Perform inference using the NSR Machine
Processes input sequences through the neural-symbolic reasoning pipeline, combining perception, parsing, and semantic computation to produce outputs…
POST
Processes input sequences through the neural-symbolic reasoning pipeline,
combining perception, parsing, and semantic computation to produce outputs.
Input Types
Perform inference with the NSR Machine.
Required scope:
text: Natural language or symbolic commands (e.g., ‘walk twice’)number: Numeric values for mathematical operationsembedding: Pre-computed vector embeddingsimage: Raw pixel data for visual inputscomposite: Numeric grounded symbol vectors such as emulator UI-node fields Example
write
Request body
NSRInferRequest
GroundedInputRequest[]
required
Input sequence for inference
string
Optional session ID for context persistence
Response
NSRInferResponse
number (double)
required
Confidence score (0.0 to 1.0)
number (double)
Confidence for the interpreted output (0.0 to 1.0)
object
string
Short rationale for how the interpreted output was chosen
object
integer (int64)
required
Processing time in milliseconds
SymbolDistributionResponse[]
Symbol distributions for each input
integer (int64)[]
required
Symbol sequence identified