File Upload
Overview
File Upload enables users to upload and analyze local files directly in Glean, Public Knowledge, and Apps. This feature allows users to query, summarize, and generate content from uploaded files. The upload limits vary based on the model used in your Glean instance.
File content and metadata are stored in the chat sessions of users and are retained while the chat session is present in the history.
Supported File Formats
Key Features
File Upload
Users can upload up to 5 files directly from their local computer, with each file having a maximum size of 64 MB.
Real-Time Querying
Query the text content of uploaded files immediately after upload for instant analysis.
Document Metadata
The chat UI displays document metadata including title and file type for easy reference.
File Management
File Deletion
Users can delete uploaded files before submitting their first query. After query submission, files can only be removed by deleting the chat session history.
Retention Policy
File content and metadata are retained while the chat session is present in history.
API Support
Developer platform customers can utilize our API for file uploads. Refer to our API documentation for details.
Security and Privacy
Security Features
- Files are parsed and scanned for malware before storage
- Malware-infected files trigger upload errors
Access Controls
- Uploaded files can only be downloaded by the original uploader or by users who have access to the associated shared chat session
- Files are not publicly accessible, even if the chat session was previously marked as public
Upload Limits
The maximum file size and number of files allowed per session depends on your model:
| Model | File Limit | Size Limit |
|---|---|---|
| 128K Models | 5 files | 64 MB |
| 32K Models | 4 files | 32 MB |
| 8K Models | 2 files | 16 MB |
Minimum file size for upload is 1 KB
Analyze archive files
You can upload and analyze .zip archives directly in Glean. This is useful for working with bundled documents, code packages, or compressed datasets. Drag and drop a .zip file into the composer, then ask questions about its contents. Other archive formats are also accepted: .tar, .tar.gz / .tgz, .tar.bz2, .gz, and .bz2.
Unlike other uploads, archives aren't parsed and indexed up front. Instead, Glean opens them in the Agent Sandbox — a virtual computer with a file system, shell, and code interpreter — and inspects or extracts only the files needed to answer your question.
Requirements
Archive analysis runs in the Agent Sandbox, so both of the following must be true:
- Agent Sandbox is turned on for your organization.
- The chat is in Thinking mode. You can't add archives in Fast mode, and switching a chat to Fast mode removes any staged archive files.
Archive analysis runs in the Agent Sandbox and may be subject to usage-based pricing.
Archive limits
| Limit | Default |
|---|---|
| Archive (compressed) file size | 64 MB |
| Total uncompressed contents | 256 MB |
Archives count toward the per-session file limit for your model, shown in Upload Limits. To protect against zip bombs, Glean also rejects archives with an unusually high compression ratio.
Security restrictions
Glean validates every archive before processing and rejects it if it contains any of the following:
- Executable or script files (for example,
.exe,.dll,.so,.sh,.bat, or.msi) - Nested archives, that is, another archive inside the archive
- Password-protected or encrypted entries
- Symbolic or hard links
- Entries with unsafe paths, such as a path that points outside the archive
Glean scans archives for malware, the same as for other file uploads.
Known Limitations
- Multi-media support for video and audio files is not available. Files outside of the supported file types above cannot be uploaded.
- Custom data retention policies for file uploads are not supported beyond your configured chat history retention. You can ask users to disable chat session history or to manually delete chat sessions if you would like to delete files and metadata sooner.
- Optical Character Recognition (OCR) must be enabled for scanned PDFs to work properly - contact Glean support if you experience issues
- For analytical queries (row counts, filtered counts, aggregations) on large spreadsheets referenced from a connected source such as SharePoint or OneDrive, uploading the file directly typically produces more accurate results than referencing the file by URL. See Data Analysis: Overview for guidance.
Enabling File Upload
To enable file upload for all users:
- Navigate to Glean section in workspace Settings
- Locate the File Upload toggle
- Enable the feature
File Upload is disabled by default for existing customers (as of GA on 9/24) but enabled by default for new customers.
FAQ
See also
- Data Analysis for Spreadsheets
- Chat Sharing
- File Creation and Export to cloud storage services (GDrive, OneDrive)