IsValid checks if the cache is valid (less than 1 hour old).

Load loads the model cache from the file.

Save saves the model cache to the file.

StreamingSSEResponse handles streaming responses from OpenAI's API.

WithMaxCompletionTokens specifies the max number of completion tokens to generate.

WithMaxTokens specifies the max number of tokens to generate.

WithModel specifies which model name to use.

WithN will add an option to set how many chat completion choices to generate for each input message.

WithSeed will add an option to use deterministic sampling.

WithTemperature specifies the model temperature, a hyperparameter that regulates the randomness, or creativity, of the AI's responses.

WithTopP will add an option to use top-p sampling.

Chat message role defined by the OpenAI API.

Chat message role defined by the OpenAI API.

Chat message role defined by the OpenAI API.

Chat message role defined by the OpenAI API.

Chat message role defined by the OpenAI API.

Chat message role defined by the OpenAI API.

Provider constants for all supported providers.

Provider constants for all supported providers.

Provider constants for all supported providers.

Provider constants for all supported providers.

Provider constants for all supported providers.

Provider constants for all supported providers.

Provider constants for all supported providers.

Provider constants for all supported providers.

Provider constants for all supported providers.

Provider constants for all supported providers.

Provider constants for all supported providers.

Provider constants for all supported providers.

ChatCompletionRequest represents a request structure for chat completion API.

ChatCompletionResponse represents a response structure for chat completion API.

CompletionTokensDetails Breakdown of tokens used in a completion.

LogProb represents the probability information for a token.

LogProbs is the top-level structure containing the log probability information.

Model represents a language model in the LLM system.

ModelCache represents the cache of models.

PromptTokensDetails Breakdown of tokens used in the prompt.

Provider represents a provider of LLM services.

Usage Represents the total token usage per request to OpenAI.

Deprecated: use FunctionDefinition instead.

ProviderType is a string type for the names of supported LLM providers.

RequestOption is a function that configures a ChatCompletionRequest.