aip_sdk.EmbeddingComputeResult
aip_sdk.EmbeddingComputeResult(coordinates: pd.DataFrame, pipelines: tuple[EmbeddingPipeline, ...])
Coordinates and per-pipeline diagnostics from one compute() call.
Attributes
coordinatespd.DataFrame: Tidy frame withCOORDINATE_COLUMNS, carrying only the pipelines that succeeded.pipelinestuple[EmbeddingPipeline, ...]: Every configured pipeline, succeeded and failed alike, so a caller can see what a config actually produced.
aip_sdk.EmbeddingComputeResult.coordinates
aip_sdk.EmbeddingComputeResult.coordinates: pd.DataFrame
No docstring is defined in the source.
aip_sdk.EmbeddingComputeResult.failed
aip_sdk.EmbeddingComputeResult.failed: tuple[EmbeddingPipeline, ...]
Pipelines that produced no coordinates, each carrying its error.
aip_sdk.EmbeddingComputeResult.for_pipeline
aip_sdk.EmbeddingComputeResult.for_pipeline(pipeline_id: str) -> pd.DataFrame
Return just pipeline_id's coordinates, indexed by position.
Parameters
pipeline_idstr: A derived pipeline id, as listed bypipeline_ids.
Returns
pd.DataFrame: The subset ofcoordinatesfor that pipeline.
Raises
EmbeddingsError: If no succeeded pipeline has that id.
aip_sdk.EmbeddingComputeResult.pipeline_ids
aip_sdk.EmbeddingComputeResult.pipeline_ids: tuple[str, ...]
Ids of the pipelines that produced coordinates.
aip_sdk.EmbeddingComputeResult.pipelines
aip_sdk.EmbeddingComputeResult.pipelines: tuple[EmbeddingPipeline, ...]
No docstring is defined in the source.
aip_sdk.EmbeddingComputeResult.succeeded
aip_sdk.EmbeddingComputeResult.succeeded: tuple[EmbeddingPipeline, ...]
Pipelines that produced coordinates.