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

@@ -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`

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"`: