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 #1387] [FEAT]: Add Optional Small-to-Big Retrieval #886

New Issue
Closed
opened 2026-02-22 18:22:01 -05:00 by yindo · 1 comment
yindo commented 2026-02-22 18:22:01 -05:00
Owner
Copy Link
Copy Source

Originally created by @cope on GitHub (May 13, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/1387

What would you like to see?

Apparently, smaller chunk sizes improve retrieval quality, but larger chunk sizes improve generation quality: Advanced RAG 01: Small-to-Big Retrieval.

If the current embediing process stores the relative chunk ids per document, then when chunk i is retrieved, we can prepend chunks [i-2, i-1] and append chunks [i+1, i+2] and pass on that big combined text to the generation step. This would have both benefits: smaller chunks for retrieval and larger chunks for generation. Naturally, we need to make sure that any i+/-n chunk exists before adding null.

My idea is to simplify the implementation by just adding optional prepend/append integers that would default to 0, but could be changed by the user in the settings.

The alternative is to do full Parent Document Retriever, but this is a much bigger task IMHO.

Originally created by @cope on GitHub (May 13, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/1387 ### What would you like to see? Apparently, smaller chunk sizes improve retrieval quality, but larger chunk sizes improve generation quality: [Advanced RAG 01: Small-to-Big Retrieval](https://towardsdatascience.com/advanced-rag-01-small-to-big-retrieval-172181b396d4). If the current embediing process stores the relative chunk ids per document, then when chunk `i` is retrieved, we can _prepend_ chunks `[i-2, i-1]` and _append_ chunks `[i+1, i+2]` and pass on that big combined text to the generation step. This would have both benefits: smaller chunks for retrieval and larger chunks for generation. _Naturally, we need to make sure that any `i+/-n` chunk exists before adding `null`._ My idea is to simplify the implementation by just adding optional prepend/append integers that would default to 0, but could be changed by the user in the settings. The alternative is to do full [Parent Document Retriever](https://python.langchain.com/v0.1/docs/modules/data_connection/retrievers/parent_document_retriever/), but this is a much bigger task IMHO.
yindo added the enhancementfeature request labels 2026-02-22 18:22:01 -05:00
yindo closed this issue 2026-02-22 18:22:01 -05:00
yindo commented 2026-02-22 18:22:01 -05:00
Author
Owner
Copy Link
Copy Source

@RahSwe commented on GitHub (May 13, 2024):

Parent Document Retriever would be a nice option for documents (like the pinning option). Due to mixes of documents in which some are too big to be retrieved as parent.

@RahSwe commented on GitHub (May 13, 2024): Parent Document Retriever would be a nice option for documents (like the pinning option). Due to mixes of documents in which some are too big to be retrieved as parent.
yindo changed title from [FEAT]: Add Optional Small-to-Big Retrieval to [GH-ISSUE #1387] [FEAT]: Add Optional Small-to-Big Retrieval 2026-06-05 14:37:45 -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#886
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?