ragflow在鲲鹏服务器上启动出现[root@k8s01 docker]# docker logs -f ragflow-server
Starting nginx...
Starting ragflow_server...
Starting 1 task executor(s) on host '61e1fda06dea'...
2025-07-30 07:27:35,391 INFO 21 ragflow_server log path: /ragflow/logs/ragflow_server.log, log levels: {'peewee': 'WARNING', 'pdfminer': 'WARNING', 'root': 'INFO'}
2025-07-30 07:28:07,339 INFO 21 found 0 gpus
2025-07-30 07:28:10,138 INFO 21 [HUQIE]:Trie file /ragflow/rag/res/huqie.txt.trie not found, build the default trie file
2025-07-30 07:28:10,139 INFO 21 [HUQIE]:Build trie from /ragflow/rag/res/huqie.txt
2025-07-30 07:28:36,500 INFO 21 [HUQIE]:Build trie cache to /ragflow/rag/res/huqie.txt.trie
2025-07-30 07:28:42,050 INFO 21 init database on cluster mode successfully
2025-07-30 07:28:47,514 INFO 21 load_model /ragflow/rag/res/deepdoc/det.onnx uses CPU
2025-07-30 07:28:47,647 INFO 21 load_model /ragflow/rag/res/deepdoc/rec.onnx uses CPU
Traceback (most recent call last):
File "/ragflow/api/ragflow_server.py", line 36, in <module>
from api.apps import app
File "/ragflow/api/apps/__init__.py", line 137, in <module>
client_urls_prefix = [
File "/ragflow/api/apps/__init__.py", line 138, in <listcomp>
register_page(path) for dir in pages_dir for path in search_pages_path(dir)
File "/ragflow/api/apps/__init__.py", line 120, in register_page
spec.loader.exec_module(page)
File "/ragflow/api/apps/api_app.py", line 28, in <module>
from api.db.services.dialog_service import DialogService, chat
File "/ragflow/api/db/services/dialog_service.py", line 36, in <module>
from rag.app.resume import forbidden_select_fields4resume
File "/ragflow/rag/app/resume.py", line 27, in <module>
from deepdoc.parser.resume import step_one, step_two
File "/ragflow/deepdoc/parser/resume/step_two.py", line 26, in <module>
from deepdoc.parser.resume.entities import degrees, schools, corporations
File "/ragflow/deepdoc/parser/resume/entities/corporations.py", line 93, in <module>
GOOD_CORP = set([corpNorm(rmNoise(c), False) for c in GOOD_CORP])
File "/ragflow/deepdoc/parser/resume/entities/corporations.py", line 93, in <listcomp>
GOOD_CORP = set([corpNorm(rmNoise(c), False) for c in GOOD_CORP])
File "/ragflow/deepdoc/parser/resume/entities/corporations.py", line 68, in corpNorm
tks = rag_tokenizer.tokenize(nm).split()
File "/ragflow/rag/nlp/rag_tokenizer.py", line 331, in tokenize
res.extend([self.stemmer.stem(self.lemmatizer.lemmatize(t)) for t in word_tokenize(L)])
File "/ragflow/.venv/lib/python3.10/site-packages/nltk/tokenize/__init__.py", line 142, in word_tokenize
sentences = [text] if preserve_line else sent_tokenize(text, language)
File "/ragflow/.venv/lib/python3.10/site-packages/nltk/tokenize/__init__.py", line 119, in sent_tokenize
tokenizer = _get_punkt_tokenizer(language)
File "/ragflow/.venv/lib/python3.10/site-packages/nltk/tokenize/__init__.py", line 105, in _get_punkt_tokenizer
return PunktTokenizer(language)
File "/ragflow/.venv/lib/python3.10/site-packages/nltk/tokenize/punkt.py", line 1744, in __init__
self.load_lang(lang)
File "/ragflow/.venv/lib/python3.10/site-packages/nltk/tokenize/punkt.py", line 1749, in load_lang
lang_dir = find(f"tokenizers/punkt_tab/{lang}/")
File "/ragflow/.venv/lib/python3.10/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:
- '/root/nltk_data'
- '/ragflow/.venv/nltk_data'
- '/ragflow/.venv/share/nltk_data'
- '/ragflow/.venv/lib/nltk_data'
- '/usr/share/nltk_data'
- '/usr/local/share/nltk_data'
- '/usr/lib/nltk_data'
- '/usr/local/lib/nltk_data'
**********************************************************************
Traceback (most recent call last):
File "/ragflow/rag/svr/task_executor.py", line 57, in <module>
from rag.app import laws, paper, presentation, manual, qa, table, book, resume, picture, naive, one, audio, \
File "/ragflow/rag/app/resume.py", line 27, in <module>
from deepdoc.parser.resume import step_one, step_two
File "/ragflow/deepdoc/parser/resume/step_two.py", line 26, in <module>
from deepdoc.parser.resume.entities import degrees, schools, corporations
File "/ragflow/deepdoc/parser/resume/entities/corporations.py", line 93, in <module>
GOOD_CORP = set([corpNorm(rmNoise(c), False) for c in GOOD_CORP])
File "/ragflow/deepdoc/parser/resume/entities/corporations.py", line 93, in <listcomp>
GOOD_CORP = set([corpNorm(rmNoise(c), False) for c in GOOD_CORP])
File "/ragflow/deepdoc/parser/resume/entities/corporations.py", line 68, in corpNorm
tks = rag_tokenizer.tokenize(nm).split()
File "/ragflow/rag/nlp/rag_tokenizer.py", line 331, in tokenize
res.extend([self.stemmer.stem(self.lemmatizer.lemmatize(t)) for t in word_tokenize(L)])
File "/ragflow/.venv/lib/python3.10/site-packages/nltk/tokenize/__init__.py", line 142, in word_tokenize
sentences = [text] if preserve_line else sent_tokenize(text, language)
File "/ragflow/.venv/lib/python3.10/site-packages/nltk/tokenize/__init__.py", line 119, in sent_tokenize
tokenizer = _get_punkt_tokenizer(language)
File "/ragflow/.venv/lib/python3.10/site-packages/nltk/tokenize/__init__.py", line 105, in _get_punkt_tokenizer
return PunktTokenizer(language)
File "/ragflow/.venv/lib/python3.10/site-packages/nltk/tokenize/punkt.py", line 1744, in __init__
self.load_lang(lang)
File "/ragflow/.venv/lib/python3.10/site-packages/nltk/tokenize/punkt.py", line 1749, in load_lang
lang_dir = find(f"tokenizers/punkt_tab/{lang}/")
File "/ragflow/.venv/lib/python3.10/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:
- '/root/nltk_data'
- '/ragflow/.venv/nltk_data'
- '/ragflow/.venv/share/nltk_data'
- '/ragflow/.venv/lib/nltk_data'
- '/usr/share/nltk_data'
- '/usr/local/share/nltk_data'
- '/usr/lib/nltk_data'
- '/usr/local/lib/nltk_data'
**********************************************************************
最新发布