Dataset

You can checkout the colab notebook to quickly get started with the FutureAGI Dataset.

Installing FutureAGI SDK

pip install futureagi

Initializing FutureAGI Dataset

from fi.datasets import Dataset

dataset = Dataset(fi_api_key="<your_api_key>", 
                  fi_secret_key="<your_api_secret>") # Optional, if you want to set the API key and secret key manually

Create a Dataset

from fi.datasets import Dataset, DatasetConfig, ModelTypes
from fi.datasets.models import Column, Row, Cell, DataTypeChoices, SourceChoices
import uuid

# Create a dataset configuration
config = DatasetConfig(
    id=None,  # Will be set by the server
    name="my_dataset",  # Choose a unique name
    model_type=ModelTypes.GENERATIVE_LLM
)

# Initialize and create the dataset
dataset = Dataset(dataset_config=config)
dataset = dataset.create()

Add Columns to Dataset

# Define columns
columns = [
    Column(
        name="Name",
        data_type=DataTypeChoices.TEXT,
        source=SourceChoices.OTHERS,
        source_id=None,
    ),
    Column(
        name="Age",
        data_type=DataTypeChoices.INTEGER,
        source=SourceChoices.OTHERS,
        source_id=None,
    ),
    Column(
        name="AUDIO_URLS",
        data_type=DataTypeChoices.AUDIO,
        source=SourceChoices.OTHERS,
        source_id=None
    )
]

# Add columns to dataset
dataset = dataset.add_columns(columns=columns)

Add Rows to Dataset

# Define rows with cells
rows = [
    Row(
        order=1,
        cells=[
            Cell(column_name="Name", value="Alice"),
            Cell(column_name="Age", value=25),
            Cell(column_name="AUDIO_URLS", value="https://example.com/audio1.mp3")
        ],
    ),
    Row(
        order=2,
        cells=[
            Cell(column_name="Name", value="Bob"),
            Cell(column_name="Age", value=30),
            Cell(column_name="AUDIO_URLS", value="https://example.com/audio2.mp3")
        ],
    ),
]

# Add rows to dataset
dataset = dataset.add_rows(rows=rows)

Download Dataset

# Download dataset to a CSV file
file_path = "my_dataset.csv"
dataset.download(file_path=file_path)

# Read the downloaded file
with open(file_path, "r") as file:
    content = file.read()
    print(content)

Delete Dataset

# Delete the dataset
dataset.delete()

import os

if os.path.exists(file_path):
    os.remove(file_path)