Uses of Class
dev.langchain4j.model.google.genai.GoogleGenAiStreamingChatModel.Builder
Packages that use GoogleGenAiStreamingChatModel.Builder
-
Uses of GoogleGenAiStreamingChatModel.Builder in dev.langchain4j.model.google.genai
Methods in dev.langchain4j.model.google.genai that return GoogleGenAiStreamingChatModel.BuilderModifier and TypeMethodDescriptionGoogleGenAiStreamingChatModel.Builder.allowedFunctionNames(List<String> allowedFunctionNames) Restricts function calling to only the specified function names.GoogleGenAiStreamingChatModel.Builder.apiEndpoint(String apiEndpoint) Overrides the default API endpoint.Sets the Google AI Gemini API key used to authenticate requests.GoogleGenAiStreamingChatModel.builder()GoogleGenAiStreamingChatModel.Builder.cachedContent(String cachedContent) Sets the name of a previously created cached content resource to use with this model.GoogleGenAiStreamingChatModel.Builder.client(com.google.genai.Client client) Sets a pre-configured Google GenAIClient.GoogleGenAiStreamingChatModel.Builder.customHeaders(Map<String, String> customHeaders) Sets extra HTTP headers to include in every request to the Google GenAI API.GoogleGenAiStreamingChatModel.Builder.defaultRequestParameters(ChatRequestParameters defaultRequestParameters) Sets defaultChatRequestParametersthat are merged into every request.GoogleGenAiStreamingChatModel.Builder.enableGoogleMaps(boolean googleMaps) Enables the Google Maps grounding tool, allowing the model to retrieve location-based information.GoogleGenAiStreamingChatModel.Builder.enableGoogleSearch(boolean googleSearch) Enables the Google Search grounding tool, allowing the model to retrieve real-time information from the web.GoogleGenAiStreamingChatModel.Builder.enableUrlContext(boolean urlContext) Enables the URL context tool, allowing the model to read and reason about content at provided URLs.GoogleGenAiStreamingChatModel.Builder.executor(ExecutorService executor) Executor used to drive the blockingResponseStreamiteration off the calling thread.GoogleGenAiStreamingChatModel.Builder.frequencyPenalty(Double frequencyPenalty) Sets the frequency penalty, which reduces the likelihood of repeating tokens proportionally to how often they have appeared in the response so far.GoogleGenAiStreamingChatModel.Builder.googleCredentials(com.google.auth.oauth2.GoogleCredentials credentials) Sets the Google OAuth2 credentials used to authenticate requests via Vertex AI.Sets labels (key-value metadata) attached to the request.GoogleGenAiStreamingChatModel.Builder.listeners(List<ChatModelListener> listeners) Sets the list ofChatModelListeners to be notified on each request and response.Sets the Google Cloud region/location for Vertex AI access (e.g.GoogleGenAiStreamingChatModel.Builder.logRequests(Boolean logRequests) Enables debug logging of request details sent to the Google GenAI API.GoogleGenAiStreamingChatModel.Builder.logRequestsAndResponses(Boolean logRequestsAndResponses) Enables debug logging of both request and response details.GoogleGenAiStreamingChatModel.Builder.logResponses(Boolean logResponses) Enables debug logging of response details received from the Google GenAI API.GoogleGenAiStreamingChatModel.Builder.maxOutputTokens(Integer maxOutputTokens) Sets the maximum number of tokens to generate in the response.Sets the model to use for streaming chat completions.GoogleGenAiStreamingChatModel.Builder.presencePenalty(Double presencePenalty) Sets the presence penalty, which reduces the likelihood of repeating any token that has already appeared in the response, regardless of frequency.Sets the Google Cloud project ID for Vertex AI access.GoogleGenAiStreamingChatModel.Builder.responseFormat(ResponseFormat responseFormat) Sets the response format, enabling structured output such as JSON mode or JSON Schema.GoogleGenAiStreamingChatModel.Builder.safetySettings(List<com.google.genai.types.SafetySetting> safetySettings) Sets safety content filter settings to block harmful content.Sets the random seed for deterministic output.GoogleGenAiStreamingChatModel.Builder.stopSequences(List<String> stopSequences) Sets sequences that, when generated, will cause the model to stop generating further tokens.GoogleGenAiStreamingChatModel.Builder.temperature(Double temperature) Sets the sampling temperature in the range[0.0, 2.0].GoogleGenAiStreamingChatModel.Builder.thinkingBudget(Integer thinkingBudget) The thinking budget to use.GoogleGenAiStreamingChatModel.Builder.thinkingLevel(String thinkingLevel) The thinking level to use.Sets the HTTP request timeout for calls to the Google GenAI API.Sets the top-K sampling value.Sets the nucleus sampling probability (top-p).GoogleGenAiStreamingChatModel.Builder.vertexSearchDatastore(String vertexSearchDatastore) Sets the Vertex AI Search datastore to use for grounding the model's responses with enterprise data.