Bulk Create for Datasets

pip install requests

import os
import requests
import json

BASE_URL = "https://orch.zenbase.ai/api"
API_KEY = "YOUR API KEY"

def api_call(method, endpoint, data=None, files=None):
    url = f"{BASE_URL}/{endpoint}"
    headers = {"Authorization": f"Api-Key {API_KEY}"}
    response = requests.request(method, url, headers=headers, data=data, files=files)
    return response

dataset_data = {
    "name": "My Bulk Dataset",
    "description": "Dataset for bulk creation example",
    "embedding_type": "OPENAI",  # Optional: if you want to use embeddings
    "embedding_api_key": "YOUR_OPENAI_API_KEY",  # Optional: if using embeddings
    "model_name": "text-embedding-3-small"  # Optional: if using embeddings
}

dataset = api_call("POST", "datasets/", dataset_data)
dataset_id = dataset.json()['id']
print(f"Created dataset with ID: {dataset_id}")

bulk_data = [
    {
        "dataset": dataset_id,
        "inputs": {
            "text": "This movie was fantastic!",
            "rating": 5
        },
        "outputs": {
            "sentiment": "positive"
        }
    },
    {
        "dataset": dataset_id,
        "inputs": {
            "text": "I didn't enjoy this film at all.",
            "rating": 1
        },
        "outputs": {
            "sentiment": "negative"
        }
    },
    {
        "dataset": dataset_id,
        "inputs": {
            "text": "The movie was okay, nothing special.",
            "rating": 3
        },
        "outputs": {
            "sentiment": "neutral"
        }
    }
]

# Save bulk data to a file
bulk_file_path = "./bulk_items.json"
with open(bulk_file_path, 'w') as f:
    json.dump(bulk_data, f, indent=2)

# Create a dictionary with the uploaded file opened in binary mode
files = {"file": open(bulk_file_path, "rb")}

# Set the mode for bulk create (optional)
data = {"mode": "upsert"}  # Options: "insert" or "upsert" or "replace"

# Submit the bulk create request
bulk_create = api_call(
    "POST",
    f"datasets/{dataset_id}/bulk_create/",
    data=data,
    files=files
)

# Get the bulk create task ID
bulk_create_task_id = bulk_create.json()['bulk_create_task_id']
print(f"Created bulk create task with ID: {bulk_create_task_id}")