DSPy implemented program of thought since a long time ago and it works great to solve user queries with code.
What is great is that you can define DSPy signature of the type “question, data -> answer” where “data” is a pandas dataframe, then DSPy prompts the llm to answer the question using the data and python code. Extremely powerful.
What is great is that you can define DSPy signature of the type “question, data -> answer” where “data” is a pandas dataframe, then DSPy prompts the llm to answer the question using the data and python code. Extremely powerful.