Inference Result Service

Inference Result Service API methods in the Galtea SDK

The Inference Result Service in the Galtea SDK allows you to manage inference results for evaluating your products. This Service is exposed by the galtea.inference_results object.

Remember that we will be using the galtea object. More information here.

Quick Example

First, initialize the Galtea SDK:

galtea = Galtea(api_key="YOUR_API_KEY")

Generate an inference result using an Agent (recommended):

# Define your agent function
def my_agent(user_message: str) -> str:
    return f"Response to: {user_message}"


inference_result = galtea.inference_results.generate(agent=my_agent, session=session, input="Generate something")

Manually create an inference result:

inference_result = galtea.inference_results.create(
    session_id=session_id,
    input="What is the capital of France?",
    output="Paris",
    latency=150.5,
)

Update an inference result:

inference_result = galtea.inference_results.update(
    inference_result_id=inference_result_id,
    output="Paris is the capital.",
    cost=0.0001,
)

Service Methods

• Generate Inference Result - Recommended for automatic trace collection
• Create Inference Result
• Create and Evaluate - Create an inference result and evaluate it in one call
• Create Inference Result Batch
• Update Inference Result
• List Inference Results
• Get Inference Result
• Delete Inference Result

Related

Inference Result

A single turn in a conversation between a user and the AI.