Package dev.langchain4j.model.jlama

Class JlamaChatModel

java.lang.Object

dev.langchain4j.model.jlama.JlamaChatModel

All Implemented Interfaces:

ChatLanguageModel

public class JlamaChatModel
extends Object
implements ChatLanguageModel

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	JlamaChatModel.JlamaChatModelBuilder

Constructor Summary

Constructors

Constructor	Description
JlamaChatModel(Path modelCachePath, String modelName, String authToken, Integer threadCount, Boolean quantizeModelAtRuntime, Path workingDirectory, com.github.tjake.jlama.safetensors.DType workingQuantizedType, Float temperature, Integer maxTokens)

Method Summary

Modifier and Type	Method	Description
static JlamaChatModel.JlamaChatModelBuilder	builder()
ChatResponse	chat(ChatRequest chatRequest)	This is the main API to interact with the chat model.

Methods inherited from class java.lang.Object

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

Methods inherited from interface dev.langchain4j.model.chat.ChatLanguageModel

chat, chat, chat, defaultRequestParameters, doChat, listeners, provider, supportedCapabilities

Constructor Details

JlamaChatModel

public JlamaChatModel(Path modelCachePath,
 String modelName,
 String authToken,
 Integer threadCount,
 Boolean quantizeModelAtRuntime,
 Path workingDirectory,
 com.github.tjake.jlama.safetensors.DType workingQuantizedType,
 Float temperature,
 Integer maxTokens)

Method Details

builder

public static JlamaChatModel.JlamaChatModelBuilder builder()

chat

public ChatResponse chat(ChatRequest chatRequest)

Description copied from interface: ChatLanguageModel

This is the main API to interact with the chat model. A temporary default implementation of this method is necessary until all ChatLanguageModel implementations adopt it. It should be removed once that occurs.

Specified by:

chat in interface ChatLanguageModel

Parameters:

chatRequest - a ChatRequest, containing all the inputs to the LLM

Returns:

a ChatResponse, containing all the outputs from the LLM