Package dev.langchain4j.model.bedrock

Class BedrockAnthropicMessageChatModel

java.lang.Object

dev.langchain4j.model.bedrock.internal.AbstractSharedBedrockChatModel

dev.langchain4j.model.bedrock.internal.AbstractBedrockChatModel<BedrockAnthropicMessageChatModelResponse>

dev.langchain4j.model.bedrock.BedrockAnthropicMessageChatModel

All Implemented Interfaces:

ChatLanguageModel

public class BedrockAnthropicMessageChatModel
extends AbstractBedrockChatModel<BedrockAnthropicMessageChatModelResponse>

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static enum	BedrockAnthropicMessageChatModel.Types	Bedrock Anthropic model ids

Field Summary

Fields inherited from class dev.langchain4j.model.bedrock.internal.AbstractSharedBedrockChatModel

ASSISTANT_PROMPT, assistantPrompt, credentialsProvider, HUMAN_PROMPT, humanPrompt, listeners, maxRetries, maxTokens, region, stopSequences, temperature, timeout, topP

Constructor Summary

Constructors

Constructor	Description
BedrockAnthropicMessageChatModel()

Method Summary

Modifier and Type	Method	Description
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 String	getModelId()	Get model id
protected Map<String,Object>	getRequestParameters(String prompt)	Get request parameters
Class<BedrockAnthropicMessageChatModelResponse>	getResponseClassType()	Get response class type

Methods inherited from class dev.langchain4j.model.bedrock.internal.AbstractBedrockChatModel

invoke, of, toAiMessage

Methods inherited from class dev.langchain4j.model.bedrock.internal.AbstractSharedBedrockChatModel

chatMessageToString, convertMessagesToAwsBody, createModelListenerRequest, createModelListenerRequest, createModelListenerResponse, listenerErrorResponse

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

BedrockAnthropicMessageChatModel

public BedrockAnthropicMessageChatModel()

Method Details

getModelId

protected String getModelId()

Description copied from class: AbstractSharedBedrockChatModel

Get model id

Specified by:

getModelId in class AbstractSharedBedrockChatModel

Returns:

model id

getRequestParameters

protected Map<String,Object> getRequestParameters(String prompt)

Description copied from class: AbstractBedrockChatModel

Get request parameters

Specified by:

getRequestParameters in class AbstractBedrockChatModel<BedrockAnthropicMessageChatModelResponse>

Parameters:

prompt - prompt

Returns:

request body

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

Overrides:

generate in class AbstractBedrockChatModel<BedrockAnthropicMessageChatModelResponse>

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 ...

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 ...

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.

getResponseClassType

public Class<BedrockAnthropicMessageChatModelResponse> getResponseClassType()

Description copied from class: AbstractBedrockChatModel

Get response class type

Specified by:

getResponseClassType in class AbstractBedrockChatModel<BedrockAnthropicMessageChatModelResponse>

Returns:

response class type