[GH-ISSUE #3094] [FEAT]: Custom Chunking #1986

Closed
opened 2026-02-22 18:27:33 -05:00 by yindo · 1 comment
Owner

Originally created by @emad-qadri on GitHub (Feb 3, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3094

What would you like to see?

Resource based chunking

I understand that AnythingLLM handles chunking independently before passing the chunks to the embedding model. While we can set the max input size based on the embedder's token window, chunking should be tailored to the type of input data.

For example, the default chunking works well for text data, but for a code repository, chunking should better align with the code structure to preserve semantic meaning—such as using ASTs (Abstract Syntax Trees) or function-level segmentation.

Originally created by @emad-qadri on GitHub (Feb 3, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3094 ### What would you like to see? ### Resource based chunking I understand that AnythingLLM handles chunking independently before passing the chunks to the embedding model. While we can set the max input size based on the embedder's token window, chunking should be tailored to the type of input data. For example, the default chunking works well for text data, but for a code repository, chunking should better align with the code structure to preserve semantic meaning—such as using ASTs (Abstract Syntax Trees) or function-level segmentation.
yindo added the enhancementfeature request labels 2026-02-22 18:27:33 -05:00
yindo closed this issue 2026-02-22 18:27:34 -05:00
Author
Owner

@timothycarambat commented on GitHub (Feb 3, 2025):

Dupe of #2146 (upvote for triage)

@timothycarambat commented on GitHub (Feb 3, 2025): Dupe of #2146 (upvote for triage)
yindo changed title from [FEAT]: Custom Chunking to [GH-ISSUE #3094] [FEAT]: Custom Chunking 2026-06-05 14:43:50 -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#1986