Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-19 14:13:35 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #2977] RAG works for Wav, Mp3 and Mp4 but not for png, jpg #1902

New Issue
Closed
opened 2026-02-22 18:27:08 -05:00 by yindo · 1 comment
yindo commented 2026-02-22 18:27:08 -05:00
Owner
Copy Link
Copy Source

Originally created by @nannib on GitHub (Jan 16, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2977

Hi,
it's a strange behavior of the RAG system, because I can embed some binary files, like wav, mp3 and mp4, but not png, jpg, because they are not text files...why?
Using LLama multimodal model, I can upload a jpg or png in the chat windows and the model can describe its content, but I cannot use it in the RAG.
At the end, the RAG system can transcribe the mp3 or wav file, if I ask the content of the file "audio1.mp3" the LLM answers the right message I can ear in the audio file.

Thanks for all folks! :-)

Originally created by @nannib on GitHub (Jan 16, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2977 Hi, it's a strange behavior of the RAG system, because I can embed some binary files, like wav, mp3 and mp4, but not png, jpg, because they are not text files...why? Using LLama multimodal model, I can upload a jpg or png in the chat windows and the model can describe its content, but I cannot use it in the RAG. At the end, the RAG system can transcribe the mp3 or wav file, if I ask the content of the file "audio1.mp3" the LLM answers the right message I can ear in the audio file. Thanks for all folks! :-)
yindo closed this issue 2026-02-22 18:27:08 -05:00
yindo commented 2026-02-22 18:27:09 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Jan 16, 2025):

We dont have the ability to upload images because they need to be embedded with a special embedder and/or OCR'd or described. This process is different from uploading an image during a chat

@timothycarambat commented on GitHub (Jan 16, 2025): We dont have the ability to upload images because they need to be embedded with a special embedder and/or OCR'd or described. This process is different from uploading an image during a chat
yindo changed title from RAG works for Wav, Mp3 and Mp4 but not for png, jpg to [GH-ISSUE #2977] RAG works for Wav, Mp3 and Mp4 but not for png, jpg 2026-06-05 14:43:21 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Desktop
Docker
Integration Request
Integration Request
OS: Linux
OS: Mobile
OS: Windows
UI/UX
blocked
bug
bug
core-team-only
documentation
duplicate
embed-widget
enhancement
feature request
github_actions
good first issue
investigating
needs info / can't replicate
possible bug
pull-request
Mirrored from GitHub Pull Request
 question
stage: specifications
wontfix
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#1902
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?