Class AnthropicChatModel.AnthropicChatModelBuilder

java.lang.Object

dev.langchain4j.model.anthropic.AnthropicChatModel.AnthropicChatModelBuilder

Enclosing class:

AnthropicChatModel

public static class AnthropicChatModel.AnthropicChatModelBuilder
extends Object

Constructor Summary

Constructors

Constructor	Description
AnthropicChatModelBuilder()

Method Summary

Modifier and Type	Method	Description
AnthropicChatModel.AnthropicChatModelBuilder	apiKey(String apiKey)	Sets the Anthropic API key used to authenticate requests.
AnthropicChatModel.AnthropicChatModelBuilder	baseUrl(String baseUrl)	Sets the base URL of the Anthropic API.
AnthropicChatModel.AnthropicChatModelBuilder	beta(String beta)	Sets the value of the anthropic-beta request header to opt into beta features.
AnthropicChatModel	build()
AnthropicChatModel.AnthropicChatModelBuilder	cacheSystemMessages(Boolean cacheSystemMessages)	Enables prompt caching for SystemMessages.
AnthropicChatModel.AnthropicChatModelBuilder	cacheTools(Boolean cacheTools)	Enables prompt caching for ToolSpecifications.
AnthropicChatModel.AnthropicChatModelBuilder	customHeaders(Supplier<Map<String,String>> customHeadersSupplier)	Sets a supplier of extra HTTP headers to include in every request to the Anthropic API.
AnthropicChatModel.AnthropicChatModelBuilder	customHeaders(Map<String,String> customHeaders)	Sets extra HTTP headers to include in every request to the Anthropic API.
AnthropicChatModel.AnthropicChatModelBuilder	customParameters(Map<String,Object> customParameters)	Sets arbitrary extra parameters to include in the Anthropic API request body.
AnthropicChatModel.AnthropicChatModelBuilder	defaultRequestParameters(ChatRequestParameters parameters)	Sets default ChatRequestParameters that are merged into every request.
AnthropicChatModel.AnthropicChatModelBuilder	disableParallelToolUse(Boolean disableParallelToolUse)	When set to true, prevents the model from calling multiple tools in a single response turn.
AnthropicChatModel.AnthropicChatModelBuilder	httpClientBuilder(HttpClientBuilder httpClientBuilder)	Sets a custom HttpClientBuilder for the underlying HTTP client.
AnthropicChatModel.AnthropicChatModelBuilder	listeners(ChatModelListener... listeners)	Sets the ChatModelListeners to be notified on each request and response.
AnthropicChatModel.AnthropicChatModelBuilder	listeners(List<ChatModelListener> listeners)	Sets the list of ChatModelListeners to be notified on each request and response.
AnthropicChatModel.AnthropicChatModelBuilder	logger(org.slf4j.Logger logger)
AnthropicChatModel.AnthropicChatModelBuilder	logRequests(Boolean logRequests)	Enables debug logging of HTTP request bodies sent to the Anthropic API.
AnthropicChatModel.AnthropicChatModelBuilder	logResponses(Boolean logResponses)	Enables debug logging of HTTP response bodies received from the Anthropic API.
AnthropicChatModel.AnthropicChatModelBuilder	maxRetries(Integer maxRetries)	Sets the number of times to retry a request on transient errors (e.g. rate limits, server errors).
AnthropicChatModel.AnthropicChatModelBuilder	maxTokens(Integer maxTokens)	Sets the maximum number of tokens to generate in the response.
AnthropicChatModel.AnthropicChatModelBuilder	modelName(AnthropicChatModelName modelName)	Sets the model to use for chat completions using a type-safe enum constant.
AnthropicChatModel.AnthropicChatModelBuilder	modelName(String modelName)	Sets the model to use for chat completions, specified as a string model ID.
AnthropicChatModel.AnthropicChatModelBuilder	responseFormat(ResponseFormat responseFormat)	Sets the response format, enabling structured output such as JSON mode.
AnthropicChatModel.AnthropicChatModelBuilder	returnServerToolResults(Boolean returnServerToolResults)	Controls whether to return server tool results (e.g., web_search, code_execution) inside AiMessage.attributes() under the key "server_tool_results".
AnthropicChatModel.AnthropicChatModelBuilder	returnThinking(Boolean returnThinking)	Controls whether to return thinking/reasoning text (if available) inside AiMessage.thinking().
AnthropicChatModel.AnthropicChatModelBuilder	sendThinking(Boolean sendThinking)	Controls whether to send thinking/reasoning text to the LLM in follow-up requests.
AnthropicChatModel.AnthropicChatModelBuilder	serverTools(AnthropicServerTool... serverTools)	Specifies server tools to be included in each request to the Anthropic API.
AnthropicChatModel.AnthropicChatModelBuilder	serverTools(List<AnthropicServerTool> serverTools)	Specifies server tools to be included in each request to the Anthropic API.
AnthropicChatModel.AnthropicChatModelBuilder	stopSequences(List<String> stopSequences)	Sets sequences that, when generated, will cause the model to stop generating further tokens.
AnthropicChatModel.AnthropicChatModelBuilder	strictTools(Boolean strictTools)	Enables strict JSON schema validation for tool input parameters.
AnthropicChatModel.AnthropicChatModelBuilder	supportedCapabilities(Capability... supportedCapabilities)	Declares the capabilities supported by the model (e.g.
AnthropicChatModel.AnthropicChatModelBuilder	supportedCapabilities(Set<Capability> supportedCapabilities)	Declares the capabilities supported by the model.
AnthropicChatModel.AnthropicChatModelBuilder	temperature(Double temperature)	Sets the sampling temperature in the range [0.0, 1.0].
AnthropicChatModel.AnthropicChatModelBuilder	thinkingBudgetTokens(Integer thinkingBudgetTokens)	Configures thinking.
AnthropicChatModel.AnthropicChatModelBuilder	thinkingDisplay(String thinkingDisplay)	Controls how thinking content is returned in the response.
AnthropicChatModel.AnthropicChatModelBuilder	thinkingType(String thinkingType)	Enables thinking.
AnthropicChatModel.AnthropicChatModelBuilder	timeout(Duration timeout)	Sets the HTTP request timeout for calls to the Anthropic API.
AnthropicChatModel.AnthropicChatModelBuilder	toolChoice(ToolChoice toolChoice)	Controls how the model uses tools.
AnthropicChatModel.AnthropicChatModelBuilder	toolChoiceName(String toolChoiceName)	Sets the name of the specific tool the model must use when ToolChoice is set to ToolChoice.REQUIRED.
AnthropicChatModel.AnthropicChatModelBuilder	toolMetadataKeysToSend(String... toolMetadataKeysToSend)	Specifies metadata keys from the ToolSpecification.metadata() to be included in the request.
AnthropicChatModel.AnthropicChatModelBuilder	toolMetadataKeysToSend(Set<String> toolMetadataKeysToSend)	Specifies metadata keys from the ToolSpecification.metadata() to be included in the request.
AnthropicChatModel.AnthropicChatModelBuilder	toolSpecifications(ToolSpecification... toolSpecifications)	Sets the tools (functions) available to the model for function calling.
AnthropicChatModel.AnthropicChatModelBuilder	toolSpecifications(List<ToolSpecification> toolSpecifications)	Sets the list of tools (functions) available to the model for function calling.
AnthropicChatModel.AnthropicChatModelBuilder	topK(Integer topK)	Sets the top-K sampling value.
AnthropicChatModel.AnthropicChatModelBuilder	topP(Double topP)	Sets the nucleus sampling probability (top-p) in the range (0.0, 1.0].
AnthropicChatModel.AnthropicChatModelBuilder	userId(String userId)	Sets the user ID for the requests.
AnthropicChatModel.AnthropicChatModelBuilder	version(String version)	Sets the value of the anthropic-version request header.

Methods inherited from class Object

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

Constructor Details

AnthropicChatModelBuilder

public AnthropicChatModelBuilder()

Method Details

httpClientBuilder

public AnthropicChatModel.AnthropicChatModelBuilder httpClientBuilder(HttpClientBuilder httpClientBuilder)

Sets a custom HttpClientBuilder for the underlying HTTP client. Use this to configure timeouts, proxies, or other HTTP-level settings.

Parameters:

httpClientBuilder - the HTTP client builder

Returns:

this

baseUrl

public AnthropicChatModel.AnthropicChatModelBuilder baseUrl(String baseUrl)

Sets the base URL of the Anthropic API.

Defaults to https://api.anthropic.com/v1/.

Parameters:

baseUrl - the base URL

Returns:

this

apiKey

public AnthropicChatModel.AnthropicChatModelBuilder apiKey(String apiKey)

Sets the Anthropic API key used to authenticate requests.

Parameters:

apiKey - the API key

Returns:

this

version

public AnthropicChatModel.AnthropicChatModelBuilder version(String version)

Sets the value of the anthropic-version request header.

Defaults to 2023-06-01. See the Anthropic API versioning docs.

Parameters:

version - the API version string

Returns:

this

beta

public AnthropicChatModel.AnthropicChatModelBuilder beta(String beta)

Sets the value of the anthropic-beta request header to opt into beta features.

See the Anthropic beta headers docs.

Parameters:

beta - the beta feature identifier

Returns:

this

modelName

public AnthropicChatModel.AnthropicChatModelBuilder modelName(String modelName)

Sets the model to use for chat completions, specified as a string model ID.

See AnthropicChatModelName for available model constants.

Parameters:

modelName - the model ID, e.g. "claude-opus-4-5"

Returns:

this

modelName

public AnthropicChatModel.AnthropicChatModelBuilder modelName(AnthropicChatModelName modelName)

Sets the model to use for chat completions using a type-safe enum constant.

Parameters:

modelName - the model name enum value

Returns:

this

temperature

public AnthropicChatModel.AnthropicChatModelBuilder temperature(Double temperature)

Sets the sampling temperature in the range [0.0, 1.0]. Higher values produce more random output; lower values produce more deterministic output.

Cannot be used together with topP(Double).

Parameters:

temperature - the sampling temperature

Returns:

this

topP

public AnthropicChatModel.AnthropicChatModelBuilder topP(Double topP)

Sets the nucleus sampling probability (top-p) in the range (0.0, 1.0]. Only the tokens whose cumulative probability exceeds this threshold are considered.

Cannot be used together with temperature(Double).

Parameters:

topP - the nucleus sampling threshold

Returns:

this

topK

public AnthropicChatModel.AnthropicChatModelBuilder topK(Integer topK)

Sets the top-K sampling value. Only the topK most-likely next tokens are considered at each step.

Recommended for advanced use only; temperature(Double) is usually sufficient.

Parameters:

topK - the number of top tokens to sample from

Returns:

this

maxTokens

public AnthropicChatModel.AnthropicChatModelBuilder maxTokens(Integer maxTokens)

Sets the maximum number of tokens to generate in the response.

Defaults to 1024 if not set.

Parameters:

maxTokens - the maximum number of output tokens

Returns:

this

stopSequences

public AnthropicChatModel.AnthropicChatModelBuilder stopSequences(List<String> stopSequences)

Sets sequences that, when generated, will cause the model to stop generating further tokens.

Parameters:

stopSequences - the list of stop sequences

Returns:

this

responseFormat

public AnthropicChatModel.AnthropicChatModelBuilder responseFormat(ResponseFormat responseFormat)

Sets the response format, enabling structured output such as JSON mode.

Parameters:

responseFormat - the desired response format

Returns:

this

toolSpecifications

public AnthropicChatModel.AnthropicChatModelBuilder toolSpecifications(List<ToolSpecification> toolSpecifications)

Sets the list of tools (functions) available to the model for function calling.

Parameters:

toolSpecifications - the tool specifications

Returns:

this

toolSpecifications

public AnthropicChatModel.AnthropicChatModelBuilder toolSpecifications(ToolSpecification... toolSpecifications)

Sets the tools (functions) available to the model for function calling.

Parameters:

toolSpecifications - the tool specifications

Returns:

this

toolChoice

public AnthropicChatModel.AnthropicChatModelBuilder toolChoice(ToolChoice toolChoice)

Controls how the model uses tools.

Use ToolChoice.AUTO to let the model decide, ToolChoice.REQUIRED to force tool use, or ToolChoice.NONE to disable tool use.

Parameters:

toolChoice - the tool choice strategy

Returns:

this

toolChoiceName

public AnthropicChatModel.AnthropicChatModelBuilder toolChoiceName(String toolChoiceName)

Sets the name of the specific tool the model must use when ToolChoice is set to ToolChoice.REQUIRED.

Parameters:

toolChoiceName - the name of the tool to force

Returns:

this

disableParallelToolUse

public AnthropicChatModel.AnthropicChatModelBuilder disableParallelToolUse(Boolean disableParallelToolUse)

When set to true, prevents the model from calling multiple tools in a single response turn.

Parameters:

disableParallelToolUse - whether to disable parallel tool use

Returns:

this

serverTools

public AnthropicChatModel.AnthropicChatModelBuilder serverTools(List<AnthropicServerTool> serverTools)

Specifies server tools to be included in each request to the Anthropic API. For example:

AnthropicServerTool webSearchTool = AnthropicServerTool.builder()
    .type("web_search_20250305")
    .name("web_search")
    .addAttribute("max_uses", 5)
    .addAttribute("allowed_domains", List.of("accuweather.com"))
    .build();

returnServerToolResults

public AnthropicChatModel.AnthropicChatModelBuilder returnServerToolResults(Boolean returnServerToolResults)

Controls whether to return server tool results (e.g., web_search, code_execution) inside AiMessage.attributes() under the key "server_tool_results".

Disabled by default to avoid polluting ChatMemory with potentially large data. If enabled, server tool results will be stored as a List<AnthropicServerToolResult> within the AiMessage attributes.

See Also:

• serverTools(List)

serverTools

public AnthropicChatModel.AnthropicChatModelBuilder serverTools(AnthropicServerTool... serverTools)

Specifies server tools to be included in each request to the Anthropic API. For example:

AnthropicServerTool webSearchTool = AnthropicServerTool.builder()
    .type("web_search_20250305")
    .name("web_search")
    .addAttribute("max_uses", 5)
    .addAttribute("allowed_domains", List.of("accuweather.com"))
    .build();

toolMetadataKeysToSend

public AnthropicChatModel.AnthropicChatModelBuilder toolMetadataKeysToSend(Set<String> toolMetadataKeysToSend)

Specifies metadata keys from the ToolSpecification.metadata() to be included in the request.

toolMetadataKeysToSend

public AnthropicChatModel.AnthropicChatModelBuilder toolMetadataKeysToSend(String... toolMetadataKeysToSend)

Specifies metadata keys from the ToolSpecification.metadata() to be included in the request.

cacheSystemMessages

public AnthropicChatModel.AnthropicChatModelBuilder cacheSystemMessages(Boolean cacheSystemMessages)

Enables prompt caching for SystemMessages.

When true, system messages are sent with the cache_control header to allow Anthropic to cache them across requests, reducing cost and latency for repeated prompts. See the prompt caching docs.

Parameters:

cacheSystemMessages - whether to cache system messages

Returns:

this

cacheTools

public AnthropicChatModel.AnthropicChatModelBuilder cacheTools(Boolean cacheTools)

Enables prompt caching for ToolSpecifications.

When true, tool definitions are sent with the cache_control header to allow Anthropic to cache them across requests. See the prompt caching docs.

Parameters:

cacheTools - whether to cache tool definitions

Returns:

this

thinkingType

public AnthropicChatModel.AnthropicChatModelBuilder thinkingType(String thinkingType)

Enables thinking.

thinkingBudgetTokens

public AnthropicChatModel.AnthropicChatModelBuilder thinkingBudgetTokens(Integer thinkingBudgetTokens)

Configures thinking.

thinkingDisplay

public AnthropicChatModel.AnthropicChatModelBuilder thinkingDisplay(String thinkingDisplay)

Controls how thinking content is returned in the response.

Valid values: "summarized" and "omitted". On Claude Opus 4.7 the server default is "omitted"; on earlier Opus/Sonnet models the default is "summarized". Set to "summarized" explicitly on Opus 4.7+ to restore visible thinking text for UIs that render it.

See Also:

• thinkingType(String)
• returnThinking(Boolean)

returnThinking

public AnthropicChatModel.AnthropicChatModelBuilder returnThinking(Boolean returnThinking)

Controls whether to return thinking/reasoning text (if available) inside AiMessage.thinking(). Please note that this does not enable thinking/reasoning for the LLM; it only controls whether to parse the thinking field from the API response and return it inside the AiMessage.

Disabled by default. If enabled, the thinking text will be stored within the AiMessage and may be persisted. If enabled, thinking signatures will also be stored and returned inside the AiMessage.attributes().

See Also:

• thinkingType(String)
• thinkingBudgetTokens(Integer)
• sendThinking(Boolean)

sendThinking

public AnthropicChatModel.AnthropicChatModelBuilder sendThinking(Boolean sendThinking)

Controls whether to send thinking/reasoning text to the LLM in follow-up requests.

Enabled by default. If enabled, the contents of AiMessage.thinking() will be sent in the API request. If enabled, thinking signatures (inside the AiMessage.attributes()) will also be sent.

See Also:

• thinkingType(String)
• thinkingBudgetTokens(Integer)
• returnThinking(Boolean)

timeout

public AnthropicChatModel.AnthropicChatModelBuilder timeout(Duration timeout)

Sets the HTTP request timeout for calls to the Anthropic API.

Parameters:

timeout - the request timeout

Returns:

this

maxRetries

public AnthropicChatModel.AnthropicChatModelBuilder maxRetries(Integer maxRetries)

Sets the number of times to retry a request on transient errors (e.g. rate limits, server errors).

Defaults to 2.

Parameters:

maxRetries - the maximum number of retry attempts

Returns:

this

logRequests

public AnthropicChatModel.AnthropicChatModelBuilder logRequests(Boolean logRequests)

Enables debug logging of HTTP request bodies sent to the Anthropic API.

Parameters:

logRequests - whether to log requests

Returns:

this

logResponses

public AnthropicChatModel.AnthropicChatModelBuilder logResponses(Boolean logResponses)

Enables debug logging of HTTP response bodies received from the Anthropic API.

Parameters:

logResponses - whether to log responses

Returns:

this

logger

public AnthropicChatModel.AnthropicChatModelBuilder logger(org.slf4j.Logger logger)

Parameters:

logger - an alternate Logger to be used instead of the default one provided by Langchain4J for logging requests and responses.

Returns:

this.

listeners

public AnthropicChatModel.AnthropicChatModelBuilder listeners(List<ChatModelListener> listeners)

Sets the list of ChatModelListeners to be notified on each request and response. Useful for logging, metrics, and observability integrations.

Parameters:

listeners - the chat model listeners

Returns:

this

listeners

public AnthropicChatModel.AnthropicChatModelBuilder listeners(ChatModelListener... listeners)

Sets the ChatModelListeners to be notified on each request and response.

Parameters:

listeners - the chat model listeners

Returns:

this

defaultRequestParameters

public AnthropicChatModel.AnthropicChatModelBuilder defaultRequestParameters(ChatRequestParameters parameters)

Sets default ChatRequestParameters that are merged into every request. Individual request parameters take precedence over these defaults.

Parameters:

parameters - the default request parameters

Returns:

this

userId

public AnthropicChatModel.AnthropicChatModelBuilder userId(String userId)

Sets the user ID for the requests. This should be a uuid, hash value, or other opaque identifier. Anthropic may use this id to help detect abuse. Do not include any identifying information such as name, email address, or phone number.

Parameters:

userId - the user identifier

Returns:

this builder

customParameters

public AnthropicChatModel.AnthropicChatModelBuilder customParameters(Map<String,Object> customParameters)

Sets arbitrary extra parameters to include in the Anthropic API request body. Use this for experimental or provider-specific fields not yet covered by dedicated builder methods.

Parameters:

customParameters - a map of parameter names to values

Returns:

this

strictTools

public AnthropicChatModel.AnthropicChatModelBuilder strictTools(Boolean strictTools)

Enables strict JSON schema validation for tool input parameters. When true, the model enforces the exact schema defined in ToolSpecification.

Parameters:

strictTools - whether to enable strict tool schema validation

Returns:

this

customHeaders

public AnthropicChatModel.AnthropicChatModelBuilder customHeaders(Map<String,String> customHeaders)

Sets extra HTTP headers to include in every request to the Anthropic API.

Parameters:

customHeaders - a map of header names to values

Returns:

this

customHeaders

public AnthropicChatModel.AnthropicChatModelBuilder customHeaders(Supplier<Map<String,String>> customHeadersSupplier)

Sets a supplier of extra HTTP headers to include in every request to the Anthropic API. The supplier is called once per request, allowing dynamic header values.

Parameters:

customHeadersSupplier - a supplier that returns a map of header names to values

Returns:

this

supportedCapabilities

public AnthropicChatModel.AnthropicChatModelBuilder supportedCapabilities(Capability... supportedCapabilities)

Declares the capabilities supported by the model (e.g. Capability.RESPONSE_FORMAT_JSON_SCHEMA). This influences how LangChain4j generates requests for this model.

Parameters:

supportedCapabilities - the capabilities to declare

Returns:

this

supportedCapabilities

public AnthropicChatModel.AnthropicChatModelBuilder supportedCapabilities(Set<Capability> supportedCapabilities)

Declares the capabilities supported by the model.

Parameters:

supportedCapabilities - the set of capabilities to declare

Returns:

this

build

public AnthropicChatModel build()