TextEmbedding

TextEmbedding extends VectorFeature to handle text-based embeddings with additional text-specific analysis capabilities. It combines vector clustering with TF-IDF analysis to provide both semantic clustering and keyword extraction for text data. The feature type is automatically set to CustomFeatureType.FROM_TEXT_EMBEDDING and uses clustering combined with TF-IDF summarization for drift computation.

Examples

# Creating a text embedding feature for review analysis:

text_feature = TextEmbedding(
    name="review_sentiment_clusters",
    column="review_embedding",
    source_column="review_text",
    n_clusters=8,
    n_tags=20
)

# Creating a feature for document classification:

doc_feature = TextEmbedding(
    name="document_topic_clusters",
    column="doc_embedding",
    source_column="document_content",
    n_clusters=12,
    n_tags=15
)

Attributes

Literal['FROM_TEXT_EMBEDDING']

Type discriminator; fixed as CustomFeatureType.FROM_TEXT_EMBEDDING.

str

Name of the original text column that generated the embedding.

int | None

Number of tokens per cluster used for TF-IDF summarization (default 5).

Dict[str, List] | None

TF-IDF analysis results; populated during training.

classmethod validate_n_tags()

Returns

int

Fiddler Python Client SDK

Fiddler Evals SDK

Fiddler OTel SDK

Fiddler LangGraph SDK

Fiddler LangChain SDK

Fiddler Google ADK SDK

Fiddler Strands Agent SDK

Fiddler OTel JS SDK

Fiddler LangGraph JS SDK

Fiddler LangChain JS SDK

Examples

Attributes

classmethod validate_n_tags()

Returns

​Examples

​Attributes

​classmethod validate_n_tags()

​Returns

Examples

Attributes

classmethod validate_n_tags()

Returns