Skip to main content

Your First API Call

Let's test your Heimdall connection with a simple API call to the Unstructured Suite for text analysis.

Prerequisites​

Test with Text Analysis​

Here's a simple example to analyze some text using your unstructured API key:

import requests

# Your API credentials
url = 'https://read.heimdallapp.org/read/v1/api/process'
headers = {
    'X-api-key': 'YOUR-UNSTRUCTURED-API-KEY',
    'X-username': 'YOUR-USERNAME'
}

# Sample text to analyze
data = {
    "text": "Heimdall is an amazing machine learning platform that makes data science simple and accessible for everyone."
}

# Make the API call and get the response
response = requests.post(url, headers=headers, json=data)
result = response.json()

print(result)

Expected Response​

You should receive a comprehensive JSON response with detailed text analysis:

{
  "length": 108,
  "word_count": 17,
  "oov_ratio": 0.17647058823529413,
  "oov_ratio_2": 0.29411764705882354,
  "sentence_count": 1,
  "avg_word_length": 5.470588235294118,
  "avg_sentence_length": 17,
  "noun_count": 7,
  "verb_count": 3,
  "adjective_count": 2,
  "adverb_count": 0,
  "pronoun_count": 0,
  "stopword_count": 5,
  "tfidf_top1": "accessible",
  "tfidf_top2": "amazing",
  "tfidf_top3": "data",
  "sentiment": "positive",
  "compound_sentiment_score": 0.5859
}
Common Issues

401 Unauthorized - Check your API key and username, ensure headers are correctly formatted

422 Unprocessable Entity - Verify your request body structure, check that text doesn't contain line breaks or double quotes

500 Internal Server Error - Contact support if this persists

Next Steps​

Great! You've successfully made your first API call. Now you can:

  1. Start Processing Data - Process different types of data
  2. Try Text Analysis - Deep dive into text processing
  3. Explore Image Analysis - Work with image processing
  4. Build Your First Model - Create ML models

Need Help?​

If you're having trouble with your first API call, check our troubleshooting guide or contact support.