The method leverages a query string provided by the user to generate a filter condition based on the columns of the CSV file. This condition is used to extract relevant data from the CSV and return it in a structured format. The filtering logic is generated by an external LLM (Large Language Model) client, which receives a prompt based on the CSV’s structure.

​
Example

This method is part of the CsvHandler class, which handles CSV file operations, and is specifically designed to search through the data in the CSV file based on a user-defined query. To use OpenAI models, you’ll need to create an OpenAI account and get an API key. For more details refer here.
Set up a OpenAI API key as an environmental variable and run the following code. 
 export OPENAI_API_KEY = "**************************"
csv_handler.py
import asyncio

from superagentx_handlers.csv_cli import CsvHandler
from superagentx.llm import LLMClient


async def search(query):
    input_path = "<File_path>"
    llm_config = {'llm_type': 'openai'}
    llm_client = LLMClient(llm_config=llm_config)
    csv_handler = CsvHandler(
        file_path=input_path,
        llm_client=llm_client
    )
    return await csv_handler.search(query)


async def main(query):
    res = await search(query)
    print(res)

if __name__ == '__main__':
    query="who are all Petroleum engineer"
    asyncio.run(main(query))

​
Result

csv cli
{
    "Index": {
        "59": 60
    },
    "User Id": {
        "59": "0f8deedb629A5f6"
    },
    "First Name": {
        "59": "Grace"
    },
    "Last Name": {
        "59": "Phelps"
    },
    "Sex": {
        "59": "Male"
    },
    "Email": {
        "59": "clarkeangela@example.net"
    },
    "Phone": {
        "59": "(034)867-8827x6777"
    },
    "Date of birth": {
        "59": "1909-10-15"
    },
    "Job Title": {
        "59": "Petroleum engineer"
    }
}