高老师，您好！第12章例程执行出错[nltk_data] Error loading punkt: <urlopen error [Errno 11004] [nltk_data] getaddrinfo failed>，请帮忙看看程序是不是对网络有特殊依赖？

[easychu]

Win11操作系统，rag1是我的虚拟环境名称，

1. 安装anaconda
2. 创建虚拟环境
   conda create -n rag1 python=3.10 -y
3. 激活 activate rag1
   并 安装rag1所需 依赖，将依赖文件requirements.txt拷贝到 用户目录下：
   pip install -r requirements.txt -i https://pypi.mirrors.ustc.edu.cn/simple --trusted-host=pypi.mirrors.ustc.edu.cn
   4.从aliendao.cn下载text2vec-base-chinese模型文件
   python model_download.py --e --repo_id shibing624/text2vec-base-chinese --token YPY8KHDQ2NAHQ2SG
   下载后的文件在C:\Users\Z /dataroot/models/shibing624/text2vec-base-chinese目录
4. github上下载 第12章代码到 D:\zhu\tech\RAG\rag1，并将嵌入模型text2vec-base-chinese 文件夹直接从 C:\Users\Z 转移到 D:\zhu\tech\RAG\rag1
5. 执行 python rag-demo.py 出现如下错误：

(rag1) D:\zhu\tech\RAG\rag1>python rag-demo.py
0%| | 0/2 [00:00<?, ?it/s][nltk_data] Error loading punkt: <urlopen error [Errno 11004]
[nltk_data] getaddrinfo failed>
Error loading file documents\README.md
50%|██████████████████████████████████████████ | 1/2 [00:25<00:25, 25.90s/it]Traceback (most recent call last):
File "D:\zhu\tech\RAG\rag1\rag-demo.py", line 92, in
documents = load_docs("./documents")
File "D:\zhu\tech\RAG\rag1\rag-demo.py", line 24, in load_docs
documents = loader.load()
File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\langchain_community\document_loaders\directory.py", line 158, in load
self.load_file(i, p, docs, pbar)
File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\langchain_community\document_loaders\directory.py", line 107, in load_file
raise e
File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\langchain_community\document_loaders\directory.py", line 100, in load_file
sub_docs = self.loader_cls(str(item), **self.loader_kwargs).load()
File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\langchain_community\document_loaders\unstructured.py", line 87, in load
elements = self._get_elements()
File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\langchain_community\document_loaders\unstructured.py", line 179, in get_elements
return partition(filename=self.file_path, **self.unstructured_kwargs)
File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\partition\auto.py", line 397, in partition
elements = partition_md(
File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\documents\elements.py", line 518, in wrapper
elements = func(*args, **kwargs)
File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\file_utils\filetype.py", line 591, in wrapper
elements = func(*args, **kwargs)
File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\file_utils\filetype.py", line 546, in wrapper
elements = func(*args, **kwargs)
File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\chunking_init.py", line 52, in wrapper
elements = func(*args, **kwargs)
File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\partition\md.py", line 104, in partition_md
return partition_html(
File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\documents\elements.py", line 518, in wrapper
elements = func(*args, **kwargs)
File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\file_utils\filetype.py", line 591, in wrapper
elements = func(*args, **kwargs)
File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\file_utils\filetype.py", line 546, in wrapper
elements = func(*args, **kwargs)
File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\chunking_init.py", line 52, in wrapper
elements = func(*args, **kwargs)
File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\partition\html.py", line 141, in partition_html
document_to_element_list(
File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\partition\common.py", line 559, in document_to_element_list
num_pages = len(document.pages)
File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\documents\xml.py", line 54, in pages
self._pages = self._parse_pages_from_element_tree()
File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\documents\html.py", line 176, in _parse_pages_from_element_tree
element = _parse_tag(tag_elem)
File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\documents\html.py", line 410, in _parse_tag
return _text_to_element(
File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\documents\html.py", line 458, in _text_to_element
elif is_narrative_tag(text, tag):
File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\documents\html.py", line 506, in is_narrative_tag
return tag not in HEADING_TAGS and is_possible_narrative_text(text)
File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\partition\text_type.py", line 77, in is_possible_narrative_text
if exceeds_cap_ratio(text, threshold=cap_threshold):
File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\partition\text_type.py", line 273, in exceeds_cap_ratio
if sentence_count(text, 3) > 1:
File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\partition\text_type.py", line 222, in sentence_count
sentences = sent_tokenize(text)
File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\nlp\tokenize.py", line 30, in sent_tokenize
return sent_tokenize(text)
File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\nltk\tokenize_init.py", line 119, in sent_tokenize
tokenizer = get_punkt_tokenizer(language)
File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\nltk\tokenize_init.py", line 105, in _get_punkt_tokenizer
return PunktTokenizer(language)
File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\nltk\tokenize\punkt.py", line 1744, in init
self.load_lang(lang)
File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\nltk\tokenize\punkt.py", line 1749, in load_lang
lang_dir = find(f"tokenizers/punkt_tab/{lang}/")
File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\nltk\data.py", line 579, in find
raise LookupError(resource_not_found)
LookupError:

---

Resource punkt_tab not found.
Please use the NLTK Downloader to obtain the resource:

import nltk
nltk.download('punkt_tab')

For more information see: https://www.nltk.org/data.html

Attempted to load tokenizers/punkt_tab/english/

Searched in:
- 'C:\Users\Z/nltk_data'
- 'C:\Users\Z\anaconda3\envs\rag1\nltk_data'
- 'C:\Users\Z\anaconda3\envs\rag1\share\nltk_data'
- 'C:\Users\Z\anaconda3\envs\rag1\lib\nltk_data'
- 'C:\Users\Z\AppData\Roaming\nltk_data'
- 'C:\nltk_data'
- 'D:\nltk_data'
- 'E:\nltk_data'

---

50%|██████████████████████████████████████████ | 1/2 [00:27<00:27, 27.18s/it]

[little51]

首次运行时，需要下载自然语言处理工具包，这个过程是自动的。但由于网络原因，往往不能正常下载。解决办法有二：
1、在Python交互式环境下，反复执行以下语句直到成功
import nltk
nltk.download('punkt_tab')

2、从https://www.nltk.org/data.html下载punkt.zip和punkt_tab.zip，解压到以下任何目录。

• 'C:\Users\Z/nltk_data'
• 'C:\Users\Z\anaconda3\envs\rag1\nltk_data'
• 'C:\Users\Z\anaconda3\envs\rag1\share\nltk_data'
• 'C:\Users\Z\anaconda3\envs\rag1\lib\nltk_data'
• 'C:\Users\Z\AppData\Roaming\nltk_data'
• 'C:\nltk_data'
• 'D:\nltk_data'
• 'E:\nltk_data'

目录结构为：

[easychu]

感谢高老师指导！问题还未解决，感觉是不是还有更多的资源要放？我这么想是根据下面两次尝试来的，两次尝试分别描述为一、二两部分。 一、直接放了两个目录并未解决问题。细节： 我按您的指导找了punkt和punkt_tab文件，解压后放到要求的一个目录下，但是执行还是有问题，错误打印如下： (rag1) D:\zhu\tech\RAG\rag1&gt;python rag-demo.py &nbsp; 0%|&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; | 0/2 [00:00<?, ?it/s]Error loading file documents\README1.md &nbsp;50%|██████████████████████████████████████████&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; | 1/2 [00:26<00:26, 26.60s/it]Traceback (most recent call last): &nbsp; File "D:\zhu\tech\RAG\rag1\rag-demo.py", line 92, in <module&gt; &nbsp; &nbsp; documents = load_docs("./documents") &nbsp; File "D:\zhu\tech\RAG\rag1\rag-demo.py", line 24, in load_docs &nbsp; &nbsp; documents = loader.load() &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\langchain_community\document_loaders\directory.py", line 158, in load &nbsp; &nbsp; self.load_file(i, p, docs, pbar) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\langchain_community\document_loaders\directory.py", line 107, in load_file &nbsp; &nbsp; raise e &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\langchain_community\document_loaders\directory.py", line 100, in load_file &nbsp; &nbsp; sub_docs = self.loader_cls(str(item), **self.loader_kwargs).load() &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\langchain_community\document_loaders\unstructured.py", line 87, in load &nbsp; &nbsp; elements = self._get_elements() &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\langchain_community\document_loaders\unstructured.py", line 179, in _get_elements &nbsp; &nbsp; return partition(filename=self.file_path, **self.unstructured_kwargs) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\partition\auto.py", line 397, in partition &nbsp; &nbsp; elements = _partition_md( &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\documents\elements.py", line 518, in wrapper &nbsp; &nbsp; elements = func(*args, **kwargs) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\file_utils\filetype.py", line 591, in wrapper &nbsp; &nbsp; elements = func(*args, **kwargs) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\file_utils\filetype.py", line 546, in wrapper &nbsp; &nbsp; elements = func(*args, **kwargs) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\chunking\__init__.py", line 52, in wrapper &nbsp; &nbsp; elements = func(*args, **kwargs) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\partition\md.py", line 104, in partition_md &nbsp; &nbsp; return partition_html( &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\documents\elements.py", line 518, in wrapper &nbsp; &nbsp; elements = func(*args, **kwargs) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\file_utils\filetype.py", line 591, in wrapper &nbsp; &nbsp; elements = func(*args, **kwargs) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\file_utils\filetype.py", line 546, in wrapper &nbsp; &nbsp; elements = func(*args, **kwargs) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\chunking\__init__.py", line 52, in wrapper &nbsp; &nbsp; elements = func(*args, **kwargs) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\partition\html.py", line 141, in partition_html &nbsp; &nbsp; document_to_element_list( &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\partition\common.py", line 559, in document_to_element_list &nbsp; &nbsp; num_pages = len(document.pages) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\documents\xml.py", line 54, in pages &nbsp; &nbsp; self._pages = self._parse_pages_from_element_tree() &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\documents\html.py", line 176, in _parse_pages_from_element_tree &nbsp; &nbsp; element = _parse_tag(tag_elem) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\documents\html.py", line 410, in _parse_tag &nbsp; &nbsp; return _text_to_element( &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\documents\html.py", line 458, in _text_to_element &nbsp; &nbsp; elif is_narrative_tag(text, tag): &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\documents\html.py", line 506, in is_narrative_tag &nbsp; &nbsp; return tag not in HEADING_TAGS and is_possible_narrative_text(text) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\partition\text_type.py", line 77, in is_possible_narrative_text &nbsp; &nbsp; if exceeds_cap_ratio(text, threshold=cap_threshold): &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\partition\text_type.py", line 273, in exceeds_cap_ratio &nbsp; &nbsp; if sentence_count(text, 3) &gt; 1: &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\partition\text_type.py", line 222, in sentence_count &nbsp; &nbsp; sentences = sent_tokenize(text) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\nlp\tokenize.py", line 30, in sent_tokenize &nbsp; &nbsp; return _sent_tokenize(text) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\nltk\tokenize\__init__.py", line 119, in sent_tokenize &nbsp; &nbsp; tokenizer = _get_punkt_tokenizer(language) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\nltk\tokenize\__init__.py", line 105, in _get_punkt_tokenizer &nbsp; &nbsp; return PunktTokenizer(language) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\nltk\tokenize\punkt.py", line 1744, in __init__ &nbsp; &nbsp; self.load_lang(lang) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\nltk\tokenize\punkt.py", line 1749, in load_lang &nbsp; &nbsp; lang_dir = find(f"tokenizers/punkt_tab/{lang}/") &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\nltk\data.py", line 579, in find &nbsp; &nbsp; raise LookupError(resource_not_found) LookupError: ********************************************************************** &nbsp; Resource punkt_tab not found. &nbsp; Please use the NLTK Downloader to obtain the resource: &nbsp; &gt;&gt;&gt; import nltk &nbsp; &gt;&gt;&gt; nltk.download('punkt_tab') &nbsp; For more information see: https://www.nltk.org/data.html &nbsp; Attempted to load tokenizers/punkt_tab/english/ &nbsp; Searched in: &nbsp; &nbsp; - 'C:\\Users\\Z/nltk_data' &nbsp; &nbsp; - 'C:\\Users\\Z\\anaconda3\\envs\\rag1\\nltk_data' &nbsp; &nbsp; - 'C:\\Users\\Z\\anaconda3\\envs\\rag1\\share\\nltk_data' &nbsp; &nbsp; - 'C:\\Users\\Z\\anaconda3\\envs\\rag1\\lib\\nltk_data' &nbsp; &nbsp; - 'C:\\Users\\Z\\AppData\\Roaming\\nltk_data' &nbsp; &nbsp; - 'C:\\nltk_data' &nbsp; &nbsp; - 'D:\\nltk_data' &nbsp; &nbsp; - 'E:\\nltk_data' ********************************************************************** 二、我按“Attempted to load tokenizers/punkt_tab/english/”把punkt_tab挪到tokenizers目录下面，但是还未解决。细节如下： (rag1) D:\zhu\tech\RAG\rag1&gt;python rag-demo.py &nbsp; 0%|&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; | 0/2 [00:00<?, ?it/s][nltk_data] Downloading package averaged_perceptron_tagger to [nltk_data]&nbsp; &nbsp; &nbsp;C:\Users\Z\anaconda3\envs\rag1\nltk_data... [nltk_data]&nbsp; &nbsp;Unzipping taggers\averaged_perceptron_tagger.zip. Error loading file documents\README1.md &nbsp;50%|██████████████████████████████████████████&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; | 1/2 [00:26<00:26, 26.75s/it]Traceback (most recent call last): &nbsp; File "D:\zhu\tech\RAG\rag1\rag-demo.py", line 92, in <module&gt; &nbsp; &nbsp; documents = load_docs("./documents") &nbsp; File "D:\zhu\tech\RAG\rag1\rag-demo.py", line 24, in load_docs &nbsp; &nbsp; documents = loader.load() &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\langchain_community\document_loaders\directory.py", line 158, in load &nbsp; &nbsp; self.load_file(i, p, docs, pbar) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\langchain_community\document_loaders\directory.py", line 107, in load_file &nbsp; &nbsp; raise e &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\langchain_community\document_loaders\directory.py", line 100, in load_file &nbsp; &nbsp; sub_docs = self.loader_cls(str(item), **self.loader_kwargs).load() &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\langchain_community\document_loaders\unstructured.py", line 87, in load &nbsp; &nbsp; elements = self._get_elements() &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\langchain_community\document_loaders\unstructured.py", line 179, in _get_elements &nbsp; &nbsp; return partition(filename=self.file_path, **self.unstructured_kwargs) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\partition\auto.py", line 397, in partition &nbsp; &nbsp; elements = _partition_md( &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\documents\elements.py", line 518, in wrapper &nbsp; &nbsp; elements = func(*args, **kwargs) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\file_utils\filetype.py", line 591, in wrapper &nbsp; &nbsp; elements = func(*args, **kwargs) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\file_utils\filetype.py", line 546, in wrapper &nbsp; &nbsp; elements = func(*args, **kwargs) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\chunking\__init__.py", line 52, in wrapper &nbsp; &nbsp; elements = func(*args, **kwargs) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\partition\md.py", line 104, in partition_md &nbsp; &nbsp; return partition_html( &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\documents\elements.py", line 518, in wrapper &nbsp; &nbsp; elements = func(*args, **kwargs) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\file_utils\filetype.py", line 591, in wrapper &nbsp; &nbsp; elements = func(*args, **kwargs) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\file_utils\filetype.py", line 546, in wrapper &nbsp; &nbsp; elements = func(*args, **kwargs) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\chunking\__init__.py", line 52, in wrapper &nbsp; &nbsp; elements = func(*args, **kwargs) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\partition\html.py", line 141, in partition_html &nbsp; &nbsp; document_to_element_list( &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\partition\common.py", line 559, in document_to_element_list &nbsp; &nbsp; num_pages = len(document.pages) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\documents\xml.py", line 54, in pages &nbsp; &nbsp; self._pages = self._parse_pages_from_element_tree() &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\documents\html.py", line 176, in _parse_pages_from_element_tree &nbsp; &nbsp; element = _parse_tag(tag_elem) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\documents\html.py", line 410, in _parse_tag &nbsp; &nbsp; return _text_to_element( &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\documents\html.py", line 458, in _text_to_element &nbsp; &nbsp; elif is_narrative_tag(text, tag): &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\documents\html.py", line 506, in is_narrative_tag &nbsp; &nbsp; return tag not in HEADING_TAGS and is_possible_narrative_text(text) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\partition\text_type.py", line 87, in is_possible_narrative_text &nbsp; &nbsp; if "eng" in languages and (sentence_count(text, 3) < 2) and (not contains_verb(text)): &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\partition\text_type.py", line 189, in contains_verb &nbsp; &nbsp; pos_tags = pos_tag(text) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\unstructured\nlp\tokenize.py", line 55, in pos_tag &nbsp; &nbsp; parts_of_speech.extend(_pos_tag(tokens)) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\nltk\tag\__init__.py", line 168, in pos_tag &nbsp; &nbsp; tagger = _get_tagger(lang) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\nltk\tag\__init__.py", line 110, in _get_tagger &nbsp; &nbsp; tagger = PerceptronTagger() &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\nltk\tag\perceptron.py", line 183, in __init__ &nbsp; &nbsp; self.load_from_json(lang) &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\nltk\tag\perceptron.py", line 273, in load_from_json &nbsp; &nbsp; loc = find(f"taggers/averaged_perceptron_tagger_{lang}/") &nbsp; File "C:\Users\Z\anaconda3\envs\rag1\lib\site-packages\nltk\data.py", line 579, in find &nbsp; &nbsp; raise LookupError(resource_not_found) LookupError: ********************************************************************** &nbsp; Resource averaged_perceptron_tagger_eng not found. &nbsp; Please use the NLTK Downloader to obtain the resource: &nbsp; &gt;&gt;&gt; import nltk &nbsp; &gt;&gt;&gt; nltk.download('averaged_perceptron_tagger_eng') &nbsp; For more information see: https://www.nltk.org/data.html &nbsp; Attempted to load taggers/averaged_perceptron_tagger_eng/ &nbsp; Searched in: &nbsp; &nbsp; - 'C:\\Users\\Z/nltk_data' &nbsp; &nbsp; - 'C:\\Users\\Z\\anaconda3\\envs\\rag1\\nltk_data' &nbsp; &nbsp; - 'C:\\Users\\Z\\anaconda3\\envs\\rag1\\share\\nltk_data' &nbsp; &nbsp; - 'C:\\Users\\Z\\anaconda3\\envs\\rag1\\lib\\nltk_data' &nbsp; &nbsp; - 'C:\\Users\\Z\\AppData\\Roaming\\nltk_data' &nbsp; &nbsp; - 'C:\\nltk_data' &nbsp; &nbsp; - 'D:\\nltk_data' &nbsp; &nbsp; - 'E:\\nltk_data' **********************************************************************

…

------------------&nbsp;原始邮件&nbsp;------------------ 发件人: "little51/llm-dev" ***@***.***&gt;; 发送时间:&nbsp;2025年3月16日(星期天) 中午1:53 ***@***.***&gt;; ***@***.******@***.***&gt;; 主题:&nbsp;Re: [little51/llm-dev] 高老师，您好！第12章例程执行出错[nltk_data] Error loading punkt: <urlopen error [Errno 11004] [nltk_data] getaddrinfo failed&gt;，请帮忙看看程序是不是对网络有特殊依赖？ (Issue #5) 首次运行时，需要下载自然语言处理工具包，这个过程是自动的。但由于网络原因，往往不能正常下载。解决办法有二： 1、在Python交互式环境下，反复执行以下语句直到成功 import nltk nltk.download('punkt_tab') 2、从https://www.nltk.org/data.html下载punkt.zip和punkt_tab.zip，解压到以下任何目录。 'C:\Users\Z/nltk_data' 'C:\Users\Z\anaconda3\envs\rag1\nltk_data' 'C:\Users\Z\anaconda3\envs\rag1\share\nltk_data' 'C:\Users\Z\anaconda3\envs\rag1\lib\nltk_data' 'C:\Users\Z\AppData\Roaming\nltk_data' 'C:\nltk_data' 'D:\nltk_data' 'E:\nltk_data' 目录结构为： 1742104336059.png (view on web) — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: ***@***.***&gt; little51 left a comment (little51/llm-dev#5) 首次运行时，需要下载自然语言处理工具包，这个过程是自动的。但由于网络原因，往往不能正常下载。解决办法有二： 1、在Python交互式环境下，反复执行以下语句直到成功 import nltk nltk.download('punkt_tab') 2、从https://www.nltk.org/data.html下载punkt.zip和punkt_tab.zip，解压到以下任何目录。 'C:\Users\Z/nltk_data' 'C:\Users\Z\anaconda3\envs\rag1\nltk_data' 'C:\Users\Z\anaconda3\envs\rag1\share\nltk_data' 'C:\Users\Z\anaconda3\envs\rag1\lib\nltk_data' 'C:\Users\Z\AppData\Roaming\nltk_data' 'C:\nltk_data' 'D:\nltk_data' 'E:\nltk_data' 目录结构为： 1742104336059.png (view on web) — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: ***@***.***&gt;

[little51]

那就是还少averaged_perceptron_tagger.zip和averaged_perceptron_tagger_eng.zip，得用第一种方法反复执行nltk.download('punkt_tab')直到下载成功。