Package org.springframework.ai.ollama

Class OllamaChatClient

java.lang.Object

org.springframework.ai.ollama.OllamaChatClient

All Implemented Interfaces:

ChatClient, StreamingChatClient, ModelClient<Prompt,ChatResponse>, StreamingModelClient<Prompt,ChatResponse>

public class OllamaChatClient
extends Object
implements ChatClient, StreamingChatClient

ChatClient 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). - 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

Constructor Summary

Constructors

Constructor	Description
OllamaChatClient(OllamaApi chatApi)

Method Summary

Modifier and Type	Method	Description
ChatResponse	call(Prompt prompt)	Executes a method call to the AI model.
reactor.core.publisher.Flux<ChatResponse>	stream(Prompt prompt)	Executes a method call to the AI model.
OllamaChatClient	withDefaultOptions(OllamaOptions options)
OllamaChatClient	withModel(String model)	Deprecated. Use OllamaOptions.setModel(java.lang.String) instead.

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.chat.ChatClient

call

Constructor Details

OllamaChatClient

public OllamaChatClient(OllamaApi chatApi)

Method Details

withModel

@Deprecated
public OllamaChatClient withModel(String model)

Deprecated.

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

withDefaultOptions

public OllamaChatClient withDefaultOptions(OllamaOptions options)

call

public ChatResponse call(Prompt prompt)

Description copied from interface: ModelClient

Executes a method call to the AI model.

Specified by:

call in interface ChatClient

Specified by:

call in interface ModelClient<Prompt,ChatResponse>

Parameters:

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

Returns:

the response from the AI model

stream

public reactor.core.publisher.Flux<ChatResponse> stream(Prompt prompt)

Description copied from interface: StreamingModelClient

Executes a method call to the AI model.

Specified by:

stream in interface StreamingChatClient

Specified by:

stream in interface StreamingModelClient<Prompt,ChatResponse>

Parameters:

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

Returns:

the streaming response from the AI model