LLMRunMetadata
Ingest metadata about your LLM inferences
Last updated
Ingest metadata about your LLM inferences
Last updated
Copyright © 2023 Arize AI, Inc
Arize class to map up to 4 columns: total_token_count_column_name
, prompt_token_count_column_name
, response_token_count_column_name
, andresponse_latency_ms_column_name
Parameters | Data Type | Description |
---|---|---|
| int | The total number of tokens used in the inference, both in the prompt sent to the LLM and in its response |
| int | The number of tokens used in the prompt sent to the LLM |
| int | The number of tokens used in the response returned by the LLM |
| int or float | The latency (in ms) experienced during the LLM run |