Skip to main content

​
What is an Inference Result?

An inference result is a single turn in a conversation — one user input paired with one AI output. It belongs to a session and can optionally include metadata like latency, token usage, cost, and retrieval context (for RAG evaluations). You can create inference results from the Galtea dashboard (using Endpoint Connections) or programmatically using the Galtea SDK.

​
SDK Integration

Inference Result Service SDK

Manage inference results using the Python SDK

​
Inference Result Properties

​
Session
required
The session to which the inference result belongs.
​
string | object
The input text or prompt for the inference result. For most runs this is a plain string. For phone (voice) runs, when the simulated user’s audio was captured, this is a content-parts envelope {"user_message": "<transcript>", "content": [{"type": "audio", "uri": "...", "transcript": "..."}]} — the user_message field is the canonical scored scalar. Access the envelope via the SDK’s .input_data field and the spoken transcript via .input.
​
string | object
The generated output or response for the inference result. For most runs this is a plain string. For phone (voice) runs, when the agent’s audio was captured, this is a content-parts envelope {"assistant_message": "<transcript>", "content": [{"type": "audio", "uri": "...", "transcript": "..."}]} — the assistant_message field is the canonical scored scalar. Access the envelope via the SDK’s .actual_output_data field and the scored transcript via .actual_output.
Retrieval context is not a stored field on the inference result. It is derived from the inference result’s RETRIEVER trace spans. You can still supply retrieval_context when logging (on create, update, or an agent response); Galtea records it as a RETRIEVER trace.If your agent already emits traces, we recommend sending RETRIEVER spans directly instead. This keeps one source of truth and lets you capture several retrieval steps per turn, which a single retrieval_context value cannot.
​
float
The latency in milliseconds for the model’s response.
​
dict
Token usage information for the inference result.
​
dict
Cost information for the inference result.
​
string
The W3C trace ID for the root span created during Direct Inference. This is the same trace ID propagated to your endpoint via the traceparent header, enabling correlation with your OTEL-instrumented service. Only present when the inference was generated via Direct Inference with W3C trace context propagation enabled.

Concepts overview

How Galtea’s concepts connect — diagram + per-entity quick reference.

Session

The conversation that groups inference results together.

Evaluation

Score inference results using metrics.

Trace

Capture internal operations linked to inference results.