[GH-ISSUE #785] RAG With images #455

Closed
opened 2026-02-22 18:19:34 -05:00 by yindo · 3 comments
Owner

Originally created by @shanvinod4u on GitHub (Feb 23, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/785

What would you like to see?

Would be good to have RAG with images, workspace chat right now has only text, its good to have images and texts from documents

Originally created by @shanvinod4u on GitHub (Feb 23, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/785 ### What would you like to see? Would be good to have RAG with images, workspace chat right now has only text, its good to have images and texts from documents
yindo added the enhancementfeature request labels 2026-02-22 18:19:34 -05:00
yindo closed this issue 2026-02-22 18:19:34 -05:00
Author
Owner

@timothycarambat commented on GitHub (Feb 23, 2024):

Tracking on https://github.com/Mintplex-Labs/anything-llm/issues/558

@timothycarambat commented on GitHub (Feb 23, 2024): Tracking on https://github.com/Mintplex-Labs/anything-llm/issues/558
Author
Owner

@timwu-ipevo commented on GitHub (May 8, 2024):

I suppose individuals may interpret "RAG with images" in various ways. One interpretation is that LLM can reference the image from the document in its response. Another interpretation is that LLM can consider both the image and text as prompts and attempt to comprehend the image.

@timwu-ipevo commented on GitHub (May 8, 2024): I suppose individuals may interpret "RAG with images" in various ways. One interpretation is that LLM can reference the image from the document in its response. Another interpretation is that LLM can consider both the image and text as prompts and attempt to comprehend the image.
Author
Owner

@dberardo-com commented on GitHub (Jan 1, 2025):

Why has this issue been closed?

AFAIK it is not possible yet to ask questions related to images when using RAG.

In my use case I would like to upload a bunch of pdf texts explaining common consumer electrical energy pattern in households and then some pdf with plots that give some statistical information on these consumption patterns.

During inference I would like to upload a pdf report with mainly plots and ask the ai if there is any anomaly

@dberardo-com commented on GitHub (Jan 1, 2025): Why has this issue been closed? AFAIK it is not possible yet to ask questions related to images when using RAG. In my use case I would like to upload a bunch of pdf texts explaining common consumer electrical energy pattern in households and then some pdf with plots that give some statistical information on these consumption patterns. During inference I would like to upload a pdf report with mainly plots and ask the ai if there is any anomaly
yindo changed title from RAG With images to [GH-ISSUE #785] RAG With images 2026-06-05 14:35:23 -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#455