Note
Access to this page requires authorization. You can try signing in or changing directories.
Access to this page requires authorization. You can try changing directories.
You can allow users of your agent to upload files and images, which your agent can then analyze and use to provide responses.
When to allow file input
The following are the two primary scenarios for allowing users to upload files to elicit agent responses:
- Questions that require information from your configured knowledge sources
- Questions that can be answered from an image or uploaded text, CSV, or PDF file
When you allow users to upload files and your agent to generate responses based on those files, it's important to follow best practices for prompt engineering.
To get the most out of this feature, review the following tips:
Upload images that are clear and high-quality. Agents might struggle to interpret grainy, poorly lit, or pixelated images.
Only upload supported file types, including CSV, PDF, TXT, JPG, PNG, WebP, or nonanimated GIF files.
Only upload files based on these size restrictions:
- Images can't exceed 15 MB (and only 4 MB for DirectLine channel interactions, such as Slack, Telegram, Twilio, Line, GroupMe, DirectLine Speech, and Email)
- PDF files smaller than 40 pages
- TXT or CSV files smaller than 180 KB
If a file triggers content moderation filtering, restart the conversation. The agent uses the current conversation history to generate answers and continues to return content moderation filtering errors if objectionable content is part of the conversation history.
If you're having issues generating high-quality responses from files, turn on Allow the AI to use its own general knowledge on the Knowledge page. This setting is required if there are no relevant knowledge sources configured. For more information, see Allow the agent to use general knowledge.
Turn on file uploads
Makers can allow users of their agent to files during chat interactions with their agent.
Go to the Settings page for your agent, and select Generative AI.
Navigate to the File processing capabilities section.
Turn on File uploads.
(Optional) Select your preferred level of strictness for content moderation.
Select Save.
Test your agent's file analysis
After you turn on File uploads, you can test your agent's capability by uploading files and images and verifying the agent's responses. To upload a file, select the paper clip icon in the Test your agent chat box. Thoroughly test your agent's accuracy by using various files and images with various queries to validate the agent's responses before you publish.
Responsible AI
Microsoft is committed to strong responsible AI practices. Review the full responsible AI guidelines for Copilot Studio before using any AI features. Like all of generative answers, content is checked twice: first during user input and again before the agent generates an output response. If the system finds harmful, offensive, or malicious content at either the input or output stage, the agent won't respond.