使用腾讯云的deepseek-r1模型报错Exception:[Errno 2] No such file or directory: '/opt/maxkb-app/model/tokenizer/models--bert-base-cased/refs/main'

MaxKB
1

image
image1437×969 228 KB

如图
查看maxkb.log
报错日志为：
_write_context(node_variable, workflow_variable, node, workflow, answer, reasoning_content)
File “/opt/00001/ccc3513/MaxKB/apps/application/flow/step_node/ai_chat_step_node/impl/base_chat_node.py”, line 35, in _write_context
message_tokens = chat_model.get_num_tokens_from_messages(node_variable.get(‘message_list’))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “/opt/00001/ccc3513/MaxKB/apps/models_provider/impl/base_chat_open_ai.py”, line 112, in get_num_tokens_from_messages
tokenizer = TokenizerManage.get_tokenizer()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “/opt/00001/ccc3513/MaxKB/apps/common/config/tokenizer_manage_config.py”, line 28, in get_tokenizer
with open(f"{model_path}/refs/main", encoding=“utf-8”) as f: snapshot = f.read()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
FileNotFoundError: [Errno 2] No such file or directory: ‘/opt/maxkb-app/model/tokenizer/models–bert-base-cased/refs/main’

2

NotImplementedError: get_num_tokens_from_messages() is not presently implemented for model deepseek-r1. See https://platform.openai.com/docs/guides/text-generation/managing-tokens for information on how messages are converted to tokens.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File “/opt/00001/ccc3513/MaxKB/apps/models_provider/impl/openai_model_provider/model/llm.py”, line 47, in get_num_tokens_from_messages
return super().get_num_tokens_from_messages(messages)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “/opt/00001/ccc3513/MaxKB/apps/models_provider/impl/base_chat_open_ai.py”, line 112, in get_num_tokens_from_messages
tokenizer = TokenizerManage.get_tokenizer()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “/opt/00001/ccc3513/MaxKB/apps/common/config/tokenizer_manage_config.py”, line 28, in get_tokenizer
with open(f"{model_path}/refs/main", encoding=“utf-8”) as f: snapshot = f.read()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
FileNotFoundError: [Errno 2] No such file or directory: ‘/opt/maxkb-app/model/tokenizer/models–bert-base-cased/refs/main’

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File “/opt/00001/ccc3513/MaxKB/apps/application/flow/workflow_manage.py”, line 427, in hand_event_node_result
for r in result:
File “/opt/00001/ccc3513/MaxKB/apps/application/flow/step_node/ai_chat_step_node/impl/base_chat_node.py”, line 92, in write_context_stream
_write_context(node_variable, workflow_variable, node, workflow, answer, reasoning_content)
File “/opt/00001/ccc3513/MaxKB/apps/application/flow/step_node/ai_chat_step_node/impl/base_chat_node.py”, line 35, in _write_context
message_tokens = chat_model.get_num_tokens_from_messages(node_variable.get(‘message_list’))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “/opt/00001/ccc3513/MaxKB/apps/models_provider/impl/openai_model_provider/model/llm.py”, line 49, in get_num_tokens_from_messages
tokenizer = TokenizerManage.get_tokenizer()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “/opt/00001/ccc3513/MaxKB/apps/common/config/tokenizer_manage_config.py”, line 28, in get_tokenizer
with open(f"{model_path}/refs/main", encoding=“utf-8”) as f: snapshot = f.read()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
FileNotFoundError: [Errno 2] No such file or directory: ‘/opt/maxkb-app/model/tokenizer/models–bert-base-cased/refs/main’

补全一下报错信息，哪个大佬给看看呢

3

什么部署方式，什么版本？

4

2.0.0的版本，部署方式是源码部署，但未改动源码

5

源码相关的问题自己检查下吧，每个人编程能力和开发环境都不同，项目组没有精力一一协助分析解决

6

好的 这块把分词模型放到对应目录下就行了 感谢回复