SDK Log Ingestion

Use the Python SDK to upload log data

Push data manually or as part of a daily orchestration job using our Python SDK. This ingestion method allows for the most flexibility, but requires the most off-platform coding.

See the Python SDK docs for more detailed information about SDK installation and functions.

The following fields are required regardless of which ingestion method you are using:

• input: The text input to the LLM as a string.

• output: The text response from the LLM as a string.

• timestamp: The UTC timecode associated with the LLM call. Must be a timezone-aware datetime in UTC (Python: datetime with tzinfo=UTC or pandas: datetime64[us, UTC]).

See the DBNL Semantic Convention for other semantically recognized fields. Only columns defined in the DBNL Semantic Convention are supported — arbitrary custom columns are not ingested. To attach custom metadata, use span attributes via the OpenInference semantic convention.

Example Code

Check out the Quickstart for an example of using the SDK Log Ingestion as a Data Connection.

4KB

DBNL-quickstart.ipynb

Open