Open NehaKoppikar opened 6 days ago
Hello @NehaKoppikar! I'm here to help you with any issues, questions, or contributions you have. Whether it's a bug or a query, feel free to ask me anything.
To resolve the ImportError
when trying to import the Agent
class from the pandasai
library, ensure that you are importing it correctly from the pandasai.agent
module. The correct import statement should be:
from pandasai.agent import Agent
This import statement should work as long as the pandasai
library is properly installed and the pandasai/agent/agent.py
file contains the Agent
class definition. If you are still encountering issues, make sure that the pandasai
library is installed in your environment. You can install it using pip if it is not already installed:
pip install pandasai
Additionally, you can refer to the unit tests provided in the tests/unit_tests/agent/test_agent.py
file to ensure that your setup is correct. The tests include various scenarios for initializing and using the Agent
class, which can help you verify that the class is being imported and used correctly in your environment [1][2][3].
To continue talking to Dosu, mention @dosu.
System Info
OS Version: 14.4.1 Python Version: 3.9.7 PandasAI version: 0.2.2
🐛 Describe the bug
Unable to import Agent
Code used: import os import pandas as pd from pandasai import Agent
Sample DataFrame
sales_by_country = pd.DataFrame({ "country": ["United States", "United Kingdom", "France", "Germany", "Italy", "Spain", "Canada", "Australia", "Japan", "China"], "sales": [5000, 3200, 2900, 4100, 2300, 2100, 2500, 2600, 4500, 7000] })
By default, unless you choose a different LLM, it will use BambooLLM.
You can get your free API key signing up at https://pandabi.ai (you can also configure it in your .env file)
os.environ["PANDASAI_API_KEY"] = ""
agent = Agent(sales_by_country) response = agent.chat('write insight about data') print(response)