[GH-ISSUE #2007] [BUG]: Document limit in workspaces? #1308

Closed
opened 2026-02-22 18:24:12 -05:00 by yindo · 1 comment
Owner

Originally created by @Sungod3000 on GitHub (Jul 31, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2007

How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

Hi, im running local with LM Studio and in house RAG.
I just added 20 small PDFs to the workspace and im noticing that only 3-5 of them are considered in queries.
The number of vectors is realistic for 20 documents but it seems when i ask about specific documents only very few of them are considered.

kind regards
F

Are there known steps to reproduce?

No response

Originally created by @Sungod3000 on GitHub (Jul 31, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2007 ### How are you running AnythingLLM? AnythingLLM desktop app ### What happened? Hi, im running local with LM Studio and in house RAG. I just added 20 small PDFs to the workspace and im noticing that only 3-5 of them are considered in queries. The number of vectors is realistic for 20 documents but it seems when i ask about specific documents only very few of them are considered. kind regards F ### Are there known steps to reproduce? _No response_
yindo added the possible bug label 2026-02-22 18:24:12 -05:00
yindo closed this issue 2026-02-22 18:24:12 -05:00
Author
Owner

@timothycarambat commented on GitHub (Jul 31, 2024):

https://docs.anythingllm.com/llm-not-using-my-docs#vector-database-settings--max-context-snippets

That is how RAG works on a fundamental level. If you want all 20 PDFs to be sent (which we highly do not recommend and wont even work unless using Claude or something with a massive context window) you can pin the documents.

RAG splits the documents up and per-query retrieves what are semantically determined to be the best chunks to answer the query.

@timothycarambat commented on GitHub (Jul 31, 2024): https://docs.anythingllm.com/llm-not-using-my-docs#vector-database-settings--max-context-snippets That is how RAG works on a fundamental level. If you want all 20 PDFs to be sent (_which we highly do not recommend and wont even work unless using Claude or something with a massive context window_) you can [pin the documents](https://docs.anythingllm.com/llm-not-using-my-docs#document-pinning). RAG splits the documents up and per-query retrieves what are semantically determined to be the best chunks to answer the query.
yindo changed title from [BUG]: Document limit in workspaces? to [GH-ISSUE #2007] [BUG]: Document limit in workspaces? 2026-06-05 14:40:03 -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#1308