argilla

import argilla as rg import os # Initialize Argilla client. It looks for ARGILLA_API_URL and ARGILLA_API_KEY in environment variables. # For local Argilla server, defaults are typically http://localhost:6900 and 'argilla.apikey'. # For Argilla Cloud, you'd typically set these env vars and potentially ARGILLA_WORKSPACE. # If env vars are not set, you can pass them directly: rg.init( api_url=os.environ.get("ARGILLA_API_URL", "http://localhost:6900"), api_key=os.environ.get("ARGILLA_API_KEY", "argilla.apikey"), # workspace=os.environ.get("ARGILLA_WORKSPACE", None) # Uncomment for Argilla Cloud ) dataset_name = "my_first_argilla_text_dataset" # Create a list of simple text records records = [ rg.TextRecord( text="This is my first text record for Argilla.", metadata={"source": "quickstart"}, # You can add predictions for classification, regression, etc. # predictions=[("label_A", 0.9), ("label_B", 0.1)] ), rg.TextRecord( text="Argilla helps with data annotation and LLM fine-tuning.", metadata={"source": "docs_example"}, ) ] try: # Check if dataset exists; if not, log the records existing_dataset = rg.load(name=dataset_name) print(f"Dataset '{dataset_name}' already exists with {len(existing_dataset)} records.") # You might want to append new records or clear it first depending on the use case # rg.log(records=records, name=dataset_name) # To append except Exception: # Catches argilla.errors.NotFoundError (or a more general Exception if not specifically handled) print(f"Dataset '{dataset_name}' not found. Creating and logging new records.") # Log the records. If the dataset doesn't exist, it will be created. # For TextRecord, the default task type is 'TextClassification' if not specified. rg.log(records=records, name=dataset_name) print(f"Logged {len(records)} records to dataset '{dataset_name}'.") # Example of loading the dataset # dataset = rg.load(name=dataset_name) # print(f"Successfully loaded dataset '{dataset_name}' with {len(dataset)} records.")