Class AnthropicChatModel.AnthropicChatModelBuilder

java.lang.Object
dev.langchain4j.model.anthropic.AnthropicChatModel.AnthropicChatModelBuilder
Enclosing class:
AnthropicChatModel
public static class AnthropicChatModel.AnthropicChatModelBuilder extends Object

  • Constructor Details

    • AnthropicChatModelBuilder

      public AnthropicChatModelBuilder()

  • Method Details

    • httpClientBuilder

      public AnthropicChatModel.AnthropicChatModelBuilder httpClientBuilder(dev.langchain4j.http.client.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(dev.langchain4j.model.chat.request.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<dev.langchain4j.agent.tool.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(dev.langchain4j.agent.tool.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(dev.langchain4j.model.chat.request.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

      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:

    • 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:

    • 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:

    • 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<dev.langchain4j.model.chat.listener.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(dev.langchain4j.model.chat.listener.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(dev.langchain4j.model.chat.request.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(dev.langchain4j.model.chat.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<dev.langchain4j.model.chat.Capability> supportedCapabilities)
      Declares the capabilities supported by the model.
      Parameters:
      supportedCapabilities - the set of capabilities to declare
      Returns:
      this

    • build

      public AnthropicChatModel build()