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 #3382] [DOCS]: Threads and the functionality they offer #2181

New Issue
Closed
opened 2026-02-22 18:28:30 -05:00 by yindo · 1 comment
yindo commented 2026-02-22 18:28:30 -05:00
Owner
Copy Link
Copy Source

Originally created by @socketbox on GitHub (Mar 2, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3382

Description

Apologies in advance if this is already explained and I overlooked it. Searching for "thread" in the documentation reveals this page , which has a screenshot that highlights the actionable New thread element, but that's not actually described.

I understand that workspaces are a means of isolating "contexts" (please pardon my loose understanding of terminology) such that language models, RAG, and embedded data can be kept and configured separately for separate projects or domains.

What I don't understand is the intent behind the concept of threads. A response from @timothycarambat here states:

... all threads share documents under a workspace, but not chat histories! So if the RAG response contains citations this simply means the vector database assumed that the citation was possibly relevant to the query/prompt. This is not problematic on its face, since this is how RAG works - however, if you want more "strict" citation behavior you can do so by setting the similarity threshold

So threads share RAG but not chat history. What use case is envisioned here? How would a team collaborating on a project (in a workspace devoted to that project) benefit from threads?

Originally created by @socketbox on GitHub (Mar 2, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3382 ### Description Apologies in advance if this is already explained and I overlooked it. Searching for "thread" in the documentation reveals [this page ](https://docs.anythingllm.com/chat-ui), which has a screenshot that highlights the actionable _New thread_ element, but that's not actually described. I understand that workspaces are a means of isolating "contexts" (please pardon my loose understanding of terminology) such that language models, RAG, and embedded data can be kept and configured separately for separate projects or domains. What I don't understand is the intent behind the concept of threads. A response from @timothycarambat [here](https://github.com/Mintplex-Labs/anything-llm/issues/2526#issuecomment-2521104252) states: >... all threads share documents under a workspace, but not chat histories! So if the RAG response contains citations this simply means the vector database assumed that the citation was possibly relevant to the query/prompt. This is not problematic on its face, since this is how RAG works - however, if you want more "strict" citation behavior you can do so by setting the [similarity threshold](https://docs.anythingllm.com/llm-not-using-my-docs#vector-database-settings--document-similarity-threshold) So threads share RAG but not chat history. What use case is envisioned here? How would a team collaborating on a project (in a workspace devoted to that project) benefit from threads?
yindo added the documentation label 2026-02-22 18:28:30 -05:00
yindo closed this issue 2026-02-22 18:28:30 -05:00
yindo commented 2026-02-22 18:28:30 -05:00
Author
Owner
Copy Link
Copy Source

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

So threads share RAG but not chat history.

Correct, that is basically the whole idea. Threads share the documents and settings of a workspace but no historical chats. Threads are at the user level, so as a user, I can have multiple threads within a workspace all working on various chats that might benefit from the documents in the workspace but are distinctively different chat threads.

With LLMs, context is everything, and historical chats are part of the context window. Changing subjects in a thread can drive outputs due to their presence in context, resulting in worse outputs. Threads help you keep the context window "focused" without having to /reset a chat window and lose your existing chat history.

This is common in basically all AI UI's from ChatGPT to Claude Chat, to every other UI.

@timothycarambat commented on GitHub (Mar 3, 2025): > So threads share RAG but not chat history. Correct, that is basically the whole idea. Threads share the documents and settings of a workspace but no historical chats. Threads are at the user level, so as a user, I can have multiple threads within a workspace all working on various chats that might benefit from the documents in the workspace but are distinctively different chat threads. With LLMs, context is everything, and historical chats are part of the context window. Changing subjects in a thread can drive outputs due to their presence in context, resulting in worse outputs. Threads help you keep the context window "focused" without having to `/reset` a chat window and lose your existing chat history. This is common in basically all AI UI's from ChatGPT to Claude Chat, to every other UI.
yindo changed title from [DOCS]: Threads and the functionality they offer to [GH-ISSUE #3382] [DOCS]: Threads and the functionality they offer 2026-06-05 14:45:01 -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 documentation
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#2181
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?