Implementation:Openai Openai python Eval Custom Data Source Config

Knowledge Sources	Openai_Openai_python OpenAI API Reference
Domains	API_Types, Python
Last Updated	2026-02-15 00:00 GMT

Overview

Concrete type for the custom data source configuration model used in evaluations, provided by the openai-python SDK.

Description

The EvalCustomDataSourceConfig Pydantic model represents a custom data source configuration that specifies the schema of your item and optionally sample namespaces for evaluation runs. It contains a schema_ field (aliased from "schema" in JSON) holding the JSON schema for run data source items, and a type field fixed to "custom". The schema defines both what testing criteria can reference and what data is required when creating an evaluation run.

Usage

Import this type when inspecting the data_source_config field on eval response objects where the type is "custom", or when building type-safe evaluation configurations.

Code Reference

Source Location

• Repository: openai-python
• File: src/openai/types/eval_custom_data_source_config.py

Signature

class EvalCustomDataSourceConfig(BaseModel):
    schema_: Dict[str, object] = FieldInfo(alias="schema")
    type: Literal["custom"]

Import

from openai.types import EvalCustomDataSourceConfig

I/O Contract

Fields

Name	Type	Required	Description
schema_	Dict[str, object]	Yes	JSON schema for run data source items (aliased from "schema" in JSON)
type	Literal["custom"]	Yes	Data source type, always "custom"

Usage Examples

from openai import OpenAI

client = OpenAI()

eval_obj = client.evals.retrieve("eval_abc123")

# Check if this eval uses a custom data source
if eval_obj.data_source_config.type == "custom":
    config = eval_obj.data_source_config
    print(f"Schema: {config.schema_}")
    print(f"Type: {config.type}")

Related Pages

• Environment:Openai_Openai_python_Python_3_9_Plus