Package dev.langchain4j.model.mistralai

Class MistralAiStreamingChatModel

java.lang.Object

dev.langchain4j.model.mistralai.MistralAiStreamingChatModel

All Implemented Interfaces:

StreamingChatLanguageModel

public class MistralAiStreamingChatModel
extends Object
implements StreamingChatLanguageModel

Represents a Mistral AI Chat Model with a chat completion interface, such as mistral-tiny and mistral-small. The model's response is streamed token by token and should be handled with StreamingResponseHandler. You can find description of parameters here.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	MistralAiStreamingChatModel.MistralAiStreamingChatModelBuilder

Constructor Summary

Constructors

Constructor	Description
MistralAiStreamingChatModel(String baseUrl, String apiKey, String modelName, Double temperature, Double topP, Integer maxTokens, Boolean safePrompt, Integer randomSeed, ResponseFormat responseFormat, Boolean logRequests, Boolean logResponses, Duration timeout, Set<Capability> supportedCapabilities)	Constructs a MistralAiStreamingChatModel with the specified parameters.

Method Summary

Modifier and Type	Method	Description
static MistralAiStreamingChatModel.MistralAiStreamingChatModelBuilder	builder()
void	chat(ChatRequest chatRequest, StreamingChatResponseHandler handler)	This is the main API to interact with the chat model.
ModelProvider	provider()
Set<Capability>	supportedCapabilities()

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.StreamingChatLanguageModel

chat, chat, defaultRequestParameters, doChat, listeners

Constructor Details

MistralAiStreamingChatModel

public MistralAiStreamingChatModel(String baseUrl,
 String apiKey,
 String modelName,
 Double temperature,
 Double topP,
 Integer maxTokens,
 Boolean safePrompt,
 Integer randomSeed,
 ResponseFormat responseFormat,
 Boolean logRequests,
 Boolean logResponses,
 Duration timeout,
 Set<Capability> supportedCapabilities)

Constructs a MistralAiStreamingChatModel with the specified parameters.

Parameters:

baseUrl - the base URL of the Mistral AI API. It uses the default value if not specified

apiKey - the API key for authentication

modelName - the name of the Mistral AI model to use

temperature - the temperature parameter for generating chat responses

topP - the top-p parameter for generating chat responses

maxTokens - the maximum number of new tokens to generate in a chat response

safePrompt - a flag indicating whether to use a safe prompt for generating chat responses

randomSeed - the random seed for generating chat responses (if not specified, a random number is used)

responseFormat - the response format for generating chat responses. Current values supported are "text" and "json_object".

logRequests - a flag indicating whether to log raw HTTP requests

logResponses - a flag indicating whether to log raw HTTP responses

timeout - the timeout duration for API requests

Method Details

supportedCapabilities

public Set<Capability> supportedCapabilities()

Specified by:

supportedCapabilities in interface StreamingChatLanguageModel

chat

public void chat(ChatRequest chatRequest,
 StreamingChatResponseHandler handler)

Description copied from interface: StreamingChatLanguageModel

This is the main API to interact with the chat model.

A temporary default implementation of this method is necessary until all StreamingChatLanguageModel implementations adopt it. It should be removed once that occurs.

Specified by:

chat in interface StreamingChatLanguageModel

Parameters:

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

handler - a StreamingChatResponseHandler that will handle streaming response from the LLM

provider

public ModelProvider provider()

Specified by:

provider in interface StreamingChatLanguageModel

builder

public static MistralAiStreamingChatModel.MistralAiStreamingChatModelBuilder builder()