[GH-ISSUE #121] Support Image Uploading #83

Closed
opened 2026-02-22 18:17:49 -05:00 by yindo · 7 comments
Owner

Originally created by @timothycarambat on GitHub (Jun 27, 2023).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/121

The document processor should support the uploading and embedding of images like PNG, JPEG, and other static formats.

Ideally, this should describe the image and return that text for embedding instead of trying to do a multi-modal embedding which will be impossible to search textually over.

Originally created by @timothycarambat on GitHub (Jun 27, 2023). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/121 The document processor should support the uploading and embedding of images like PNG, JPEG, and other static formats. Ideally, this should describe the image and return that text for embedding instead of trying to do a multi-modal embedding which will be impossible to search textually over.
yindo added the enhancement label 2026-02-22 18:17:49 -05:00
yindo closed this issue 2026-02-22 18:17:49 -05:00
Author
Owner

@AntonioCiolino commented on GitHub (Jul 5, 2023):

Are you thinking that it should use something like a BERT or Deepdanbooru to extract info from?

@AntonioCiolino commented on GitHub (Jul 5, 2023): Are you thinking that it should use something like a BERT or Deepdanbooru to extract info from?
Author
Owner

@timothycarambat commented on GitHub (Jul 6, 2023):

Are you thinking that it should use something like a BERT or Deepdanbooru to extract info from?

Both of these would be an issue to run locally since they require some big resources. Deepdanbooru is also specific to anime-girls image tagging and tends to give more NSFW results so honestly easiest implementation is just using something simple like OpenAIs CLIP which can run on replicate pretty easily (but will still cost money)

https://replicate.com/rmokady/clip_prefix_caption

@timothycarambat commented on GitHub (Jul 6, 2023): > Are you thinking that it should use something like a BERT or Deepdanbooru to extract info from? Both of these would be an issue to run locally since they require some big resources. Deepdanbooru is also specific to anime-girls image tagging and tends to give more NSFW results so honestly easiest implementation is just using something simple like OpenAIs CLIP which can run on replicate pretty easily (but will still cost money) https://replicate.com/rmokady/clip_prefix_caption
Author
Owner

@AntonioCiolino commented on GitHub (Jul 6, 2023):

If you are calling out to external resources, there’s lots of choices of course.

@AntonioCiolino commented on GitHub (Jul 6, 2023): If you are calling out to external resources, there’s lots of choices of course.
Author
Owner

@phicha20224 commented on GitHub (May 30, 2024):

it return anythingllm File extension .jpg not supported for parsing and cannot be assumed as text file type.

@phicha20224 commented on GitHub (May 30, 2024): it return anythingllm File extension .jpg not supported for parsing and cannot be assumed as text file type.
Author
Owner

@timothycarambat commented on GitHub (May 30, 2024):

@phicha20224 - that is because we dont support uploading images right now

@timothycarambat commented on GitHub (May 30, 2024): @phicha20224 - that is because we dont support uploading images right now
Author
Owner

@timothycarambat commented on GitHub (May 30, 2024):

@phicha20224 - that is because we dont support uploading images right now

@timothycarambat commented on GitHub (May 30, 2024): @phicha20224 - that is because we dont support uploading images right now
Author
Owner

@xyz-rainbow commented on GitHub (Jun 15, 2024):

what i need to do for the support on images?

@xyz-rainbow commented on GitHub (Jun 15, 2024): what i need to do for the support on images?
yindo changed title from Support Image Uploading to [GH-ISSUE #121] Support Image Uploading 2026-06-05 14:33:23 -04:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#83