File Attachments
PebbleChat can analyse files you upload directly in the conversation. Attach documents, spreadsheets, code, emails, and images to get AI-powered insights and assistance.
Supported Formats
PebbleChat accepts a wide range of file types, including but not limited to:
| Category | Formats |
|---|---|
| Documents | PDF, Word (.docx), Rich Text (.rtf) |
| Spreadsheets | CSV, TSV |
| Data | JSON, XML, YAML |
| EML, MSG | |
| OpenDocument | ODF-based files (ODT, ODS, ODP) |
| Images | PNG, JPG, GIF, WebP |
| Code | Most text-based code files |
How to Attach Files
Click to Upload
- Click the attachment icon (paperclip) in the input area
- Select one or more files from your device
- The files appear as chips above the message input
- Type your question about the files and press Enter
Drag and Drop
You can also drag files from your desktop or file manager directly onto the PebbleChat window.
Working with Attachments
Document Analysis
Upload a document and ask questions about its content:
[Attached: quarterly-report.pdf]
Summarise the key findings from this report and highlight any risks mentioned.Data Processing
Upload structured data for analysis:
[Attached: sales-data.csv]
What were the top 5 products by revenue? Show me a breakdown by region.Image Analysis
Upload images for description, analysis, or extraction:
[Attached: screenshot.png]
What error message is shown in this screenshot? How can I fix it?Email Analysis
Upload email files for summarisation or action extraction:
[Attached: client-thread.eml]
What are the key action items from this email thread?Context Persistence
When you upload a file, its content is included in the conversation context. This means:
- Follow-up questions work — You can ask additional questions about an uploaded file later in the same conversation
- Files persist across reloads — If you reload the page, previously uploaded file content is still available
- Multiple files are supported — Upload several files and ask questions that reference all of them
Limitations
- File size — Very large files may be truncated to fit within the model’s context window
- Binary formats — Some complex binary formats may not be fully parseable
- Context window — Multiple large files may consume significant context, triggering automatic conversation compression
- Image support — Image analysis requires a model that supports vision capabilities (most modern models do)