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 #3385] [FEAT]: Process CSV rows as separate documents with metadata. #2182

New Issue
Open
opened 2026-02-22 18:28:31 -05:00 by yindo · 0 comments
yindo commented 2026-02-22 18:28:31 -05:00
Owner
Copy Link
Copy Source

Originally created by @jtkiley on GitHub (Mar 3, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3385

What would you like to see?

It would be nice to be able to import CSVs such that each row is a separate document with the ability to specify metadata columns (for LanceDB).

I have a bunch of text with nested levels and time that are broken out in the metadata, and I'd like for the LLM to be able to get at that/provide id citations back from the metadata.

If there's some way to build the database in LanceDB outside of AnythingLLM and then use it, that would be helpful, too.

My main goal right now (which seems like a common use case, at least for me) is to take some convenient data and as efficiently as possible see how well RAG works on this data for answering specific questions as a prototype. It's decent with the basics, but I think the data representation is why it's having trouble giving me better results. It's creating about 10 chunks per document on average, so it can't find ids or nesting level metadata very well.

Originally created by @jtkiley on GitHub (Mar 3, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3385 ### What would you like to see? It would be nice to be able to import CSVs such that each row is a separate document with the ability to specify metadata columns (for LanceDB). I have a bunch of text with nested levels and time that are broken out in the metadata, and I'd like for the LLM to be able to get at that/provide id citations back from the metadata. If there's some way to build the database in LanceDB outside of AnythingLLM and then use it, that would be helpful, too. My main goal right now (which seems like a common use case, at least for me) is to take some convenient data and as efficiently as possible see how well RAG works on this data for answering specific questions as a prototype. It's decent with the basics, but I think the data representation is why it's having trouble giving me better results. It's creating about 10 chunks per document on average, so it can't find ids or nesting level metadata very well.
yindo added the enhancementfeature request labels 2026-02-22 18:28:31 -05:00
yindo changed title from [FEAT]: Process CSV rows as separate documents with metadata. to [GH-ISSUE #3385] [FEAT]: Process CSV rows as separate documents with metadata. 2026-06-05 14:45:02 -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 enhancement feature request
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#2182
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?