#13 修正该错误

This commit is contained in:
YILING0013
2025-02-01 10:20:40 +08:00
parent 2a5602009b
commit ed7e74583d
2 changed files with 3 additions and 3 deletions
+2 -2
View File
@@ -45,11 +45,11 @@
```bash
pip install -r requirements.txt
```
3. (可选)若需要手动安装 `nltk` 的 `punkt` 数据包:
3. (可选)若需要手动安装 `nltk` 的 `punkt_tab` 数据包:
```bash
python
>>> import nltk
>>> nltk.download('punkt')
>>> nltk.download('punkt_tab')
```
---
+1 -1
View File
@@ -583,7 +583,7 @@ def advanced_split_content(content: str,
"""
将文本先按句子切分,然后根据语义相似度进行合并,最后根据max_length进行二次切分。
"""
nltk.download('punkt', quiet=True) # 确保 punkt 数据可用
nltk.download('punkt_tab', quiet=True)
sentences = nltk.sent_tokenize(content)
if not sentences: