custom_prompts using the new Prompt classes

[RoyKulik]

I previously overriden the default prompt using this class:

from pandasai.prompts.base import Prompt

class CustomGeneratePythonCodePrompt(Prompt):
    """Prompt to generate Python code"""

    text: str = """
You are provided with the following pandas DataFrames with the following metadata:

{dataframes}

This is the initial python code to be updated:
```python
# TODO import all the dependencies required
{default_import}

# Analyze the data
# Merge tables only if data is needed from different tables. When merging merge all the 3 tables.
# It is extremely important to merge only when needed to avoid misleading results.
# 1. Prepare: Preprocessing and cleaning data
# 2. Process: Manipulating data for analysis (grouping, filtering, aggregating, etc.)
# 3. Analyze: Conducting the actual analysis (if the user asks to create a chart save it to an image in exports/charts/temp_chart.png and do not show the chart.)
# 4. Output: return a dictionary of:
# - type (possible values "text", "number", "dataframe", "plot")
# - value (can be a string, a dataframe or the path of the plot, NOT a dictionary)
# Example output: {{ "type": "text", "value": "The average loan amount is $15,000." }}
# Another example output: {{ "type": "dataframe", "value": computed_df }}
# The code should consider only 1 thing to return (text, number, dataframe, plot)
# 5. Make sure you use the right variable name in the return statement
# 6. If you are not sure about the type that should be generated decide it yourself
def analyze_data(dfs: list[{engine_df_name}]) -> dict:
   # Code goes here (do not add comments)
    
# Declare a result variable
result = analyze_data(dfs)

Using the provided dataframes (`dfs`), update the python code based on the last user question:
{conversation}
In case of plot make the figures wide.

Updated code:
"""  # noqa: E501

    def __init__(self):
        default_import = "import pandas as pd"
        engine_df_name = "pd.DataFrame"

        self.set_var("default_import", default_import)
        self.set_var("engine_df_name", engine_df_name)

Im trying to reimplement it using the new version but bit confused about how it should be done using the new prompt classes.
Will apprecaite any help