Package dev.langchain4j.model.googleai

Class GoogleAiGeminiChatModel

java.lang.Object

dev.langchain4j.model.googleai.GoogleAiGeminiChatModel

All Implemented Interfaces:

ChatLanguageModel, TokenCountEstimator

public class GoogleAiGeminiChatModel
extends Object
implements ChatLanguageModel, TokenCountEstimator

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	GoogleAiGeminiChatModel.GoogleAiGeminiChatModelBuilder

Field Summary

Fields

Modifier and Type	Field	Description
protected final boolean	allowCodeExecution
protected final String	apiKey
protected final dev.langchain4j.model.googleai.GeminiService	geminiService
protected final boolean	includeCodeExecutionOutput
protected final List<ChatModelListener>	listeners
protected final Integer	maxOutputTokens
protected final Integer	maxRetries
protected final String	modelName
protected final ResponseFormat	responseFormat
protected final List<GeminiSafetySetting>	safetySettings
protected final List<String>	stopSequences
protected final Double	temperature
protected final GeminiFunctionCallingConfig	toolConfig
protected final Integer	topK
protected final Double	topP

Constructor Summary

Constructors

Constructor

Description

GoogleAiGeminiChatModel(String apiKey, String modelName, Integer maxRetries, Double temperature, Integer topK, Double topP, Integer maxOutputTokens, Duration timeout, ResponseFormat responseFormat, List<String> stopSequences, GeminiFunctionCallingConfig toolConfig, Boolean allowCodeExecution, Boolean includeCodeExecutionOutput, Boolean logRequestsAndResponses, List<GeminiSafetySetting> safetySettings, List<ChatModelListener> listeners)

Method Summary

Modifier and Type	Method	Description
ChatResponse	chat(ChatRequest chatRequest)
protected static String	computeMimeType(ResponseFormat responseFormat)
protected ChatModelRequest	createChatModelRequest(List<ChatMessage> messages, List<ToolSpecification> toolSpecifications)
protected dev.langchain4j.model.googleai.GeminiGenerateContentRequest	createGenerateContentRequest(List<ChatMessage> messages, List<ToolSpecification> toolSpecifications, ResponseFormat responseFormat)
int	estimateTokenCount(List<ChatMessage> messages)	Estimates the count of tokens in the specified list of messages.
Response<AiMessage>	generate(List<ChatMessage> messages)	Generates a response from the model based on a sequence of messages.
Response<AiMessage>	generate(List<ChatMessage> messages, ToolSpecification toolSpecification)	Generates a response from the model based on a list of messages and a single tool specification.
Response<AiMessage>	generate(List<ChatMessage> messages, List<ToolSpecification> toolSpecifications)	Generates a response from the model based on a list of messages and a list of tool specifications.
protected void	notifyListenersOnError(Exception exception, ChatModelRequest request, ConcurrentHashMap<Object,Object> attributes)
protected void	notifyListenersOnRequest(ChatModelRequestContext context)
protected void	notifyListenersOnResponse(Response<AiMessage> response, ChatModelRequest request, ConcurrentHashMap<Object,Object> attributes)
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.ChatLanguageModel

generate, generate

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

estimateTokenCount, estimateTokenCount, estimateTokenCount, estimateTokenCount

Field Details

geminiService

protected final dev.langchain4j.model.googleai.GeminiService geminiService

apiKey

protected final String apiKey

modelName

protected final String modelName

temperature

protected final Double temperature

topK

protected final Integer topK

topP

protected final Double topP

maxOutputTokens

protected final Integer maxOutputTokens

stopSequences

protected final List<String> stopSequences

responseFormat

protected final ResponseFormat responseFormat

toolConfig

protected final GeminiFunctionCallingConfig toolConfig

allowCodeExecution

protected final boolean allowCodeExecution

includeCodeExecutionOutput

protected final boolean includeCodeExecutionOutput

safetySettings

protected final List<GeminiSafetySetting> safetySettings

listeners

protected final List<ChatModelListener> listeners

maxRetries

protected final Integer maxRetries

Constructor Details

GoogleAiGeminiChatModel

public GoogleAiGeminiChatModel(String apiKey,
 String modelName,
 Integer maxRetries,
 Double temperature,
 Integer topK,
 Double topP,
 Integer maxOutputTokens,
 Duration timeout,
 ResponseFormat responseFormat,
 List<String> stopSequences,
 GeminiFunctionCallingConfig toolConfig,
 Boolean allowCodeExecution,
 Boolean includeCodeExecutionOutput,
 Boolean logRequestsAndResponses,
 List<GeminiSafetySetting> safetySettings,
 List<ChatModelListener> listeners)

Method Details

generate

public Response<AiMessage> generate(List<ChatMessage> messages)

Description copied from interface: ChatLanguageModel

Generates a response from the model based on a sequence of messages. Typically, the sequence contains messages in the following order: System (optional) - User - AI - User - AI - User ...

Specified by:

generate in interface ChatLanguageModel

Parameters:

messages - A list of messages.

Returns:

The response generated by the model.

generate

public Response<AiMessage> generate(List<ChatMessage> messages,
 ToolSpecification toolSpecification)

Description copied from interface: ChatLanguageModel

Generates a response from the model based on a list of messages and a single tool specification. The model is forced to execute the specified tool. This is usually achieved by setting `tool_choice=ANY` in the LLM provider API.
Typically, the list contains messages in the following order: System (optional) - User - AI - User - AI - User ...

Specified by:

generate in interface ChatLanguageModel

Parameters:

messages - A list of messages.

toolSpecification - The specification of a tool that must be executed. The model is forced to execute this tool.

Returns:

The response generated by the model. AiMessage contains a request to execute the specified tool.

generate

public Response<AiMessage> generate(List<ChatMessage> messages,
 List<ToolSpecification> toolSpecifications)

Description copied from interface: ChatLanguageModel

Generates a response from the model based on a list of messages and a list of tool specifications. The response may either be a text message or a request to execute one of the specified tools. Typically, the list contains messages in the following order: System (optional) - User - AI - User - AI - User ...

Specified by:

generate in interface ChatLanguageModel

Parameters:

messages - A list of messages.

toolSpecifications - A list of tools that the model is allowed to execute. The model autonomously decides whether to use any of these tools.

Returns:

The response generated by the model. AiMessage can contain either a textual response or a request to execute one of the tools.

chat

public ChatResponse chat(ChatRequest chatRequest)

Specified by:

chat in interface ChatLanguageModel

estimateTokenCount

public int estimateTokenCount(List<ChatMessage> messages)

Description copied from interface: TokenCountEstimator

Estimates the count of tokens in the specified list of messages.

Specified by:

estimateTokenCount in interface TokenCountEstimator

Parameters:

messages - the list of messages

Returns:

the estimated count of tokens

supportedCapabilities

public Set<Capability> supportedCapabilities()

Specified by:

supportedCapabilities in interface ChatLanguageModel

createGenerateContentRequest

protected dev.langchain4j.model.googleai.GeminiGenerateContentRequest createGenerateContentRequest(List<ChatMessage> messages,
 List<ToolSpecification> toolSpecifications,
 ResponseFormat responseFormat)

createChatModelRequest

protected ChatModelRequest createChatModelRequest(List<ChatMessage> messages,
 List<ToolSpecification> toolSpecifications)

computeMimeType

protected static String computeMimeType(ResponseFormat responseFormat)

notifyListenersOnRequest

protected void notifyListenersOnRequest(ChatModelRequestContext context)

notifyListenersOnResponse

protected void notifyListenersOnResponse(Response<AiMessage> response,
 ChatModelRequest request,
 ConcurrentHashMap<Object,Object> attributes)

notifyListenersOnError

protected void notifyListenersOnError(Exception exception,
 ChatModelRequest request,
 ConcurrentHashMap<Object,Object> attributes)