I have a dataframe(df) and want to give the whole "df" as context to Dolly-7B model and ask any questions from that dataset - it can be simple calculations or insights or aggregation etc.

import torch
from transformers import pipeline
from langchain import PromptTemplate, LLMChain
from langchain.llms import HuggingFacePipeline

Load the dataframe

df = pd.read_csv("./Table.csv")

generate_text = pipeline(model="databricks/dolly-v2-7b", torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto", return_full_text=True)

hf_pipeline = HuggingFacePipeline(pipeline=generate_text)

I am new to language models, can anyone guide me how the code should be written further to ask questions to Dolly and it answer analyzing my dataframe.

Thanks in advance!!