本地部署agent时，报错Fatal Python error: _Py_HashRandomization_Init: failed to get random numbers to initialize Python

[lllLllori]

使用的是anaconda的虚拟环境，pythonpath环境变量也添加了modelscopeagent的路径

[mushenL]

您好，本地部署可以参考这个文档 https://github.com/modelscope/modelscope-agent/blob/master/docs/local_deploy.md 请问您具体是在那个环节报的错，方便提供一下相应的参数我们这边复现一下为您定位？

[lllLllori]

你好，我主要参考这篇文章进行本地部署https://tianchi.aliyun.com/forum/post/641455?t=1708935285270，可以运行app.py。但是打开页面后会报如上的错误导致无法对话

[lllLllori]

这是我的报错信息，我删除了部分INFO 2024-02-26 16:20:28,836 - modelscope - INFO - PyTorch version 2.2.1 Found. 2024-02-26 16:20:28,840 - modelscope - INFO - Loading ast index from C:\Users\lenovo.cache\modelscope\ast_indexer 2024-02-26 16:20:29,044 - modelscope - INFO - Loading done! Current index file version is 1.12.0, with md5 9db3b0eca2da1eb205e4bf56bc262664 and a total number of 964 components indexed Running on local URL: http://127.0.0.1:7860

To create a public link, set share=True in launch(). 2024-02-26 16:20:31.263 - modelscope-agent - INFO - | message: builder_cfg | uuid: local_user | details: {'builder_cfg': "Config (path: /tmp/agentfabric\config\builder_config.json): {'name': '保险agent', 'avatar': 'custom_bot_avatar.png', 'description': '保险领域专业人士，负责对保险理赔进行分析处理', 'instruction': '分析保险责任，计算理赔金额。', 'prompt_recommend': ['你可以做什么？', '你有 什么功能？', '如何使用你的功能？', '能否给我一些示例指令？'], 'knowledge': [], 'tools': {'image_gen': {'name': 'Wanx Image Generation', 'is_active': True, 'use': False, 'is_remote_tool': True}, 'code_interpreter': {'name': 'Code Interpreter', 'is_active': True, 'use': True, 'is_remote_tool': False, 'max_output': 2000}, 'web_browser': {'name': 'Web Browsing', 'is_active': True, 'use': False, 'max_browser_length': 2000}, 'amap_weather': {'name': '高德天气', 'is_active': True, 'use': False}, 'wordart_texture_generation': {'name': '艺术字纹理生成', 'is_active': True, 'use': False}, 'paraformer_asr': {'name': 'Paraformer语音识别', 'is_active': True, 'use': False, 'is_remote_tool': True}, 'sambert_tts': {'name': 'Sambert语音合成', 'is_active': True, 'use': False, 'is_remote_tool': True}, 'web_search': {'name': 'Web Searching', 'is_active': True, 'use': False, 'searcher': 'bing'}, 'qwen_vl': {'name': 'Qwen-VL识图', 'is_active': True, 'use': False}, 'style_repaint': {'name': '人物风格重绘', 'is_active': True, 'use': False}, 'image_enhancement': {'name': '追影-放大镜', 'is_active': True, 'use': False}, 'text-address': {'name': '地址解析', 'url': 'https://api-inference.modelscope.cn/api-inference/v1/models/damo/mgeo_geographic_elements_tagging_chinese_base', 'use': False, 'is_active': True, 'is_remote_tool': True}, 'speech-generation': {'name': '语音生成', 'url': 'https://api-inference.modelscope.cn/api-inference/v1/models/damo/speech_sambert-hifigan_tts_zh-cn_16k', 'use': False, 'is_active': True, 'is_remote_tool': True}, 'video-generation': {'name': '视频生成', 'url': 'https://api-inference.modelscope.cn/api-inference/v1/models/damo/text-to-video-synthesis', 'use': False, 'is_active': True, 'is_remote_tool': True}}, 'model': 'qwen-max', 'language': 'zh'}"} | step: | error: 2024-02-26 16:20:31.327 - modelscope-agent - INFO - | message: using model qwen-max | uuid: local_user | details: {'model_config': {'type': 'dashscope', 'model': 'qwen-max', 'length_constraint': {'knowledge': 4000, 'input': 6000}, 'generate_cfg': {'use_raw_prompt': True, 'top_p': 0.5, 'stop': 'Observation'}}} | step: | error: INFO: kernel process's PID = 13524 Fatal Python error: _Py_HashRandomization_Init: failed to get random numbers to initialize Python Python runtime state: preinitialized

[mushenL]

您好，可以提供一下您的python环境以及操作系统吗？根据您提供的文档，您是运行app.py之后报错，还是运行了将appBot.py改名为app.py之后报的错？从您这边提供的报错信息来看是您的Python在尝试初始化哈希随机化时遇到了问题，可能是系统权限问题或者环境依赖问题，您可以实时用部署文档中提供的modelscope-agent镜像拉起来的容器部署一下试试？

[lllLllori]

在执行本地部署第二步sudo nvidia-docker run -ti --net host -v /data/work:/data/work registry.cn-hangzhou.aliyuncs.com/modelscope-repo/modelscope-agent:v0.3.0 bash的时候报错了： docker: Error response from daemon: failed to create task for container: failed to create shim task: OCI runtime create failed: runc create failed: unable to start container process: error during container init: error running hook #0: error running hook: exit status 1, stdout: , stderr: Auto-detected mode as 'legacy' nvidia-container-cli: initialization error: load library failed: /usr/lib/wsl/drivers/nvlti.inf_amd64_b169173487045715/libnvidia-ml.so.1: file too short: unknown. ERRO[0000] error waiting for container: context canceled

[zzhangpurdue]

看起来是环境的问题，是否可以考虑千万modelscope的免费notebook上使用。 或者重新装一个conda环境用python 3.9？