Skip to main content
View source on Github Arize class to map up to 2 columns: model_column_name and params_column_name 
class LLMConfigColumnNames:
    model_column_name: Optional[str] = None
    params_column_name: Optional[str] = None
ParametersData TypeExpected Type in ColumnDescription
model_column_namestrThe contents of this column must be stringsColumn name for the name of the LLM model used.
params_column_namestrThe contents of this column must be be well formatted JSON stringsColumn name for the invocation parameters used at inference

​
Code Example

Indexllm_model_namellm_params
0gpt-4{``"temperature": 0.9,``"stop":[".","?"],``"frequency_penalty":"0.0"``}
1gpt3.5-turbo{``"temperature": 0.7,``"stop":[".","?"],``"frequency_penalty":"0.2"``}
from arize.utils.types import LLMConfigColumnNames

# Declare LLM config columns
llm_config = LLMConfigColumnNames(
    model_column_name = "llm_model_name", # column containing the LLM model name
    params_version_column_name = "llm_params", # column containing the LLM invocation params
)