Datasets

import requests
import json

# Query dataset rows
response = requests.post(
    f"https://api.helicone.ai/v1/helicone-dataset/{dataset_id}/query",
    headers={"Authorization": f"Bearer {HELICONE_API_KEY}"},
    json={"limit": 1000, "offset": 0}
)

rows = response.json()

# Format for fine-tuning
training_data = []
for row in rows:
    # Fetch full request/response from signed URL
    data = requests.get(row['signed_url']).json()
    training_data.append({
        "messages": data['request']['messages']
    })

# Save as JSONL
with open('training_data.jsonl', 'w') as f:
    for item in training_data:
        f.write(json.dumps(item) + '\n')

// Create evaluation datasets for different capabilities
const evalDatasets = {
  reasoning: {
    name: 'Complex Reasoning',
    description: 'Multi-step problems with verified solutions',
    requestIds: [] // Add IDs of reasoning examples
  },
  extraction: {
    name: 'Data Extraction',
    description: 'Structured data extraction with known correct outputs',
    requestIds: [] // Add IDs of extraction examples
  },
  creativity: {
    name: 'Creative Writing',
    description: 'Creative writing with human-rated quality scores',
    requestIds: [] // Add IDs of creative examples
  }
};

// Use these to:
// - Compare model versions before deploying
// - Test prompt changes against consistent examples
// - Identify model weaknesses and blind spots

# Export dataset with metadata for research
import pandas as pd

rows = query_dataset(dataset_id)
df = pd.DataFrame(rows)

# Add analysis columns
df['response_length'] = df['assistant_response'].str.len()
df['prompt_complexity'] = df['user_message'].apply(calculate_complexity)
df['contains_code'] = df['assistant_response'].str.contains('```')

# Export for analysis
df.to_csv('research_dataset.csv', index=False)

# Generate statistics
stats = df.groupby('model').agg({
    'cost': 'sum',
    'prompt_tokens': 'mean',
    'completion_tokens': 'mean'
})
print(stats)