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

Miscellaneous UI updates (#6471)

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



### Type of change


- [x] Documentation Update
This commit is contained in:
writinwaters
2025-03-24 19:36:47 +08:00
committed by GitHub
parent f691b4ddd2
commit a40c5aea83
11 changed files with 61 additions and 63 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/guides/dataset/configure_knowledge_base.md
View File

@ -43,6 +43,7 @@ RAGFlow offers multiple chunking template to facilitate chunking files of differ
|--------------|-----------------------------------------------------------------------|-----------------------------------------------------------------------------------------------|
| General | Files are consecutively chunked based on a preset chunk token number. | DOCX, XLSX, XLS (Excel97~2003), PPT, PDF, TXT, JPEG, JPG, PNG, TIF, GIF, CSV, JSON, EML, HTML |
| Q&A | | XLSX, XLS (Excel97~2003), CSV/TXT |
| Resume | Enterprise edition only. You can also try it out on demo.ragflow.io. | DOCX, PDF, TXT |
| Manual | | PDF |
| Table | | XLSX, XLS (Excel97~2003), CSV/TXT |
| Paper | | PDF |
@ -50,7 +51,8 @@ RAGFlow offers multiple chunking template to facilitate chunking files of differ
| Laws | | DOCX, PDF, TXT |
| Presentation | | PDF, PPTX |
| Picture | | JPEG, JPG, PNG, TIF, GIF |
| One | The entire document is chunked as one. | DOCX, XLSX, XLS (Excel97~2003), PDF, TXT |
| One | Each document is chunked in its entirety (as one). | DOCX, XLSX, XLS (Excel97~2003), PDF, TXT |
| Tag | The knowledge base functions as a tag set for the others. | XLSX, CSV/TXT |
You can also change a file's chunk method on the **Datasets** page.

2
docs/guides/dataset/run_retrieval_test.md
View File

@ -27,7 +27,7 @@ In contrast, chunks created from [knowledge graph construction](./construct_know
### Similarity threshold
This sets the bar for retrieving chunks: chunks with similarities below the threshold will be filtered out. By default, the threshold is set to 0.2.
This sets the bar for retrieving chunks: chunks with similarities below the threshold will be filtered out. By default, the threshold is set to 0.2. That means that only chunks with hybrid similarity score of 20 or higher will be retrieved.
### Keyword similarity weight