Hi, I'm looking for something I can use to construct a pipeline where the LLM can construct SQL queries and execute them, then save the results into a pandas dataframe in memory and construct and execute code to produce new dataframe(s) or results from the generated dataframes

For example:
"Calculate net income by month for 2024 and show me the months where I lost money along with the loss"

• LLM constructs a plan for two sql queries to get revenue by month, expense by month
• Execute queries and save into two separate dataframes
• LLM can construct Pandas code, given the two dataframes, to join them and get the loss for each month
• Execute the code, get the result dataframe

Is this possible with LlamaIndex?

hi im trying to understand what llamaparse does
is it using a public vision language model like gpt, claude so the data goes there? is it something closed source that llamaindex has built themselves?

i'm asking due to compliance reasons as im working with enterprise data

thanks!