​
Returns

Returns an InferenceResult object.

​
Example

inference_result = galtea.inference_results.create(
    session_id="YOUR_SESSION_ID",
    input="What is the capital of France?",
    output="Paris is the capital of France."
)

​
Parameters

​
session_id
string
required
The session ID to log the inference result to.
​
input
string
required
The input text/prompt.
​
output
string
required
The generated output/response.
​
retrieval_context
string
Context retrieved for RAG systems.
​
latency
float
Latency in milliseconds.
​
usage_info
dict
Token usage information (e.g., {"input_tokens": 10, "output_tokens": 5}).
​
cost_info
dict
Cost information (e.g., {"cost_per_input_token": 0.0001}).