Class AnthropicBatchChatModel.Builder

java.lang.Object

dev.langchain4j.model.anthropic.AnthropicBatchChatModel.Builder

Enclosing class:

AnthropicBatchChatModel

public static final class AnthropicBatchChatModel.Builder
extends Object

Method Summary

Modifier and Type	Method	Description
AnthropicBatchChatModel.Builder	apiKey(String apiKey)	Sets the Anthropic API key used to authenticate requests.
AnthropicBatchChatModel.Builder	baseUrl(String baseUrl)	Sets the base URL of the Anthropic API.
AnthropicBatchChatModel.Builder	beta(String beta)	Sets the value of the anthropic-beta request header to opt into beta features.
AnthropicBatchChatModel	build()
AnthropicBatchChatModel.Builder	customHeaders(Supplier<Map<String,String>> customHeadersSupplier)	Sets a supplier of custom HTTP headers, invoked for every request to the Anthropic API.
AnthropicBatchChatModel.Builder	customHeaders(Map<String,String> customHeaders)	Sets custom HTTP headers sent with every request to the Anthropic API.
AnthropicBatchChatModel.Builder	customParameters(Map<String,Object> customParameters)	Sets additional top-level parameters added verbatim to every batched request body.
AnthropicBatchChatModel.Builder	defaultRequestParameters(ChatRequestParameters parameters)	Sets the default ChatRequestParameters applied to every batched request.
AnthropicBatchChatModel.Builder	httpClientBuilder(HttpClientBuilder httpClientBuilder)	Sets a custom HttpClientBuilder for the underlying HTTP client.
AnthropicBatchChatModel.Builder	logRequests(Boolean logRequests)	Enables debug logging of HTTP request bodies sent to the Anthropic API.
AnthropicBatchChatModel.Builder	logResponses(Boolean logResponses)	Enables debug logging of HTTP response bodies received from the Anthropic API.
AnthropicBatchChatModel.Builder	maxRetries(Integer maxRetries)	Sets the number of times to retry a request on transient errors (e.g. rate limits, server errors).
AnthropicBatchChatModel.Builder	maxTokens(Integer maxTokens)	Sets the maximum number of tokens to generate per batched request.
AnthropicBatchChatModel.Builder	modelName(AnthropicChatModelName modelName)	Sets the model applied to every batched request.
AnthropicBatchChatModel.Builder	modelName(String modelName)	Sets the model applied to every batched request, specified as a string model ID.
AnthropicBatchChatModel.Builder	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".
AnthropicBatchChatModel.Builder	returnThinking(Boolean returnThinking)	Controls whether thinking returned by the API is stored in AiMessage.thinking().
AnthropicBatchChatModel.Builder	serverTools(AnthropicServerTool... serverTools)
AnthropicBatchChatModel.Builder	serverTools(List<AnthropicServerTool> serverTools)	Specifies server tools (e.g. web search, code execution) to be included in every batched request.
AnthropicBatchChatModel.Builder	skills(AnthropicSkill... skills)
AnthropicBatchChatModel.Builder	skills(List<AnthropicSkill> skills)	Enables Anthropic Agent Skills for every batched request.
AnthropicBatchChatModel.Builder	stopSequences(List<String> stopSequences)	Sets sequences that, when generated, will cause the model to stop generating further tokens.
AnthropicBatchChatModel.Builder	strictTools(Boolean strictTools)	Enables strict mode for tools, guaranteeing that generated tool arguments match the tool's schema.
AnthropicBatchChatModel.Builder	temperature(Double temperature)	Sets the sampling temperature in the range [0.0, 1.0].
AnthropicBatchChatModel.Builder	thinkingDisplay(String thinkingDisplay)	Controls how thinking is returned by the API, e.g.
AnthropicBatchChatModel.Builder	timeout(Duration timeout)	Sets the HTTP request timeout for calls to the Anthropic API.
AnthropicBatchChatModel.Builder	toolMetadataKeysToSend(String... toolMetadataKeysToSend)
AnthropicBatchChatModel.Builder	toolMetadataKeysToSend(Set<String> toolMetadataKeysToSend)	Specifies metadata keys from the ToolSpecification.metadata() to be included in the request.
AnthropicBatchChatModel.Builder	topK(Integer topK)	Sets the top-K sampling value.
AnthropicBatchChatModel.Builder	topP(Double topP)	Sets the nucleus sampling probability (top-p) in the range (0.0, 1.0].
AnthropicBatchChatModel.Builder	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

Method Details

httpClientBuilder

public AnthropicBatchChatModel.Builder 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 AnthropicBatchChatModel.Builder 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 AnthropicBatchChatModel.Builder apiKey(String apiKey)

Sets the Anthropic API key used to authenticate requests.

Parameters:

apiKey - the API key

Returns:

this

version

public AnthropicBatchChatModel.Builder 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 AnthropicBatchChatModel.Builder 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 AnthropicBatchChatModel.Builder modelName(String modelName)

Sets the model applied to every batched request, specified as a string model ID.

See AnthropicChatModelName for available model constants. It can be overridden per request via ChatRequestParameters.modelName().

Parameters:

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

Returns:

this

modelName

public AnthropicBatchChatModel.Builder modelName(AnthropicChatModelName modelName)

Sets the model applied to every batched request.

It can be overridden per request via ChatRequestParameters.modelName().

Parameters:

modelName - the model

Returns:

this

maxTokens

public AnthropicBatchChatModel.Builder maxTokens(Integer maxTokens)

Sets the maximum number of tokens to generate per batched request.

Defaults to 1024 if not set.

Parameters:

maxTokens - the maximum number of output tokens

Returns:

this

temperature

public AnthropicBatchChatModel.Builder 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 AnthropicBatchChatModel.Builder 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 AnthropicBatchChatModel.Builder 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

stopSequences

public AnthropicBatchChatModel.Builder 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

timeout

public AnthropicBatchChatModel.Builder timeout(Duration timeout)

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

Parameters:

timeout - the request timeout

Returns:

this

maxRetries

public AnthropicBatchChatModel.Builder 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 AnthropicBatchChatModel.Builder 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 AnthropicBatchChatModel.Builder logResponses(Boolean logResponses)

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

Parameters:

logResponses - whether to log responses

Returns:

this

defaultRequestParameters

public AnthropicBatchChatModel.Builder defaultRequestParameters(ChatRequestParameters parameters)

Sets the default ChatRequestParameters applied to every batched request.

Pass AnthropicChatRequestParameters to configure Anthropic-specific defaults such as thinking, prompt caching and tool choice. Individual builder methods (e.g. modelName(String)) take precedence over the corresponding value here, and per-request parameters take precedence over both.

Parameters:

parameters - the default request parameters

Returns:

this

thinkingDisplay

public AnthropicBatchChatModel.Builder thinkingDisplay(String thinkingDisplay)

Controls how thinking is returned by the API, e.g. "summarized" or "omitted".

Applies only when thinking is enabled via AnthropicChatRequestParameters.Builder.thinkingType(String).

Parameters:

thinkingDisplay - the thinking display mode

Returns:

this

See Also:

• returnThinking(Boolean)

returnThinking

public AnthropicBatchChatModel.Builder returnThinking(Boolean returnThinking)

Controls whether thinking returned by the API is stored in AiMessage.thinking().

Disabled by default. Unlike AnthropicChatModel, this is resolved once per model rather than per request, because results are mapped in AnthropicBatchChatModel.retrieve(String), which has no access to the originating request.

Parameters:

returnThinking - whether to return thinking

Returns:

this

returnServerToolResults

public AnthropicBatchChatModel.Builder 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 returning potentially large data.

Parameters:

returnServerToolResults - whether to return server tool results

Returns:

this

See Also:

• serverTools(List)

serverTools

public AnthropicBatchChatModel.Builder serverTools(List<AnthropicServerTool> serverTools)

Specifies server tools (e.g. web search, code execution) to be included in every batched request.

Parameters:

serverTools - the server tools

Returns:

this

See Also:

• AnthropicChatModel.AnthropicChatModelBuilder.serverTools(List)

serverTools

public AnthropicBatchChatModel.Builder serverTools(AnthropicServerTool... serverTools)

See Also:

• serverTools(List)

skills

public AnthropicBatchChatModel.Builder skills(List<AnthropicSkill> skills)

Enables Anthropic Agent Skills for every batched request.

The required beta features must be opted into via beta(String).

Parameters:

skills - the skills to enable

Returns:

this

See Also:

• AnthropicChatModel.AnthropicChatModelBuilder.skills(List)

skills

public AnthropicBatchChatModel.Builder skills(AnthropicSkill... skills)

See Also:

• skills(List)

toolMetadataKeysToSend

public AnthropicBatchChatModel.Builder toolMetadataKeysToSend(Set<String> toolMetadataKeysToSend)

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

Parameters:

toolMetadataKeysToSend - the metadata keys

Returns:

this

toolMetadataKeysToSend

public AnthropicBatchChatModel.Builder toolMetadataKeysToSend(String... toolMetadataKeysToSend)

See Also:

• toolMetadataKeysToSend(Set)

strictTools

public AnthropicBatchChatModel.Builder strictTools(Boolean strictTools)

Enables strict mode for tools, guaranteeing that generated tool arguments match the tool's schema.

Parameters:

strictTools - whether tools are strict

Returns:

this

customParameters

public AnthropicBatchChatModel.Builder customParameters(Map<String,Object> customParameters)

Sets additional top-level parameters added verbatim to every batched request body. Use this to send parameters that are not yet supported by langchain4j.

Parameters:

customParameters - the custom parameters

Returns:

this

customHeaders

public AnthropicBatchChatModel.Builder customHeaders(Map<String,String> customHeaders)

Sets custom HTTP headers sent with every request to the Anthropic API.

Parameters:

customHeaders - a map of header names to values

Returns:

this

customHeaders

public AnthropicBatchChatModel.Builder customHeaders(Supplier<Map<String,String>> customHeadersSupplier)

Sets a supplier of custom HTTP headers, invoked for every request to the Anthropic API. Use this when header values need to be refreshed, e.g. for short-lived tokens.

Parameters:

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

Returns:

this

build

public AnthropicBatchChatModel build()

Returns:

a new AnthropicBatchChatModel configured with this builder's values.