Package com.hw.langchain.llms.ollama

Class Ollama

java.lang.Object

com.hw.langchain.llms.base.BaseLLM

com.hw.langchain.llms.ollama.Ollama

All Implemented Interfaces:

BaseLanguageModel

public class Ollama
extends BaseLLM

Ollama locally run large language models.

Author:

HamaWhite

Constructor Summary

Constructors

Constructor	Description
Ollama()

Method Summary

Modifier and Type	Method	Description
protected reactor.core.publisher.Flux<AsyncLLMResult>	asyncInnerGenerate(List<String> prompts, List<String> stop)	Run the LLM on the given prompts async.
List<String>	createStream(String prompt, List<String> stop)
Ollama	init()
protected LLMResult	innerGenerate(List<String> prompts, List<String> stop)	Call out to Ollama to generate endpoint.
String	llmType()	Return type of llm.
static GenerationChunk	streamResponseToGenerationChunk(String streamResponse)	Convert a stream response to a generation chunk.

Methods inherited from class com.hw.langchain.llms.base.BaseLLM

asyncGeneratePrompt, asyncPredict, call, call, generate, generatePrompt, predict, predictMessages

Methods inherited from class java.lang.Object

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

Methods inherited from interface com.hw.langchain.base.language.BaseLanguageModel

asyncGeneratePrompt, asyncPredict, asyncPredictMessages, predict, predictMessages

Constructor Details

Ollama

public Ollama()

Method Details

llmType

public String llmType()

Description copied from class: BaseLLM

Return type of llm.

Specified by:

llmType in class BaseLLM

init

public Ollama init()

createStream

public List<String> createStream(String prompt,
 List<String> stop)

innerGenerate

protected LLMResult innerGenerate(List<String> prompts,
 List<String> stop)

Call out to Ollama to generate endpoint.

Specified by:

innerGenerate in class BaseLLM

Parameters:

prompts - The prompt to pass into the model.

stop - list of stop words to use when generating.

Returns:

The string generated by the model.

asyncInnerGenerate

protected reactor.core.publisher.Flux<AsyncLLMResult> asyncInnerGenerate(List<String> prompts,
 List<String> stop)

Description copied from class: BaseLLM

Run the LLM on the given prompts async.

Specified by:

asyncInnerGenerate in class BaseLLM

streamResponseToGenerationChunk

public static GenerationChunk streamResponseToGenerationChunk(String streamResponse)

Convert a stream response to a generation chunk.

Parameters:

streamResponse - The stream response as a JSON string.

Returns:

A GenerationChunk object containing the converted data.