From 2a11b2c3315c182d35b0679af06ce602d9d34bc0 Mon Sep 17 00:00:00 2001 From: Liu An Date: Thu, 10 Jul 2025 09:43:19 +0800 Subject: [PATCH] Docs: Update default `chunk_token_num` to 512 in API references (#8766) ### 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 --- docs/references/http_api_reference.md | 4 ++-- docs/references/python_api_reference.md | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/docs/references/http_api_reference.md b/docs/references/http_api_reference.md index d3f87b00a..098ee8bb9 100644 --- a/docs/references/http_api_reference.md +++ b/docs/references/http_api_reference.md @@ -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` diff --git a/docs/references/python_api_reference.md b/docs/references/python_api_reference.md index bb50e1e99..8afda00dd 100644 --- a/docs/references/python_api_reference.md +++ b/docs/references/python_api_reference.md @@ -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"`: