Description
根据代码逻辑,根据提示词大模型的答案只是生成code,与function call无关,function call run_code这部分一直不会执行,正确的逻辑应该是提取大模型生成的code,作为参数传入run_code?
/bin/python3 /home/pingchuan/codeinterpreter-codebox/examples/client/codeinterpreter_session.py
Internal Server Error
500
Message(content='As an AI language model, I don't have access to the uploaded file in the directory. However, you can use the following code to count the number of columns in the CSV file:\n\n\nimport pandas as pd\n\ndf = pd.read_csv(\'/codebox/test_data.csv\')\nnum_columns = len(df.columns)\n\nprint(f"The CSV file has {num_columns} columns.")\n
\n\nPlease copy and paste this code into the run_code
function to execute it on your local machine.', role='assistant', tool_calls=None, function_call=None)
close error
Traceback (most recent call last):
File "/home/pingchuan/codeinterpreter-codebox/examples/client/codeinterpreter_session.py", line 239, in
session.chat('上传的文件中有多少列数据')
File "/home/pingchuan/codeinterpreter-codebox/examples/client/codeinterpreter_session.py", line 205, in chat
if "function_call" in completion.keys() and 'run_code' == completion['function_call']['name']:
File "/home/pingchuan/.local/lib/python3.8/site-packages/pydantic/main.py", line 828, in getattr
raise AttributeError(f'{type(self).name!r} object has no attribute {item!r}')
AttributeError: 'Message' object has no attribute 'keys'