RAG后不能用GPT-4o进行query

[2530909]

将文档进行rag后
engine = SimpleEngine.from_docs(input_dir=DOC_PATH, retriever_configs=[FAISSRetrieverConfig()]).persist(persist_dir)
answer = await engine.aqvery（‘查询内容’）
在/.metagpt/config2.yaml 配置文件中model使用gpt-4-1106-preview  gpt-4-turbo-preview gpt-3.5-turbo-1106都可以正常aquery，GPT-4o不能正常进行

报错如下：
Traceback (most recent call last):
File "C:\Users\xxxxxxx\Desktop\MetaGPT\MetaGPT\metagpt\utils\common.py", line 640, in wrapper
return await func(self, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\xxxxxxx\Desktop\MetaGPT\MetaGPT\metagpt\roles\role.py", line 555, in run
rsp = await self.react()
^^^^^^^^^^^^^^^^^^
ValueError: Calculated available context size -320 was not non-negative.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "C:\Users\xxxxxxx\Desktop\MetaGPT\MetaGPT\metagpt\utils\common.py", line 626, in wrapper
result = await func(self, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\xxxxxxx\Desktop\MetaGPT\MetaGPT\metagpt\team.py", line 131, in run
await self.env.run()
Exception: Traceback (most recent call last):
File "C:\Users\xxxxxxx\Desktop\MetaGPT\MetaGPT\metagpt\utils\common.py", line 640, in wrapper
return await func(self, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\xxxxxxx\Desktop\MetaGPT\MetaGPT\metagpt\roles\role.py", line 555, in run
rsp = await self.react()
^^^^^^^^^^^^^^^^^^
File "C:\Users\xxxxxxx\Desktop\MetaGPT\MetaGPT\metagpt\roles\role.py", line 522, in react
rsp = await self._react()
^^^^^^^^^^^^^^^^^^^
File "C:\Users\xxxxxxx\Desktop\MetaGPT\MetaGPT\metagpt\roles\role.py", line 468, in _react
rsp = await self._act()
^^^^^^^^^^^^^^^^^
File "C:\Users\xxxxxxx\Desktop\MetaGPT\MetaGPT\metagpt\roles\role.py", line 397, in _act
response = await self.rc.todo.run(self.rc.history)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\xxxxxxx\Desktop\MetaGPT\MetaGPT\auto_pentest\pentest_rag\pentest_rag.py", line 71, in run
answer = await engine.aquery(
^^^^^^^^^^^^^^^^^^^^
File "C:\Users\xxxxxxx\Desktop\MetaGPT\MetaGPT.venv\Lib\site-packages\llama_index\core\instrume

[seehi]

Which version are you using, have you tried the main branch?

[2530909]

In version 0.8, I'm using the main branch

Which version are you using, have you tried the main branch?

[seehi]

Is the output normal when executing the following code?

>>> from metagpt.utils.token_counter import TOKEN_MAX
>>> print(TOKEN_MAX["gpt-4o"])
128000

[2530909]

from metagpt.utils.token_counter import TOKEN_MAX
print(TOKEN_MAX["gpt-4o"])
Traceback (most recent call last):
File "C:\Users\xxxxxx\Desktop\MetaGPT\MetaGPT.venv\Lib\site-packages\IPython\core\interactiveshell.py", line 3548, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "", line 1, in
print(TOKEN_MAX["gpt-4o"])
~~~~~~~~~^^^^^^^^^^
KeyError: 'gpt-4o'

执行以下代码时，输出是否正常？

>>> from metagpt.utils.token_counter import TOKEN_MAX
>>> print(TOKEN_MAX["gpt-4o"])
128000

[2530909]

from metagpt.utils.token_counter import TOKEN_MAX print（TOKEN_MAX[“gpt-4o”]） 回溯（最近调用最后一次）：文件“C：\Users\liuqihui\Desktop\MetaGPT\MetaGPT.venv\Lib\site-packages\IPython\core\interactiveshell.py”，第 3548 行，run_code exec（code_obj， self.user_global_ns， self.user_ns） 文件“”，第 1 行，在 print（TOKEN_MAX[“gpt-4o”]） ~~~~~~~~~^^^^^^^^^^ KeyError： 'gpt-4o'

执行以下代码时，输出是否正常？

>>> from metagpt.utils.token_counter import TOKEN_MAX
>>> print(TOKEN_MAX["gpt-4o"])
128000

What kind of question is that

[seehi]

Need to use main branch

[2530909]

What does that mean? What am I supposed to do

Need to use main branch

[seehi]

“Install latest development version” or “Install in development mode”： https://docs.deepwisdom.ai/main/en/guide/get_started/installation.html

[2530909]

I'll try

“Install latest development version” or “Install in development mode”： https://docs.deepwisdom.ai/main/en/guide/get_started/installation.html

[2530909]

I can't install the latest version of metagpt 0.81, and I'm not sure why.

“Install latest development version” 或 “Install in development mode” （安装最新开发版本） 或 “Install in development mode（以开发模式安装）”：https://docs.deepwisdom.ai/main/en/guide/get_started/installation.html