Package dev.langchain4j.model.vertexai

Class VertexAiGeminiChatModel

java.lang.Object

dev.langchain4j.model.vertexai.VertexAiGeminiChatModel

All Implemented Interfaces:

ChatLanguageModel, Closeable, AutoCloseable

public class VertexAiGeminiChatModel
extends Object
implements ChatLanguageModel, Closeable

Represents a Google Vertex AI Gemini language model with a chat completion interface, such as gemini-pro. See details here.
Please follow these steps before using this model:
1. Authentication
When developing locally, you can use one of:
a) Google Cloud SDK
b) Service account When using service account, ensure that GOOGLE_APPLICATION_CREDENTIALS environment variable points to your JSON service account key.
2. Authorization
3. Prerequisites

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	VertexAiGeminiChatModel.VertexAiGeminiChatModelBuilder

Constructor Summary

Constructors

Constructor	Description
VertexAiGeminiChatModel(com.google.cloud.vertexai.generativeai.GenerativeModel generativeModel, com.google.cloud.vertexai.api.GenerationConfig generationConfig)
VertexAiGeminiChatModel(com.google.cloud.vertexai.generativeai.GenerativeModel generativeModel, com.google.cloud.vertexai.api.GenerationConfig generationConfig, Integer maxRetries)
VertexAiGeminiChatModel(String project, String location, String modelName, Float temperature, Integer maxOutputTokens, Integer topK, Float topP, Integer maxRetries, String responseMimeType, com.google.cloud.vertexai.api.Schema responseSchema, Map<HarmCategory,SafetyThreshold> safetySettings, Boolean useGoogleSearch, String vertexSearchDatastore, ToolCallingMode toolCallingMode, List<String> allowedFunctionNames, Boolean logRequests, Boolean logResponses)

Method Summary

Modifier and Type	Method	Description
static VertexAiGeminiChatModel.VertexAiGeminiChatModelBuilder	builder()
void	close()
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.

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, generate, generate, supportedCapabilities

Constructor Details

VertexAiGeminiChatModel

public VertexAiGeminiChatModel(String project,
 String location,
 String modelName,
 Float temperature,
 Integer maxOutputTokens,
 Integer topK,
 Float topP,
 Integer maxRetries,
 String responseMimeType,
 com.google.cloud.vertexai.api.Schema responseSchema,
 Map<HarmCategory,SafetyThreshold> safetySettings,
 Boolean useGoogleSearch,
 String vertexSearchDatastore,
 ToolCallingMode toolCallingMode,
 List<String> allowedFunctionNames,
 Boolean logRequests,
 Boolean logResponses)

VertexAiGeminiChatModel

public VertexAiGeminiChatModel(com.google.cloud.vertexai.generativeai.GenerativeModel generativeModel,
 com.google.cloud.vertexai.api.GenerationConfig generationConfig)

VertexAiGeminiChatModel

public VertexAiGeminiChatModel(com.google.cloud.vertexai.generativeai.GenerativeModel generativeModel,
 com.google.cloud.vertexai.api.GenerationConfig generationConfig,
 Integer maxRetries)

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,
 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.

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. 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.

close

public void close()
           throws IOException

Specified by:

close in interface AutoCloseable

Specified by:

close in interface Closeable

Throws:

IOException

builder

public static VertexAiGeminiChatModel.VertexAiGeminiChatModelBuilder builder()