Index (Quarkus Langchain4j - OpenAI

A

apiKey() - Method in interface io.quarkiverse.langchain4j.openai.runtime.config.Langchain4jOpenAiConfig: OpenAI API key

baseUrl() - Method in interface io.quarkiverse.langchain4j.openai.runtime.config.Langchain4jOpenAiConfig: Base URL of OpenAI API

chatModel() - Method in interface io.quarkiverse.langchain4j.openai.runtime.config.Langchain4jOpenAiConfig: Chat model related settings
chatModel(Langchain4jOpenAiConfig) - Method in class io.quarkiverse.langchain4j.openai.runtime.OpenAiRecorder
ChatModelConfig - Interface in io.quarkiverse.langchain4j.openai.runtime.config
cleanUp(ShutdownContext) - Method in class io.quarkiverse.langchain4j.openai.runtime.OpenAiRecorder

embeddingModel() - Method in interface io.quarkiverse.langchain4j.openai.runtime.config.Langchain4jOpenAiConfig: Embedding model related settings
embeddingModel(Langchain4jOpenAiConfig) - Method in class io.quarkiverse.langchain4j.openai.runtime.OpenAiRecorder
EmbeddingModelConfig - Interface in io.quarkiverse.langchain4j.openai.runtime.config

frequencyPenalty() - Method in interface io.quarkiverse.langchain4j.openai.runtime.config.ChatModelConfig: Number between -2.0 and 2.0.

io.quarkiverse.langchain4j.openai.runtime - package io.quarkiverse.langchain4j.openai.runtime
io.quarkiverse.langchain4j.openai.runtime.config - package io.quarkiverse.langchain4j.openai.runtime.config

Langchain4jOpenAiConfig - Interface in io.quarkiverse.langchain4j.openai.runtime.config
logRequests() - Method in interface io.quarkiverse.langchain4j.openai.runtime.config.Langchain4jOpenAiConfig: Whether the OpenAI client should log requests
logResponses() - Method in interface io.quarkiverse.langchain4j.openai.runtime.config.Langchain4jOpenAiConfig: Whether the OpenAI client should log responses

maxRetries() - Method in interface io.quarkiverse.langchain4j.openai.runtime.config.Langchain4jOpenAiConfig: The maximum number of times to retry
maxTokens() - Method in interface io.quarkiverse.langchain4j.openai.runtime.config.ChatModelConfig: The maximum number of tokens to generate in the completion.
modelName() - Method in interface io.quarkiverse.langchain4j.openai.runtime.config.ChatModelConfig: Model name to use
modelName() - Method in interface io.quarkiverse.langchain4j.openai.runtime.config.EmbeddingModelConfig: Model name to use
modelName() - Method in interface io.quarkiverse.langchain4j.openai.runtime.config.ModerationModelConfig: Model name to use
moderationModel() - Method in interface io.quarkiverse.langchain4j.openai.runtime.config.Langchain4jOpenAiConfig: Moderation model related settings
moderationModel(Langchain4jOpenAiConfig) - Method in class io.quarkiverse.langchain4j.openai.runtime.OpenAiRecorder
ModerationModelConfig - Interface in io.quarkiverse.langchain4j.openai.runtime.config

OpenAiRecorder - Class in io.quarkiverse.langchain4j.openai.runtime
OpenAiRecorder() - Constructor for class io.quarkiverse.langchain4j.openai.runtime.OpenAiRecorder

presencePenalty() - Method in interface io.quarkiverse.langchain4j.openai.runtime.config.ChatModelConfig: Number between -2.0 and 2.0.

streamingChatModel(Langchain4jOpenAiConfig) - Method in class io.quarkiverse.langchain4j.openai.runtime.OpenAiRecorder

temperature() - Method in interface io.quarkiverse.langchain4j.openai.runtime.config.ChatModelConfig: What sampling temperature to use, with values between 0 and 2.
timeout() - Method in interface io.quarkiverse.langchain4j.openai.runtime.config.Langchain4jOpenAiConfig: Timeout for OpenAI calls
topP() - Method in interface io.quarkiverse.langchain4j.openai.runtime.config.ChatModelConfig: An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with topP probability mass.