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 #2946] How can I adjust to improve the accuracy of text similarity retrieval? #1878

New Issue
Closed
opened 2026-02-22 18:26:58 -05:00 by yindo · 1 comment
yindo commented 2026-02-22 18:26:58 -05:00
Owner
Copy Link
Copy Source

Originally created by @zhangyibing2025 on GitHub (Jan 7, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2946

Thank you very much for the contributions of the project team members. I am using Anythingllm to build an interesting application, which is a cool thing, but now I am having some trouble and don't know how to solve it.
When I was testing the/app/v1/workspace/{slug}/vector search interface, I found that the similarity between the entered keywords and the searched documents was very low，However, when I entered keywords within the document, I couldn't find them. What is the reason for this? How can I adjust to improve the accuracy of text similarity retrieval?

Originally created by @zhangyibing2025 on GitHub (Jan 7, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2946 Thank you very much for the contributions of the project team members. I am using Anythingllm to build an interesting application, which is a cool thing, but now I am having some trouble and don't know how to solve it. When I was testing the/app/v1/workspace/{slug}/vector search interface, I found that the similarity between the entered keywords and the searched documents was very low，However, when I entered keywords within the document, I couldn't find them. What is the reason for this? How can I adjust to improve the accuracy of text similarity retrieval?
yindo closed this issue 2026-02-22 18:26:58 -05:00
yindo commented 2026-02-22 18:26:58 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Jan 7, 2025):

In general - this document helps

As for the vector search endpoint itself the search is done via semantic similarity - not full text search. You have not specified what kind of version of AnythingLLM you are running -- but on the latest docker tag we now support reranking in the workspace - it helps a lot!

@timothycarambat commented on GitHub (Jan 7, 2025): In general - [this document helps](https://docs.anythingllm.com/llm-not-using-my-docs#how-can-i-make-retrieval-better-then) As for the vector search endpoint itself the search is done via semantic similarity - not full text search. You have not specified what kind of version of AnythingLLM you are running -- but on the latest docker tag we now support reranking in the workspace - it helps a lot!
yindo changed title from How can I adjust to improve the accuracy of text similarity retrieval? to [GH-ISSUE #2946] How can I adjust to improve the accuracy of text similarity retrieval? 2026-06-05 14:43:13 -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#1878
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?