Package com.google.genkit.plugins.milvus

Class MilvusCollectionConfig

java.lang.Object

com.google.genkit.plugins.milvus.MilvusCollectionConfig

public final class MilvusCollectionConfig
extends Object

Configuration for a single Milvus collection managed by MilvusPlugin.

Each config registers a retriever and indexer named milvus/<collectionName>. The collection is created in Milvus "quick setup" mode (auto id primary key, a vector field, and dynamic fields) storing the document text under text and its metadata as a JSON string under metadata.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static final class	MilvusCollectionConfig.Builder	Builder for MilvusCollectionConfig.
static enum	MilvusCollectionConfig.Metric	Vector similarity metric used by the Milvus index.

Method Summary

Modifier and Type	Method	Description
static MilvusCollectionConfig.Builder	builder()	Creates a new builder.
Map<String,Object>	getAdditionalMetadata()	Returns additional metadata merged into every indexed document.
String	getCollectionName()	Returns the Milvus collection name.
int	getDimension()	Returns the embedding dimension (default 768).
String	getEmbedderName()	Returns the name of the embedder used to vectorize documents and queries.
MilvusCollectionConfig.Metric	getMetric()	Returns the vector similarity metric (default MilvusCollectionConfig.Metric.COSINE).
boolean	isCreateCollectionIfNotExists()	Returns whether to create the collection on first use if it does not exist (default true).

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Method Details

getCollectionName

public String getCollectionName()

Returns the Milvus collection name.

Returns:

the collection name

getEmbedderName

public String getEmbedderName()

Returns the name of the embedder used to vectorize documents and queries.

Returns:

the embedder name

getDimension

public int getDimension()

Returns the embedding dimension (default 768).

Returns:

the embedding dimension

getMetric

public MilvusCollectionConfig.Metric getMetric()

Returns the vector similarity metric (default MilvusCollectionConfig.Metric.COSINE).

Returns:

the metric

isCreateCollectionIfNotExists

public boolean isCreateCollectionIfNotExists()

Returns whether to create the collection on first use if it does not exist (default true).

Returns:

true if the collection should be created when missing

getAdditionalMetadata

public Map<String,Object> getAdditionalMetadata()

Returns additional metadata merged into every indexed document.

Returns:

the additional metadata

builder

public static MilvusCollectionConfig.Builder builder()

Creates a new builder.

Returns:

a new builder