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

Docs: Update default chunk_token_num to 512 in API references (#8766)

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

Changed the default value of `chunk_token_num` from 128 to 512 in both
HTTP and Python API reference documentation to reflect the updated
configuration.

#8753

### Type of change

- [x] Documentation Update
This commit is contained in:
Liu An
2025-07-10 09:43:19 +08:00
committed by Zhichang Yu
parent f8524462b0
commit 2a11b2c331
2 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/references/http_api_reference.md
View File

@ -410,7 +410,7 @@ curl --request POST \
- Minimum: `0`
- Maximum: `10`
- `"chunk_token_num"`: `int`
- Defaults to `128`
- Defaults to `512`
- Minimum: `1`
- Maximum: `2048`
- `"delimiter"`: `string`
@ -631,7 +631,7 @@ curl --request PUT \
- Minimum: `0`
- Maximum: `10`
- `"chunk_token_num"`: `int`
- Defaults to `128`
- Defaults to `512`
- Minimum: `1`
- Maximum: `2048`
- `"delimiter"`: `string`

2
docs/references/python_api_reference.md
View File

@ -152,7 +152,7 @@ The chunking method of the dataset to create. Available options:
The parser configuration of the dataset. A `ParserConfig` object's attributes vary based on the selected `chunk_method`:
- `chunk_method`=`"naive"`:
`{"chunk_token_num":128,"delimiter":"\\n","html4excel":False,"layout_recognize":True,"raptor":{"use_raptor":False}}`.
`{"chunk_token_num":512,"delimiter":"\\n","html4excel":False,"layout_recognize":True,"raptor":{"use_raptor":False}}`.
- `chunk_method`=`"qa"`:
`{"raptor": {"use_raptor": False}}`
- `chunk_method`=`"manuel"`: