These features are in Research Preview. The provided summaries may display inaccurate information.
AI-Driven Document Summarization
This feature is available on all Platform plans.
Try out Egnyte’s new AI-based document summarization feature! It synthesizes the content using industry-leading large language models (LLMs), and is sensitive to the type of documents.
In order to create a document summary, please visit the new ‘Summary’ tab on the document preview pane. The summary will be synthesized and displayed in the tab.
Users can provide feedback on whether the summary is useful by using the thumbs-up/thumbs-down icons at the bottom of the summary pane.
The thumbs up/down icons will appear when you hover over the summary pane.
AI-Driven Document Q&A
Document Q&A (aka ‘Ask’) feature allows the users to ask questions about a document, using either a chatbot-style interface, or from a list of suggested questions. The answers are synthesized using industry-leading large language models (LLMs).
For users that have access to this feature, both the summarization and the Q&A are combined into a single Ask tab. In order to utilize this feature, click on the Ask tab in the document preview pane.
At this point, the users can click on the displayed buttons to generate a summary of the document, or view suggested questions. The user can also type their own questions in the chat box at the bottom.
Users can provide feedback on whether the answers are helpful by clicking on the thumbs-up/thumbs-down icons.
Frequently Asked Questions
Is Data Confidentiality Assured while Generating AI-Driven Summaries?
Egnyte remains committed to the confidentiality of your data. Your inputs, summaries, and your
- Are not available to other customers,
- Are not used to improve third-party models, or any third-party products or services,
- Are not stored by third-party models
- Are not accessible by or visible to Egnyte employees
In addition, all generated summaries can only be accessed by users on your domain that have permissions to view the original documents.
Can I Opt-Out of these AI features?
Yes. An admin user can turn off these features by navigating to the ‘Settings -> Configuration’ page and then setting the ‘AI-Powered features’ toggle to 'disabled'.
Turning the toggle off will turn off both the Document Summarization as well as the Document Q&A features (if available in your plan and on your domain). It is not possible to enable/disable individual features.
What Types of Files Can Be Summarized by this Feature?
Any file where we can extract text from the file, can be summarized. This includes text documents, presentations, spreadsheets, PDF files, audio/video files, BIM files (with Specialized File Handler add-on), etc.
Can I Exclude Some Documents from Being Summarized?
No. The summarization feature will summarize all files when enabled. Individual files can not be excluded from summarization.
What Types of Files Can Be Summarized and Can Be Used for the Q&A Feature?
Any file where we can extract text from the file, can be summarized, and can also be used for Q&A. This includes text documents, presentations, spreadsheets, PDF files, audio/video files, BIM files (with Specialized File Handler add-on), etc.
Can I Exclude Some Documents from AI-Powered Summarization and Q&A?
No, the features will affect all files when enabled. Individual files can not be excluded.
Can I Provide Feedback on these Features?
Yes, provide feedback on whether the summary or the answers are useful by using the thumbs-up/thumbs-down icons.
In the summary tab, note that the thumbs up/down icons will appear when you hover over the summary pane.
Do the Users Have Any Control Over the Length/Type/Format of the Summary that is Created?
Not at this time. We are looking at adding additional configuration tools for the users.
Are there any document size limitations for creating summaries?
The AI only considers the first 12000 characters [~1700 to 3000 words] in the document to generate the summary.
Will the Summary always generate the same responses?
Responses are cached and reused. However, the cache can expire and there is a possibility that the generated responses have some variation
Are the generated summaries always accurate?
Like any AI feature, AI driven summary is not perfect. It can sometimes generate responses that are incorrect, or misleading. It's important to fact-check information and not rely solely on the responses for critical decisions.
How are the Summaries and Answers Stored, And Who Has Access To Them?
Summaries are cached in-memory for performance and are only visible to users who have permission to view the underlying file.