mirror of
https://github.com/deepseek-ai/DeepSeek-R1.git
synced 2026-11-05 00:47:42 +00:00
[GH-ISSUE #83] Feature request: Add Support for Base64-Encoded Image Data via the API #68
Labels
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
deepseek-ai/DeepSeek-R1#68
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @p-siatos on GitHub (Jan 27, 2025).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-R1/issues/83
As the title says, is there an ETA for this or the API will remain text only?
@davidogundepo commented on GitHub (Jan 27, 2025):
Current API is text-only. Base64 image support would enable more multimodal capabilities. Is this needed for a specific use case?
@p-siatos commented on GitHub (Jan 27, 2025):
Yes, in a pipeline where for a PDF, each page is converted to an image (pymupdf) to markdown format through LLM API.
@msmaromi commented on GitHub (Jan 28, 2025):
Would love to have this feature also!
I wonder how is it enabled on deepseek chat web/apps?
@github-actions[bot] commented on GitHub (Mar 3, 2025):
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. If you believe this issue is still relevant, please leave a comment to keep it open. Thank you for your contributions!
@DonLeKouT commented on GitHub (Mar 19, 2025):
I would also like to keep that request alive. DeepSeek R1 is excellent for math and encoding math/finance/statistics papers in Base64 would be an easy way for analyzing these papers in bulk. Research would be so much better.
@github-actions[bot] commented on GitHub (Jun 1, 2025):
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. If you believe this issue is still relevant, please leave a comment to keep it open. Thank you for your contributions!
@github-actions[bot] commented on GitHub (Jun 17, 2025):
false
@base64imageconverter-beep commented on GitHub (Dec 1, 2025):
It would be really useful to have Base64 image support in the API, especially for workflows that convert PDFs or images in bulk. For quick testing or converting images to Base64, I use base64 image converter
, which helps a lot during development.