chatmodel

type Anthropic struct {
	schema.Tokenizer
	// contains filtered or unexported fields
}

type AnthropicClient interface {
	CreateCompletion(ctx context.Context, request *anthropic.CompletionRequest) (*anthropic.CompletionResponse, error)
}

type AnthropicOptions struct {
	*schema.CallbackOptions `map:"-"`
	schema.Tokenizer        `map:"-"`

	// Model name to use.
	ModelName string `map:"model_name,omitempty"`

	// Temperature parameter controls the randomness of the generation output.
	Temperature float32 `map:"temperature,omitempty"`

	// Denotes the number of tokens to predict per generation.
	MaxTokens int `map:"max_tokens,omitempty"`

	// TopK parameter specifies the number of highest probability tokens to consider for generation.
	TopK int `map:"top_k,omitempty"`

	// TopP parameter specifies the cumulative probability threshold for generating tokens.
	TopP float32 `map:"top_p,omitempty"`
}

type AzureOpenAI struct {
	*OpenAI
	// contains filtered or unexported fields
}

type AzureOpenAIOptions struct {
	OpenAIOptions
	Deployment string `map:"deployment,omitempty"`
}

type Bedrock struct {
	schema.Tokenizer
	// contains filtered or unexported fields
}

type BedrockAnthropicOptions struct {
	*schema.CallbackOptions `map:"-"`
	schema.Tokenizer        `map:"-"`

	// Model id to use.
	ModelID string `map:"model_id,omitempty"`

	// MaxTokensToSmaple sets the maximum number of tokens in the generated text.
	MaxTokensToSample int `map:"max_tokens_to_sample"`

	// Temperature controls the randomness of text generation. Higher values make it more random.
	Temperature float32 `map:"temperature"`

	// TopP is the total probability mass of tokens to consider at each step.
	TopP float32 `map:"top_p,omitempty"`

	// TopK determines how the model selects tokens for output.
	TopK int `map:"top_k"`

	// Stream indicates whether to stream the results or not.
	Stream bool `map:"stream,omitempty"`
}

type BedrockInputOutputAdapter struct {
	// contains filtered or unexported fields
}

type BedrockMetaOptions struct {
	*schema.CallbackOptions `map:"-"`
	schema.Tokenizer        `map:"-"`

	// Model id to use.
	ModelID string `map:"model_id,omitempty"`

	// Temperature controls the randomness of text generation. Higher values make it more random.
	Temperature float32 `map:"temperature"`

	// TopP is the total probability mass of tokens to consider at each step.
	TopP float32 `map:"top_p,omitempty"`

	// MaxGenLen specify the maximum number of tokens to use in the generated response.
	MaxGenLen int `map:"max_gen_len"`

	// Stream indicates whether to stream the results or not.
	Stream bool `map:"stream,omitempty"`
}

type BedrockOptions struct {
	*schema.CallbackOptions `map:"-"`
	schema.Tokenizer        `map:"-"`

	// Model params to use.
	ModelParams map[string]any `map:"model_params,omitempty"`

	// Stream indicates whether to stream the results or not.
	Stream bool `map:"stream,omitempty"`
}

type BedrockRuntimeClient interface {
	InvokeModel(ctx context.Context, params *bedrockruntime.InvokeModelInput, optFns ...func(*bedrockruntime.Options)) (*bedrockruntime.InvokeModelOutput, error)
	InvokeModelWithResponseStream(ctx context.Context, params *bedrockruntime.InvokeModelWithResponseStreamInput, optFns ...func(*bedrockruntime.Options)) (*bedrockruntime.InvokeModelWithResponseStreamOutput, error)
}

type Cohere struct {
	schema.Tokenizer
	// contains filtered or unexported fields
}

type CohereClient interface {
	// Chat performs a non-streaming chat with the Cohere API, generating a response based on the provided request.
	// It returns a non-streamed response or an error if the operation fails.
	Chat(ctx context.Context, request *cohere.ChatRequest, opts ...core.RequestOption) (*cohere.NonStreamedChatResponse, error)

	// ChatStream performs a streaming chat with the Cohere API, generating responses in a stream based on the provided request.
	// It returns a stream of responses or an error if the operation fails.
	ChatStream(ctx context.Context, request *cohere.ChatStreamRequest, opts ...core.RequestOption) (*core.Stream[cohere.StreamedChatResponse], error)
}

type CohereOptions struct {
	// CallbackOptions specify options for handling callbacks during text generation.
	*schema.CallbackOptions `map:"-"`

	// Tokenizer represents the tokenizer to be used with the LLM model.
	schema.Tokenizer `map:"-"`

	// Model represents the name or identifier of the Cohere language model to use.
	Model string `map:"model,omitempty"`

	// Temperature is a non-negative float that tunes the degree of randomness in generation.
	Temperature float64 `map:"temperature"`

	// MaxRetries represents the maximum number of retries to make when generating.
	MaxRetries uint `map:"max_retries,omitempty"`

	// Stream indicates whether to stream the results or not.
	Stream bool `map:"stream,omitempty"`
}

type Ernie struct {
	schema.Tokenizer
	// contains filtered or unexported fields
}

type ErnieClient interface {
	CreateChatCompletion(ctx context.Context, model string, request *ernie.ChatCompletionRequest) (*ernie.ChatCompletionResponse, error)
}

type ErnieOptions struct {
	*schema.CallbackOptions `map:"-"`
	schema.Tokenizer        `map:"-"`

	// ModelName is the name of the Ernie chat model to use.
	ModelName string `map:"model_name,omitempty"`

	// Temperature is the sampling temperature to use during text generation.
	Temperature float64 `map:"temperature,omitempty"`

	// TopP is the total probability mass of tokens to consider at each step.
	TopP float64 `map:"top_p,omitempty"`

	// PenaltyScore is a parameter used during text generation to apply a penalty for generating longer responses.
	PenaltyScore float64 `map:"penalty_score"`
}

type Fake struct {
	schema.Tokenizer
	// contains filtered or unexported fields
}

type FakeOptions struct {
	*schema.CallbackOptions `map:"-"`
	schema.Tokenizer        `map:"-"`
	ChatModelType           string `map:"-"`
}

type FakeResultFunc func(ctx context.Context, messages schema.ChatMessages) (*schema.ModelResult, error)

type GoogleGenAI struct {
	schema.Tokenizer
	// contains filtered or unexported fields
}

type GoogleGenAIClient interface {
	GenerateContent(context.Context, *generativelanguagepb.GenerateContentRequest, ...gax.CallOption) (*generativelanguagepb.GenerateContentResponse, error)
	StreamGenerateContent(ctx context.Context, req *generativelanguagepb.GenerateContentRequest, opts ...gax.CallOption) (generativelanguagepb.GenerativeService_StreamGenerateContentClient, error)
	CountTokens(context.Context, *generativelanguagepb.CountTokensRequest, ...gax.CallOption) (*generativelanguagepb.CountTokensResponse, error)
}

type GoogleGenAIOptions struct {
	// CallbackOptions specify options for handling callbacks during text generation.
	*schema.CallbackOptions `map:"-"`
	// Tokenizer represents the tokenizer to be used with the LLM model.
	schema.Tokenizer `map:"-"`
	// ModelName is the name of the GoogleGenAI model to use.
	ModelName string `map:"model_name,omitempty"`
	// CandidateCount is the number of candidate generations to consider.
	CandidateCount int32 `map:"candidate_count,omitempty"`
	// MaxOutputTokens is the maximum number of tokens to generate in the output.
	MaxOutputTokens int32 `map:"max_output_tokens,omitempty"`
	// Temperature controls the randomness of the generation. Higher values make the output more random.
	Temperature float32 `map:"temperature,omitempty"`
	// TopP is the nucleus sampling parameter. It controls the cumulative probability of the most likely tokens to sample from.
	TopP float32 `map:"top_p,omitempty"`
	// TopK is the number of top tokens to consider for sampling.
	TopK int32 `map:"top_k,omitempty"`
	// Stream indicates whether to stream the results or not.
	Stream bool `map:"stream,omitempty"`
}

type Ollama struct {
	schema.Tokenizer
	// contains filtered or unexported fields
}

type OllamaClient interface {
	// CreateChat produces a single request and response for the Ollama generative model.
	CreateChat(ctx context.Context, req *ollama.ChatRequest) (*ollama.ChatResponse, error)
	// CreateChatStream initiates a streaming request and returns a stream for the Ollama generative model.
	CreateChatStream(ctx context.Context, req *ollama.ChatRequest) (*ollama.ChatStream, error)
}

type OllamaOptions struct {
	// CallbackOptions specify options for handling callbacks during text generation.
	*schema.CallbackOptions `map:"-"`
	// Tokenizer represents the tokenizer to be used with the LLM model.
	schema.Tokenizer `map:"-"`
	// ModelName is the name of the Gemini model to use.
	ModelName string `map:"model_name,omitempty"`
	// Temperature controls the randomness of the generation. Higher values make the output more random.
	Temperature float32 `map:"temperature,omitempty"`
	// MaxTokens is the maximum number of tokens to generate in the completion.
	MaxTokens int `map:"max_tokens,omitempty"`
	// TopP is the nucleus sampling parameter. It controls the cumulative probability of the most likely tokens to sample from.
	TopP float32 `map:"top_p,omitempty"`
	// TopK is the number of top tokens to consider for sampling.
	TopK int `map:"top_k,omitempty"`
	// PresencePenalty penalizes repeated tokens.
	PresencePenalty float32 `map:"presence_penalty,omitempty"`
	// FrequencyPenalty penalizes repeated tokens according to frequency.
	FrequencyPenalty float32 `map:"frequency_penalty,omitempty"`
	// Stream indicates whether to stream the results or not.
	Stream bool `map:"stream,omitempty"`
}

type OpenAI struct {
	schema.Tokenizer
	// contains filtered or unexported fields
}

type OpenAIClient interface {
	CreateChatCompletion(ctx context.Context, request openai.ChatCompletionRequest) (response openai.ChatCompletionResponse, err error)
	CreateChatCompletionStream(ctx context.Context, request openai.ChatCompletionRequest) (stream *openai.ChatCompletionStream, err error)
}

type OpenAIOptions struct {
	*schema.CallbackOptions `map:"-"`
	schema.Tokenizer        `map:"-"`
	// Model name to use.
	ModelName string `map:"model_name,omitempty"`
	// Sampling temperature to use.
	Temperature float32 `map:"temperature,omitempty"`
	// The maximum number of tokens to generate in the completion.
	// -1 returns as many tokens as possible given the prompt and
	//the models maximal context size.
	MaxTokens int `map:"max_tokens,omitempty"`
	// Total probability mass of tokens to consider at each step.
	TopP float32 `map:"top_p,omitempty"`
	// Penalizes repeated tokens.
	PresencePenalty float32 `map:"presence_penalty,omitempty"`
	// Penalizes repeated tokens according to frequency.
	FrequencyPenalty float32 `map:"frequency_penalty,omitempty"`
	// How many completions to generate for each prompt.
	N int `map:"n,omitempty"`
	// BaseURL is the base URL of the OpenAI service.
	BaseURL string `map:"base_url,omitempty"`
	// OrgID is the organization ID for accessing the OpenAI service.
	OrgID string `map:"org_id,omitempty"`
	// Stream indicates whether to stream the results or not.
	Stream bool `map:"stream,omitempty"`
	// MaxRetries represents the maximum number of retries to make when generating.
	MaxRetries uint `map:"max_retries,omitempty"`
}