The following improvements are made to the Python REPL Tool:
1) Improved the sanitization of query (using regex), by removing python command (since gpt-3.5-turbo sometimes assumes python console as a terminal, and runs python command first which causes error). Also sometimes 1 line python codes contain single backticks.
(i) Eg of python in query:
> Entering new LLMMathChain chain...
1291.25 * 6
```python
print(1291.25 * 6)

```
(ii) Eg of 1 line query with single backtick:
Thought:I have the number of unique Account IDs, but I need to count the number of active accounts
Action: python_repl_ast
Action Input: `len(df[df['Status'] == 'Active'])`

2) Improved the capturing of print by redirecting stdout to output of Python REPL Tool (without cluttering the actual stdout).

3) Made sure the exception format type is returned in all cases, when the exec() function throws an exception.

Updated formatting by running the "poetry run black ." command.