Package org.springframework.ai.ollama

Class OllamaEmbeddingClient

java.lang.Object

org.springframework.ai.embedding.AbstractEmbeddingClient

org.springframework.ai.ollama.OllamaEmbeddingClient

All Implemented Interfaces:

EmbeddingClient, ModelClient<EmbeddingRequest,EmbeddingResponse>

public class OllamaEmbeddingClient
extends AbstractEmbeddingClient

EmbeddingClient implementation for Ollama. Ollama allows developers to run large language models and generate embeddings locally. It supports open-source models available on [Ollama AI Library](https://ollama.ai/library). Examples of models supported: - Llama 2 (7B parameters, 3.8GB size) - Mistral (7B parameters, 4.1GB size) Please refer to the official Ollama website for the most up-to-date information on available models.

Since:

0.8.0

Author:

Christian Tzolov

Field Summary

Fields inherited from class org.springframework.ai.embedding.AbstractEmbeddingClient

embeddingDimensions

Constructor Summary

Constructors

Constructor	Description
OllamaEmbeddingClient(OllamaApi ollamaApi)

Method Summary

Modifier and Type	Method	Description
EmbeddingResponse	call(EmbeddingRequest request)	Executes a method call to the AI model.
List<Double>	embed(Document document)	Embeds the given document's content into a vector.
OllamaEmbeddingClient	withDefaultOptions(OllamaOptions options)
OllamaEmbeddingClient	withModel(String model)	Deprecated. Use OllamaOptions.setModel(java.lang.String) instead.

Methods inherited from class org.springframework.ai.embedding.AbstractEmbeddingClient

dimensions, dimensions

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.springframework.ai.embedding.EmbeddingClient

embed, embed, embedForResponse

Constructor Details

OllamaEmbeddingClient

public OllamaEmbeddingClient(OllamaApi ollamaApi)

Method Details

withModel

@Deprecated
public OllamaEmbeddingClient withModel(String model)

Deprecated.

Use OllamaOptions.setModel(java.lang.String) instead.

withDefaultOptions

public OllamaEmbeddingClient withDefaultOptions(OllamaOptions options)

embed

public List<Double> embed(Document document)

Description copied from interface: EmbeddingClient

Embeds the given document's content into a vector.

Parameters:

document - the document to embed.

Returns:

the embedded vector.

call

public EmbeddingResponse call(EmbeddingRequest request)

Description copied from interface: ModelClient

Executes a method call to the AI model.

Parameters:

request - the request object to be sent to the AI model

Returns:

the response from the AI model