search

geekan / MetaGPT

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
https://deepwisdom.ai/
MIT License
41.33k stars 4.93k forks source link

"researcher" can't run on Ubuntu #1330

Open BlizeGit opened 3 weeks ago

BlizeGit commented 3 weeks ago

Bug description

  1. platform root@qingyi:~/MetaGPT/config# lsb_release -a LSB Version: core-11.1.0ubuntu4-noarch:security-11.1.0ubuntu4-noarch Distributor ID: Ubuntu Description: Ubuntu 22.04.4 LTS Release: 22.04 Codename: jammy

    root@qingyi:~/MetaGPT/config# python3 --version Python 3.10.12

  2. all components are installed successfully with the below command lines: 2.1 git clone https://github.com/geekan/MetaGPT.git cd /your/path/to/MetaGPT pip install -e .

    2.2 pip install -e .[rag]

    2.3 pip install playwright playwright install --with-deps chromium (but this package can't be found with command pip list|grep chromium)

    2.4 pip install metagpt[search-google] pip install metagpt[search-ddg] pip install metagpt[playwright] pip install metagpt[selenium]

  3. configuration root@qingyi:~/MetaGPT/config# cat config2.yaml

    Full Example: https://github.com/geekan/MetaGPT/blob/main/config/config2.example.yaml

    Reflected Code: https://github.com/geekan/MetaGPT/blob/main/metagpt/config2.py

    Config Docs: https://docs.deepwisdom.ai/main/en/guide/get_started/configuration.html

    llm: api_type: "spark"

    对应模型的url 参考 https://www.xfyun.cn/doc/spark/Web.html#_1-%E6%8E%A5%E5%8F%A3%E8%AF%B4%E6%98%8E

    base_url: "ws(s)://spark-api.xf-yun.com/v3.5/chat" app_id: "8888888" api_key: "8888888888" api_secret: "8888888888888" domain: "generalv2" # 取值为 [general,generalv2,generalv3,generalv3.5] 和url一一对应 search: engine: "ddg" browser: engine: "selenium" browser_type: "chrome"

Screenshots or logs root@qingyi:~/MetaGPT# python3 -m metagpt.roles.researcher "tensorflow vs. pytorch" 2024-06-06 17:08:48.182 | INFO | metagpt.const:get_metagpt_package_root:29 - Package root set to /root/MetaGPT 2024-06-06 17:08:55.695 | INFO | main:_act:56 - David(Researcher): to do CollectLinks(David) 2024-06-06 17:08:55.859 | WARNING | tenacity.after:log_it:44 - Finished call to 'metagpt.provider.base_llm.BaseLLM.acompletion_text' after 0.164(s), this was the 1st time calling it. 2024-06-06 17:08:56.472 | WARNING | metagpt.utils.common:wrapper:649 - There is a exception in role's execution, in order to resume, we delete the newest role communication message in the role's memory. Traceback (most recent call last): File "/root/MetaGPT/metagpt/utils/common.py", line 640, in wrapper return await func(self, *args, kwargs) File "/root/MetaGPT/metagpt/roles/role.py", line 550, in run rsp = await self.react() File "/root/MetaGPT/metagpt/roles/researcher.py", line 105, in react msg = await super().react() File "/root/MetaGPT/metagpt/roles/role.py", line 519, in react rsp = await self._react() File "/root/MetaGPT/metagpt/roles/role.py", line 474, in _react rsp = await self._act() File "/root/MetaGPT/metagpt/roles/researcher.py", line 67, in _act links = await todo.run(topic, 4, 4) File "/root/MetaGPT/metagpt/actions/research.py", line 113, in run keywords = await self._aask(SEARCH_TOPIC_PROMPT, [system_text]) File "/root/MetaGPT/metagpt/actions/action.py", line 93, in _aask return await self.llm.aask(prompt, system_msgs) File "/root/MetaGPT/metagpt/provider/base_llm.py", line 152, in aask rsp = await self.acompletion_text(message, stream=stream, timeout=self.get_timeout(timeout)) File "/usr/local/lib/python3.10/dist-packages/tenacity/_asyncio.py", line 88, in async_wrapped return await fn(*args, *kwargs) File "/usr/local/lib/python3.10/dist-packages/tenacity/_asyncio.py", line 47, in call do = self.iter(retry_state=retry_state) File "/usr/local/lib/python3.10/dist-packages/tenacity/init.py", line 314, in iter return fut.result() File "/usr/lib/python3.10/concurrent/futures/_base.py", line 451, in result return self.get_result() File "/usr/lib/python3.10/concurrent/futures/_base.py", line 403, in get_result raise self._exception File "/usr/local/lib/python3.10/dist-packages/tenacity/_asyncio.py", line 50, in call result = await fn(args, kwargs) File "/root/MetaGPT/metagpt/provider/base_llm.py", line 202, in acompletion_text return await self._achat_completion_stream(messages, timeout=self.get_timeout(timeout)) File "/root/MetaGPT/metagpt/provider/spark_api.py", line 76, in _achat_completion_stream async for chunk in response: File "/usr/local/lib/python3.10/dist-packages/sparkai/core/language_models/chat_models.py", line 309, in astream raise e File "/usr/local/lib/python3.10/dist-packages/sparkai/core/language_models/chat_models.py", line 301, in astream assert generation is not None AssertionError

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main return _run_code(code, main_globals, None, File "/usr/lib/python3.10/runpy.py", line 86, in _run_code exec(code, run_globals) File "/root/MetaGPT/metagpt/roles/researcher.py", line 126, in fire.Fire(main) File "/usr/local/lib/python3.10/dist-packages/fire/core.py", line 141, in Fire component_trace = _Fire(component, args, parsed_flag_args, context, name) File "/usr/local/lib/python3.10/dist-packages/fire/core.py", line 466, in _Fire component, remaining_args = _CallAndUpdateTrace( File "/usr/local/lib/python3.10/dist-packages/fire/core.py", line 679, in _CallAndUpdateTrace component = loop.run_until_complete(fn(*varargs, kwargs)) File "/usr/lib/python3.10/asyncio/base_events.py", line 649, in run_until_complete return future.result() File "/root/MetaGPT/metagpt/roles/researcher.py", line 124, in main await role.run(topic) File "/root/MetaGPT/metagpt/utils/common.py", line 662, in wrapper raise Exception(format_trackback_info(limit=None)) Exception: Traceback (most recent call last): File "/root/MetaGPT/metagpt/utils/common.py", line 640, in wrapper return await func(self, *args, *kwargs) File "/root/MetaGPT/metagpt/roles/role.py", line 550, in run rsp = await self.react() File "/root/MetaGPT/metagpt/roles/researcher.py", line 105, in react msg = await super().react() File "/root/MetaGPT/metagpt/roles/role.py", line 519, in react rsp = await self._react() File "/root/MetaGPT/metagpt/roles/role.py", line 474, in _react rsp = await self._act() File "/root/MetaGPT/metagpt/roles/researcher.py", line 67, in _act links = await todo.run(topic, 4, 4) File "/root/MetaGPT/metagpt/actions/research.py", line 113, in run keywords = await self._aask(SEARCH_TOPIC_PROMPT, [system_text]) File "/root/MetaGPT/metagpt/actions/action.py", line 93, in _aask return await self.llm.aask(prompt, system_msgs) File "/root/MetaGPT/metagpt/provider/base_llm.py", line 152, in aask rsp = await self.acompletion_text(message, stream=stream, timeout=self.get_timeout(timeout)) File "/usr/local/lib/python3.10/dist-packages/tenacity/_asyncio.py", line 88, in async_wrapped return await fn(args, kwargs) File "/usr/local/lib/python3.10/dist-packages/tenacity/_asyncio.py", line 47, in call do = self.iter(retry_state=retry_state) File "/usr/local/lib/python3.10/dist-packages/tenacity/init.py", line 314, in iter return fut.result() File "/usr/lib/python3.10/concurrent/futures/_base.py", line 451, in result return self.get_result() File "/usr/lib/python3.10/concurrent/futures/_base.py", line 403, in get_result raise self._exception File "/usr/local/lib/python3.10/dist-packages/tenacity/_asyncio.py", line 50, in call result = await fn(*args, **kwargs) File "/root/MetaGPT/metagpt/provider/base_llm.py", line 202, in acompletion_text return await self._achat_completion_stream(messages, timeout=self.get_timeout(timeout)) File "/root/MetaGPT/metagpt/provider/spark_api.py", line 76, in _achat_completion_stream async for chunk in response: File "/usr/local/lib/python3.10/dist-packages/sparkai/core/language_models/chat_models.py", line 309, in astream raise e File "/usr/local/lib/python3.10/dist-packages/sparkai/core/language_models/chat_models.py", line 301, in astream assert generation is not None AssertionError

shenchucheng commented 3 weeks ago

星火的API报错了，应该是配置有问题，你可以把除了api_key/api_secret以为实际用的配置发下

usamimeri commented 3 weeks ago

image 这里的domain需要和你的url一一对应，你的url是星火3.5，因此domain需要是generalv3.5

BlizeGit commented 3 weeks ago

"你的url是星火3.5，因此domain需要是generalv3.5", 这个正确，根据这个建议修改，且将search的ddg换成serpapi，现在是新的问题。 在将配置修改为： 1717747160791 现在的问题是： 2024-06-07 15:55:09.709 | INFO | metagpt.const:get_metagpt_package_root:29 - Package root set to /root/MetaGPT 2024-06-07 15:55:13.695 | INFO | main:_act:56 - David(Researcher): to do CollectLinks(David) 2024-06-07 15:55:15.052 | WARNING | metagpt.utils.cost_manager:update_cost:49 - Model generalv3.5 not found in TOKEN_COSTS. 2024-06-07 15:55:16.386 | WARNING | metagpt.utils.common:wrapper:649 - There is a exception in role's execution, in order to resume, we delete the newest role communication message in the role's memory. Traceback (most recent call last): File "/root/MetaGPT/metagpt/utils/common.py", line 640, in wrapper return await func(self, *args, **kwargs) File "/root/MetaGPT/metagpt/roles/role.py", line 550, in run rsp = await self.react() File "/root/MetaGPT/metagpt/roles/researcher.py", line 105, in react msg = await super().react() File "/root/MetaGPT/metagpt/roles/role.py", line 519, in react rsp = await self._react() File "/root/MetaGPT/metagpt/roles/role.py", line 474, in _react rsp = await self._act() File "/root/MetaGPT/metagpt/roles/researcher.py", line 67, in _act links = await todo.run(topic, 4, 4) File "/root/MetaGPT/metagpt/actions/research.py", line 137, in run prompt = reduce_message_length(gen_msg(), model_name, system_text, config.llm.max_token) File "/root/MetaGPT/metagpt/utils/text.py", line 26, in reduce_message_length max_token = TOKEN_MAX.get(model_name, 2048) - count_output_tokens(system_text, model_name) - reserved File "/root/MetaGPT/metagpt/utils/token_counter.py", line 366, in count_output_tokens encoding = tiktoken.encoding_for_model(model) File "/usr/local/lib/python3.10/dist-packages/tiktoken/model.py", line 103, in encoding_for_model return get_encoding(encoding_name_for_model(model_name)) File "/usr/local/lib/python3.10/dist-packages/tiktoken/model.py", line 86, in encoding_name_for_model if model_name.startswith(model_prefix): AttributeError: 'NoneType' object has no attribute 'startswith'

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main return _run_code(code, main_globals, None, File "/usr/lib/python3.10/runpy.py", line 86, in _run_code exec(code, run_globals) File "/root/MetaGPT/metagpt/roles/researcher.py", line 126, in fire.Fire(main) File "/usr/local/lib/python3.10/dist-packages/fire/core.py", line 141, in Fire component_trace = _Fire(component, args, parsed_flag_args, context, name) File "/usr/local/lib/python3.10/dist-packages/fire/core.py", line 466, in _Fire component, remaining_args = _CallAndUpdateTrace( File "/usr/local/lib/python3.10/dist-packages/fire/core.py", line 679, in _CallAndUpdateTrace component = loop.run_until_complete(fn(*varargs, *kwargs)) File "/usr/lib/python3.10/asyncio/base_events.py", line 649, in run_until_complete return future.result() File "/root/MetaGPT/metagpt/roles/researcher.py", line 124, in main await role.run(topic) File "/root/MetaGPT/metagpt/utils/common.py", line 662, in wrapper raise Exception(format_trackback_info(limit=None)) Exception: Traceback (most recent call last): File "/root/MetaGPT/metagpt/utils/common.py", line 640, in wrapper return await func(self, args, **kwargs) File "/root/MetaGPT/metagpt/roles/role.py", line 550, in run rsp = await self.react() File "/root/MetaGPT/metagpt/roles/researcher.py", line 105, in react msg = await super().react() File "/root/MetaGPT/metagpt/roles/role.py", line 519, in react rsp = await self._react() File "/root/MetaGPT/metagpt/roles/role.py", line 474, in _react rsp = await self._act() File "/root/MetaGPT/metagpt/roles/researcher.py", line 67, in _act links = await todo.run(topic, 4, 4) File "/root/MetaGPT/metagpt/actions/research.py", line 137, in run prompt = reduce_message_length(gen_msg(), model_name, system_text, config.llm.max_token) File "/root/MetaGPT/metagpt/utils/text.py", line 26, in reduce_message_length max_token = TOKEN_MAX.get(model_name, 2048) - count_output_tokens(system_text, model_name) - reserved File "/root/MetaGPT/metagpt/utils/token_counter.py", line 366, in count_output_tokens encoding = tiktoken.encoding_for_model(model) File "/usr/local/lib/python3.10/dist-packages/tiktoken/model.py", line 103, in encoding_for_model return get_encoding(encoding_name_for_model(model_name)) File "/usr/local/lib/python3.10/dist-packages/tiktoken/model.py", line 86, in encoding_name_for_model if model_name.startswith(model_prefix): AttributeError: 'NoneType' object has no attribute 'startswith'

["tensorflow", "pytorch"]

BlizeGit commented 1 week ago

现在换成了openai，出现问题如下 1719218698217 1719218698222