Replies: 2 comments 1 reply
-
@kchusam I confirm you that with
Hope that works for you! |
Beta Was this translation helpful? Give feedback.
1 reply
-
@kchusam Here's a MRE (minimal reproducible example) adapted from the """Example of using PandasAI with a Pandas DataFrame"""
import pandas as pd
from pandasai import PandasAI
from pandasai.llm import OpenAI
# dummy example dataframe
dataframe = {
"country": [
"United States",
"United Kingdom",
"France",
"Germany",
"Italy",
"Spain",
"Canada",
"Australia",
"Japan",
"China",
],
"gdp": [
19294482071552,
2891615567872,
2411255037952,
3435817336832,
1745433788416,
1181205135360,
1607402389504,
1490967855104,
4380756541440,
14631844184064,
],
"happiness_index": [6.94, 7.16, 6.66, 7.07, 6.38, 6.4, 7.23, 7.22, 5.87, 5.12],
}
df = pd.DataFrame(dataframe)
api_key = 'sk-...' # <-- your OpenAI API key here
llm = OpenAI(api_token=api_key)
pandas_ai = PandasAI(llm, enable_cache=False, enforce_privacy=True)
response = pandas_ai(df, "Calculate the sum of the gdp of north american countries")
print(pandas_ai.last_prompt) Which displays:
The reason why you see the conversational prompt instead is due to the |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
I would like to understand what is really sent to the llm server and how the dataframe schema looks like. How can I do that?
Specially when set enforce_privacy = True, I want to be sure, that only the header is sent
Beta Was this translation helpful? Give feedback.
All reactions