Package com.tnsai.evaluation.rag.embedding

Class OllamaEmbeddingFunction

java.lang.Object

com.tnsai.evaluation.rag.embedding.OllamaEmbeddingFunction

All Implemented Interfaces:

com.tnsai.memory.advanced.EmbeddingFunction

public final class OllamaEmbeddingFunction
extends Object
implements com.tnsai.memory.advanced.EmbeddingFunction

EmbeddingFunction over an Ollama /api/embed endpoint.

Used only by the opt-in bench. Production RAG does not depend on this client. Query and passage prefixes are applied here so mE5's query:/passage: convention is not forgotten.

Since:

0.14.0

Constructor Summary

Constructors

Constructor	Description
OllamaEmbeddingFunction(String baseUrl, String model, String queryPrefix, String documentPrefix)

Method Summary

Modifier and Type	Method	Description
float[]	embed(String text)
float[]	embedQuery(String text)	Embeds a retrieval query with the model-specific query prefix.
String	model()
static boolean	modelAvailable(String baseUrl, String model)	True when /api/tags lists model.

Methods inherited from class java.lang.Object

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

Constructor Details

OllamaEmbeddingFunction

public OllamaEmbeddingFunction(String baseUrl,
 String model,
 String queryPrefix,
 String documentPrefix)

Method Details

model

public String model()

embed

public float[] embed(String text)

Specified by:

embed in interface com.tnsai.memory.advanced.EmbeddingFunction

embedQuery

public float[] embedQuery(String text)

Embeds a retrieval query with the model-specific query prefix.

modelAvailable

public static boolean modelAvailable(String baseUrl,
 String model)

True when /api/tags lists model.