Publish inference

Name of the column with the model outputs.

Name of the column with the total number of tokens.

Name of the column with the context retrieved. Applies to RAG use cases. Providing the context enables RAG-specific metrics.

Name of the column with the cost associated with each row.

Name of the column with the ground truths.

Name of the column with the inference ids. This is useful if you want to update rows at a later point in time. If not provided, a unique id is generated by Openlayer.

Array of input variable names. Each input variable should be a dataset column.

Name of the column with the latencies.

Object with metadata.

Prompt for the LLM.

Name of the column with the questions. Applies to RAG use cases. Providing the question enables RAG-specific metrics.

Name of the column with the timestamps. Timestamps must be in UNIX sec format. If not provided, the upload timestamp is used.