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 #3574] [BUG]: Metadata content is stored as text based when uploaded file from AnythingLLM #2305

New Issue
Closed
opened 2026-02-22 18:29:05 -05:00 by yindo · 1 comment
yindo commented 2026-02-22 18:29:05 -05:00
Owner
Copy Link
Copy Source

Originally created by @johnec2 on GitHub (Apr 1, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3574

How are you running AnythingLLM?

Local development

What happened?

When a JSON file is uploaded to anythingLLM, I want to store specific fields like "category" and "role" as metadata rather than having them embedded in the text-based payload

how to format the json file data to store metadata separately so that we can easily query by category or role.

The data format we are using is as below:
{
"id": "01",
"questions": ["How to upload games?" ],
"answer": "Games can be created individually or uploaded in bulk. ...",
"metadata": {
"category": "Bulk Upload Game",
"role": ["admin"],
"module":"Game"
}
}
Can you suggest how to format the data to store metadata separately in the payload?

Are there known steps to reproduce?

No response

Originally created by @johnec2 on GitHub (Apr 1, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3574 ### How are you running AnythingLLM? Local development ### What happened? When a JSON file is uploaded to anythingLLM, I want to store specific fields like "category" and "role" as metadata rather than having them embedded in the text-based payload how to format the json file data to store metadata separately so that we can easily query by category or role. The data format we are using is as below: { "id": "01", "questions": ["How to upload games?" ], "answer": "Games can be created individually or uploaded in bulk. ...", "metadata": { "category": "Bulk Upload Game", "role": ["admin"], "module":"Game" } } Can you suggest how to format the data to store metadata separately in the payload? ### Are there known steps to reproduce? _No response_
yindo added the possible bug label 2026-02-22 18:29:05 -05:00
yindo closed this issue 2026-02-22 18:29:05 -05:00
yindo commented 2026-02-22 18:29:06 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Apr 1, 2025):

This is not a bug, it is intentional because when using basic RAG - or even accuracy optimized reranking - having a small amount of the metadata in the snippet improves retrival by a lot since normally this content is not included or searchable since we do not expose metadata searching since that would be very complex to surface in the UI.

If you want to change it, you can do so here:
https://github.com/Mintplex-Labs/anything-llm/blob/962c96a7b4a08b15195e27d383ed93e83809a969/server/utils/TextSplitter/index.js#L70
Just return "" here

@timothycarambat commented on GitHub (Apr 1, 2025): This is not a bug, it is intentional because when using basic RAG - or even accuracy optimized reranking - having a small amount of the metadata in the snippet improves retrival by a lot since normally this content is not included or searchable since we do not expose metadata searching since that would be very complex to surface in the UI. If you want to change it, you can do so here: https://github.com/Mintplex-Labs/anything-llm/blob/962c96a7b4a08b15195e27d383ed93e83809a969/server/utils/TextSplitter/index.js#L70 Just return "" here
yindo changed title from [BUG]: Metadata content is stored as text based when uploaded file from AnythingLLM to [GH-ISSUE #3574] [BUG]: Metadata content is stored as text based when uploaded file from AnythingLLM 2026-06-05 14:45:47 -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 possible bug
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#2305
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?