Screen 10,000 Rows

Add the FutureSearch connector if you haven't already. Then upload the FDA product recalls CSV and ask Claude:

Screen this FDA product recalls dataset to find recalls of products that I might have used for my child born on 2021-08-01.

Go to futuresearch.ai/app, upload the FDA product recalls CSV, and enter:

Screen this FDA product recalls dataset to find recalls of products that I might have used for my child born on 2021-08-01.

Screening is binary classification: set categories=["yes", "no"] and only passing rows are returned.

pip install futuresearch
export FUTURESEARCH_API_KEY=your_key_here  # Get one at futuresearch.ai/app/api-key

import asyncio
import pandas as pd
from futuresearch import create_session
from futuresearch.ops import classify

fda_recalls = pd.read_csv("fda_product_recalls.csv")
fda_recalls["center_classification_date"] = pd.to_datetime(
    fda_recalls["center_classification_date"], errors="coerce"
)
fda_recalls = fda_recalls[
    fda_recalls["center_classification_date"] > pd.Timestamp("2021-08-01")
]

async def main():
    async with create_session(name="FDA Recall Screening") as session:
        result = await classify(
            task="Find recalls of products that I might have used for my child born on 2021-08-01.",
            categories=["yes", "no"],
            input=fda_recalls,
        )
        return result.data

results = asyncio.run(main())