Julia AI detector quickstart
Send at least 150 characters for a more reliable signal. The response score ranges from 0 (more likely human-written) to 1 (more likely AI-generated); use it as evidence, not proof.
No language-specific SDK is required. The example uses a standard or commonly used HTTP client to call Sapling's JSON API.
Julia
/api/v1/aidetect
This example uses the HTTP.jl and JSON.jl packages.
using HTTP
using JSON
api_key = ENV["SAPLING_API_KEY"]
url = "https://api.sapling.ai/api/v1/aidetect"
headers = [
"Authorization" => "Bearer $api_key",
"Content-Type" => "application/json",
]
payload = Dict(
"text" => "I am an artificial intelligence system designed to help people solve complex problems. My capabilities include natural language processing, machine learning, and predictive analytics.",
"sent_scores" => true,
)
response = HTTP.post(url, headers, JSON.json(payload); status_exception=true)
println(String(response.body))
Example response
application/json
{
"score": 0.9989,
"sentence_scores": [
{
"score": 0.9764,
"sentence": "I am an artificial intelligence system designed to help people solve complex problems."
},
{
"score": 0.9812,
"sentence": "My capabilities include natural language processing, machine learning, and predictive analytics."
}
],
"text": "I am an artificial intelligence system designed to help people solve complex problems. My capabilities include natural language processing, machine learning, and predictive analytics."
}The overall score and sentence scores use different methods and may not match exactly. Choose thresholds based on the false-positive and false-negative costs of your use case.
About Julia
Julia is a popular programming language for data science applications in industry and academia like numerical analysis and computational science. It is designed to be dynamic, concurrent/parallel and includes efficient libraries for linear algebra and floating-point calculations.