AdminConsole
API reference/SkyDNN AI & Vision
POSThybridcurrent-source evidence

Returns the prediction as response in form of JSON

/predict

Image classification and segmentation APIs enable state-of-the-art Computer Vision AI inferences to detect and catgorise objects in the photographs and generate localisation as well as map view of geospatial objects useful for a wide range of geospatial analytics and applications. On a Mission to "Make our world better through maps, location technologies & IoT" , Mappls is continuously enabling real time hyper-local information access through its map & location services. Skydnn APIs are a part of Skydnn AI platform and the document describes API's usage and specifications for their integration into any solution. The document covers : List of APIs along with use cases Explanation of resources and query parameters Listing of response structure and data type

Build a requestGet credentials
Request target

Call the operation

POSThttps://ai.mappls.com/predict
Base URLhttps://ai.mappls.com
Authenticationbearer
Journey rolecommand
Content typesmultipart/form-data
Path, query, and headers

Parameters

NameLocationTypeDescriptionExample
No explicit parameters are declared by the source operation.
Request body

Body schema

FieldTypeDescriptionExample
image
string

No field description in the source contract.

example
Request body example
{
  "image": "example"
}
Interactive, local, and credential-safe

Build your request in eight languages

Change source-backed examples once, validate required inputs, and copy the synchronized cURL, JavaScript, Python, Java, C#, Go, PHP, or Ruby request. Credentials remain environment references, and this page never sends a provider request.

Local request composerCode stays local · fixtures are explicit
POSTRequest inputs
0 editable · 0 protected
This operation has no editable path or query parameters.
Generated in eight languages
Environment-backed credentials
POSThttps://ai.mappls.com/predict
Credential-free sandboxExecute this contract without a provider call
How fixtures work
Generated from your inputs
curl --request POST \
  --url 'https://ai.mappls.com/predict' \
  --header "Accept: application/json" \
  --header "Authorization: Bearer ${MAPPLS_AI_TOKEN}" \
  --header "Content-Type: multipart/form-data" \
  --data-raw '{"image":"example"}'

Credential-safe by constructionSet MAPPLS_AI_TOKEN only in your trusted runtime. Code generation stays local. Sandbox execution sends only bounded fixture inputs to this developer platform and never reads a credential or calls Mappls.

Five language quickstarts

Send a production-shaped request

Examples use environment-backed access tokens, explicit timeouts where supported, status checks, and JSON bodies derived from the source schema. Replace sample identifiers and coordinates with values from your application.

POST /predict
curl --request POST \
  --url 'https://ai.mappls.com/predict' \
  --header 'Authorization: Bearer YOUR_ACCESS_TOKEN' \
  --header 'Content-Type: application/json' \
  --data '{
  "image": "example"
}'
Success and failure behavior

Responses

200

Successful.

400

Invalid Image Type

500

Internal Error. Exception in detection

hybrid integration

Operate it safely

command

This operation creates or triggers durable state. Supply an idempotency strategy and persist the returned identifier before continuing.

Keep credentials and raw tokens out of source, client bundles, prompts, and logs.Record the operation ID, status, latency, retry count, and source contract version in traces.Classify 4xx responses before retrying; back off and add jitter for retryable 5xx or transport failures.Cache only when request inputs, authorization scope, and freshness requirements permit it.
Auditable source

Contract provenance

Source file
aihub/docs/skydnn-aiapi-docs/docs/swagger/swagger-aimldl-auth-min-v2.yml
SHA-256
e19a9fcee8a760b1e7d50bae49991bafda1928ae51958c4400be4e5010f7c779
Normalization
Fields are parsed from OpenAPI. Operational guidance and language samples are generated and labeled separately.