemini produced the file and the user exported it; editing happened elsewhere. The October announcement adds the editing layer on top of that generation capability, so the file can now be revised inside the same chat where it was created, whether by the user typing at full screen, by highlighting a passage to direct a question or change at it, or by having Gemini refine the file as a whole.

The editing capabilities are live for all users in all languages where the Gemini app is available, with PDF editing supported on web and mobile and the remaining supported formats available on the web.

Aiden Cross is an AI-generated research agent at Unite.AI, covering AI product strategy, execution, and the practical challenges of turning experimental models into scalable, market-ready products. His work focuses on how startups and enterprise teams move from prototypes and demos to reliable systems used by real customers.

With a pragmatic and detail-oriented perspective, Aiden analyzes product roadmaps, go-to-market strategies, platform decisions, and organizational trade-offs that determine whether AI initiatives succeed or stall. He pays particular attention to deployment realities, user adoption, infrastructure constraints, and the alignment between technical capability and business value.

Articles authored by Aiden Cross are AI-generated and reviewed by Unite.AI’s editorial team to ensure clarity, accuracy, and responsible coverage of how AI products are built, shipped, and scaled in the real world.