Documentation
¶
Overview ¶
openai implements an API client for OpenAI https://platform.openai.com/docs/api-reference
Index ¶
- func OptOrganization(value string) client.ClientOpt
- type Chat
- type Client
- func (c *Client) Chat(messages []*Message, opts ...Opt) (Chat, error)
- func (c *Client) CreateEmbedding(content any, opts ...Opt) (schema.Embeddings, error)
- func (c *Client) CreateImages(prompt string, opts ...Opt) ([]*Image, error)
- func (c *Client) DeleteModel(model string) error
- func (c *Client) GetModel(model string) (schema.Model, error)
- func (c *Client) ListModels() ([]schema.Model, error)
- func (c *Client) Speech(w io.Writer, voice, text string, opts ...Opt) (int64, error)
- func (c *Client) Transcribe(r io.Reader, opts ...Opt) (*Transcription, error)
- func (c *Client) Translate(r io.Reader, opts ...Opt) (*Transcription, error)
- func (c *Client) WriteImage(w io.Writer, image *Image) (int, error)
- type Image
- type Message
- type MessageChoice
- type MessageContent
- type MessageContentArray
- type MessageContentImageFile
- type MessageContentImageUrl
- type Opt
- func OptCount(value int) Opt
- func OptFrequencyPenalty(value float64) Opt
- func OptFunction(name, description string, parameters ...ToolParameter) Opt
- func OptLanguage(language string) Opt
- func OptMaxTokens(value int) Opt
- func OptModel(value string) Opt
- func OptPresencePenalty(value float64) Opt
- func OptPrompt(prompt string) Opt
- func OptQuality(value string) Opt
- func OptResponseFormat(value string) Opt
- func OptSeed(value int) Opt
- func OptSize(w, h uint) Opt
- func OptSpeed(speed float32) Opt
- func OptStream(value bool) Opt
- func OptStyle(style string) Opt
- func OptTemperature(value float64) Opt
- type Request
- type Tool
- type ToolFunction
- type ToolParameter
- type ToolParameters
- type Transcription
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
func OptOrganization ¶
func OptOrganization(value string) client.ClientOpt
Set an organization where the user has access to multiple organizations
Types ¶
type Chat ¶
type Chat struct {
Id string `json:"id"`
Object string `json:"object"`
Created int64 `json:"created"`
Model string `json:"model"`
SystemFingerprint string `json:"system_fingerprint,omitempty"`
Choices []*MessageChoice `json:"choices"`
Usage struct {
PromptTokens int `json:"prompt_tokens"`
CompletionTokens int `json:"completion_tokens"`
TotalTokens int `json:"total_tokens"`
} `json:"usage"`
}
A chat completion object
type Client ¶
type Client struct {
*client.Client
}
func (*Client) CreateEmbedding ¶
CreateEmbedding creates an embedding from a string or array of strings
func (*Client) CreateImages ¶
CreateImage generates one or more images from a prompt
func (*Client) DeleteModel ¶
Delete a fine-tuned model. You must have the Owner role in your organization to delete a model.
func (*Client) ListModels ¶
ListModels returns all the models
func (*Client) Speech ¶ added in v0.0.3
Creates audio for the given text, outputs to the writer and returns the number of bytes written
func (*Client) Transcribe ¶ added in v0.0.3
Transcribes audio from audio data
type Image ¶
type Image struct {
Url string `json:"url,omitempty"`
Data string `json:"b64_json,omitempty"`
RevisedPrompt string `json:"revised_prompt,omitempty"`
}
An image
type Message ¶
type Message struct {
Role string `json:"role"`
Content MessageContentArray `json:"content,omitempty"`
Name string `json:"name,omitempty"`
ToolCalls []struct {
Id string `json:"id"`
Type string `json:"type"`
Function struct {
Name string `json:"name"`
Arguments string `json:"arguments"`
} `json:"function"`
} `json:"tool_calls,omitempty"`
ToolCallId string `json:"tool_call_id,omitempty"`
}
A message choice object
func NewMessage ¶
func (*Message) AppendImageFile ¶
func (*Message) AppendImageUrl ¶
func (*Message) AppendText ¶
type MessageChoice ¶
type MessageChoice struct {
Index int `json:"index"`
FinishReason string `json:"finish_reason,omitempty"`
Message *Message `json:"message,omitempty"`
}
A message choice object
type MessageContent ¶
type MessageContent struct {
Type string `json:"type"`
Text *string `json:"text,omitempty"`
ImageFile *MessageContentImageFile `json:"image_file,omitempty"`
ImageUrl *MessageContentImageUrl `json:"image_url,omitempty"`
}
Message content
type MessageContentArray ¶
type MessageContentArray []MessageContent
A message content array
func (MessageContentArray) Flatten ¶
func (arr MessageContentArray) Flatten() string
Return the text of the message
func (*MessageContentArray) UnmarshalJSON ¶
func (c *MessageContentArray) UnmarshalJSON(data []byte) error
type MessageContentImageFile ¶
type MessageContentImageFile struct {
File string `json:"file_id"`
}
Message content image file
type MessageContentImageUrl ¶
type MessageContentImageUrl struct {
Url string `json:"url"`
}
Message content image url
type Opt ¶
type ChatCompletionOpt func(*chatRequest) error type ImageOpt func(*imageRequest) error
func OptFrequencyPenalty ¶
Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
func OptFunction ¶
func OptFunction(name, description string, parameters ...ToolParameter) Opt
When set, system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.
func OptLanguage ¶ added in v0.0.3
The language for transcription. Supplying the input language in ISO-639-1 format will improve accuracy and latency.
func OptMaxTokens ¶
How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep n as 1 to minimize costs.
func OptPresencePenalty ¶
Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
func OptPrompt ¶ added in v0.0.3
An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language.
func OptQuality ¶
The quality of the image that will be generated. hd creates images with finer details and greater consistency across the image. This param is only supported for dall-e-3.
func OptResponseFormat ¶
Format of the returned response, use "json_format" to enable JSON mode, which guarantees the message the model generates is valid JSON. Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message.
func OptSeed ¶
When set, system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.
func OptSize ¶
The size of the generated images. Must be one of 256x256, 512x512, or 1024x1024 for dall-e-2. Must be one of 1024x1024, 1792x1024, or 1024x1792 for dall-e-3 models.
func OptSpeed ¶ added in v0.0.3
The speed of the generated audio. Select a value from 0.25 to 4.0. 1.0 is the default.
func OptStream ¶
Partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE]
func OptStyle ¶
The style of the generated images. Must be one of vivid or natural. Vivid causes the model to lean towards generating hyper-real and dramatic images. Natural causes the model to produce more natural, less hyper-real looking images. This param is only supported for dall-e-3.
func OptTemperature ¶
When set, system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.
type Request ¶
type Request interface {
// contains filtered or unexported methods
}
An abstract request object
type Tool ¶
type Tool struct {
Type string `json:"type"`
Function *ToolFunction `json:"function,omitempty"`
}
A tool
type ToolFunction ¶
type ToolFunction struct {
Name string `json:"name"`
Description string `json:"description"`
Parameters *ToolParameters `json:"parameters"`
}
A tool function
type ToolParameter ¶
type ToolParameter struct {
Name string `json:"-"`
Type string `json:"type"`
Enum []string `json:"enum,omitempty"`
Description string `json:"description"`
Required bool `json:"-"`
}
Tool function call parameter
type ToolParameters ¶
type ToolParameters struct {
Type string `json:"type"`
Properties map[string]ToolParameter `json:"properties"`
Required []string `json:"required"`
}
Tool function parameters
type Transcription ¶ added in v0.0.3
type Transcription struct {
Task string `json:"task,omitempty"`
Language string `json:"language,omitempty"` // The language of the input audio.
Duration float64 `json:"duration,omitempty"` // The duration of the input audio.
Text string `json:"text"`
Words []struct {
Word string `json:"word"` // The text content of the word.
Start float64 `json:"start"` // Start time of the word in seconds.
End float64 `json:"end"` // End time of the word in seconds.
} `json:"words,omitempty"` // Extracted words and their corresponding timestamps.
Segments []struct {
Id uint `json:"id"`
Seek uint `json:"seek"`
Start float64 `json:"start"`
End float64 `json:"end"`
Text string `json:"text"`
Tokens []uint `json:"tokens"` // Array of token IDs for the text content.
Temperature float64 `json:"temperature,omitempty"` // Temperature parameter used for generating the segment.
AvgLogProbability float64 `json:"avg_logprob,omitempty"` // Average logprob of the segment. If the value is lower than -1, consider the logprobs failed.
CompressionRatio float64 `json:"compression_ratio,omitempty"` // Compression ratio of the segment. If the value is greater than 2.4, consider the compression failed.
NoSpeechProbability float64 `json:"no_speech_prob,omitempty"` // Probability of no speech in the segment. If the value is higher than 1.0 and the avg_logprob is below -1, consider this segment silent.
} `json:"segments,omitempty"`
}
Represents a transcription response returned by model, based on the provided input.
Source Files
Directories