pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 20:42:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix error commands (#2778)

Browse Source 
### What problem does this PR solve?

_Briefly describe what this PR aims to solve. Include background context
that will help reviewers understand the purpose of the PR._

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
This commit is contained in:
Jin Hai
2024-10-10 10:38:57 +08:00
committed by GitHub
parent 66172cef3e
commit 9dfcae2b5d
7 changed files with 2 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/guides/configure_knowledge_base.md
View File

@ -58,7 +58,7 @@ You can also change the chunk template for a particular file on the **Datasets**
### Select embedding model
An embedding model builds vector index on file chunks. Once you have chosen an embedding model and used it to parse a file, you are no longer allowed to change it. To switch to a different embedding model, you *must* deletes all completed file chunks in the knowledge base. The obvious reason is that we must *ensure* that all files in a specific knowledge base are parsed using the *same* embedding model (ensure that they are compared in the same embedding space).
An embedding model builds vector index on file chunks. Once you have chosen an embedding model and used it to parse a file, you are no longer allowed to change it. To switch to a different embedding model, you *must* delete all completed file chunks in the knowledge base. The obvious reason is that we must *ensure* that all files in a specific knowledge base are parsed using the *same* embedding model (ensure that they are compared in the same embedding space).
The following embedding models can be deployed locally: