gpt

package module
v0.1.0 Latest Latest
Warning

This package is not in the latest version of its module.

 Go to latest Published: Apr 18, 2023 License: Apache-2.0 Imports: 8 Imported by: 3

README

GPT-Go: OpenAI ChatGPT/GPT-4/GPT-3 SDK Go Client to Interact with the GPT-4/GPT-3 APIs.


English | 中文

GitHub license Go PkgGoDev Go Report Card codecov

OpenAI Docs API Reference: https://platform.openai.com/docs/api-reference/introduction

Note: Already support GPT-4 API, please use Chat Completions API.

Quick Start

# clone the project
git clone https://github.com/hanyuancheung/gpt-go.git

# go to the project directory
cd gpt-go

# set API_KEY as environment variable
export API_KEY={YOUR_API_KEY} chatgpt

# go build example binary
make chatgpt-example

# run example
./chatgpt

Snapshot

How To Get API_KEY

https://platform.openai.com/account/api-keys

Documentation

Check out the go docs for more detailed documentation on the types and methods provided: https://pkg.go.dev/github.com/hanyuancheung/gpt-go

Support

  • List Engines API
  • Get Engine API
  • Completion API (this is the main gpt-3 API)
  • Streaming support for the Completion API
  • Document Search API
  • Image generation API
  • Overriding default url, user-agent, timeout, and other options

Usage Examples

ChatGPT streaming completion 
func main() {
	client := gpt.NewClient("API_KEY")
	err := client.ChatCompletionStream(context.Background(), &gpt.ChatCompletionRequest{
		Model: gpt.GPT3Dot5Turbo,
		Messages: []gpt.ChatCompletionRequestMessage{
			{
				Role:    "user",
				Content: "Hello!",
			},
		},
	}, func(response *gpt.ChatCompletionStreamResponse) {
		fmt.Print(response.Choices[0].Delta.Content)
	})
	if err != nil {
		fmt.Printf("ChatCompletionStream error: %v\n", err)
		return
	}
}
GPT-3 completion 
func main() {
	client := gpt.NewClient("API_KEY")
	rsp, err := client.CompletionWithEngine(context.Background(), &gpt.CompletionRequest{
		Model:  gpt.TextDavinci003Engine,
		Prompt: []string{"Hello!"},
	})
	if err != nil {
		fmt.Printf("ChatCompletionStream error: %v\n", err)
		return
	}
	fmt.Print(rsp.Choices[0].Text)
}
DALL-E 2 image generation 
func main() {
	client := gpt.NewClient("API_KEY")
	rsp, err := client.Image(context.Background(), &gpt.ImageRequest{
		Prompt: "Chicken",
	})
	if err != nil {
		fmt.Printf("ChatCompletionStream error: %v\n", err)
		return
	}
	fmt.Print(rsp.Data[0].URL)
}

Contributor

Contribute

Please open up an issue on GitHub before you put a lot of efforts on pull request. The code submitting to PR must be filtered with gofmt.

Star History

Star History Chart

License

This package is licensed under MIT license. See LICENSE for details.

Show your support

Give a ⭐️ if this project helped you!

Documentation

Overview

Package gpt provides a client for the OpenAI GPT-3 API

Package gpt provides a client for the OpenAI GPT-3 API

Package gpt provides a client for the OpenAI GPT-3 API

Package gpt provides a client for the OpenAI GPT-3 API

Index

Constants

View Source 
const (
	TextAda001Engine     = "text-ada-001"     // TextAda001Engine Text Ada 001
	TextBabbage001Engine = "text-babbage-001" // TextBabbage001Engine Text Babbage 001
	TextCurie001Engine   = "text-curie-001"   // TextCurie001Engine Text Curie 001
	TextDavinci001Engine = "text-davinci-001" // TextDavinci001Engine Text Davinci 001
	TextDavinci002Engine = "text-davinci-002" // TextDavinci002Engine Text Davinci 002
	TextDavinci003Engine = "text-davinci-003" // TextDavinci003Engine Text Davinci 003
	AdaEngine            = "ada"              // AdaEngine Ada
	BabbageEngine        = "babbage"          // BabbageEngine Babbage
	CurieEngine          = "curie"            // CurieEngine Curie
	DavinciEngine        = "davinci"          // DavinciEngine Davinci
	DefaultEngine        = DavinciEngine      // DefaultEngine Default Engine
)

Define GPT-3 Engine Types

View Source 
const (
	GPT4                      = "gpt-4"                         // GPT4 GPT-4
	GPT3Dot5Turbo             = "gpt-3.5-turbo"                 // GPT3Dot5Turbo GPT-3.5 Turbo
	GPT3Dot5Turbo0301         = "gpt-3.5-turbo-0301"            // GPT3Dot5Turbo0301 GPT-3.5 Turbo 0301
	TextSimilarityAda001      = "text-similarity-ada-001"       // TextSimilarityAda001 Text Similarity Ada 001
	TextSimilarityBabbage001  = "text-similarity-babbage-001"   // TextSimilarityBabbage001 Text Similarity Babbage 001
	TextSimilarityCurie001    = "text-similarity-curie-001"     // TextSimilarityCurie001 Text Similarity Curie 001
	TextSimilarityDavinci001  = "text-similarity-davinci-001"   // TextSimilarityDavinci001 Text Similarity Davinci 001
	TextSearchAdaDoc001       = "text-search-ada-doc-001"       // TextSearchAdaDoc001 Text Search Ada Doc 001
	TextSearchAdaQuery001     = "text-search-ada-query-001"     // TextSearchAdaQuery001 Text Search Ada Query 001
	TextSearchBabbageDoc001   = "text-search-babbage-doc-001"   // TextSearchBabbageDoc001 Text Search Babbage Doc 001
	TextSearchBabbageQuery001 = "text-search-babbage-query-001" // TextSearchBabbageQuery001 Text Search Babbage Query 001
	TextSearchCurieDoc001     = "text-search-curie-doc-001"     // TextSearchCurieDoc001 Text Search Curie Doc 001
	TextSearchCurieQuery001   = "text-search-curie-query-001"   // TextSearchCurieQuery001 Text Search Curie Query 001
	TextSearchDavinciDoc001   = "text-search-davinci-doc-001"   // TextSearchDavinciDoc001 Text Search Davinci Doc 001
	TextSearchDavinciQuery001 = "text-search-davinci-query-001" // TextSearchDavinciQuery001 Text Search Davinci Query 001
	CodeSearchAdaCode001      = "code-search-ada-code-001"      // CodeSearchAdaCode001 Code Search Ada Code 001
	CodeSearchAdaText001      = "code-search-ada-text-001"      // CodeSearchAdaText001 Code Search Ada Text 001
	CodeSearchBabbageCode001  = "code-search-babbage-code-001"  // CodeSearchBabbageCode001 Code Search Babbage Code 001
	CodeSearchBabbageText001  = "code-search-babbage-text-001"  // CodeSearchBabbageText001 Code Search Babbage Text 001
	TextEmbeddingAda002       = "text-embedding-ada-002"        // TextEmbeddingAda002 Text Embedding Ada 002
)
View Source 
const (
	CreateImageSize256x256   = "256x256"   // CreateImageSize256x256 256x256
	CreateImageSize512x512   = "512x512"   // CreateImageSize512x512 512x512
	CreateImageSize1024x1024 = "1024x1024" // CreateImageSize1024x1024 1024x1024

	CreateImageResponseFormatURL     = "url"      // CreateImageResponseFormatURL URL
	CreateImageResponseFormatB64JSON = "b64_json" // CreateImageResponseFormatB64JSON B64 JSON
)

Image sizes defined by the OpenAI API.

Variables

This section is empty.

Functions

func Float32Ptr 

func Float32Ptr(f float32) *float32

Float32Ptr converts a float32 to a *float32 as a convenience

func IntPtr 

func IntPtr(i int) *int

IntPtr converts an integer to an *int as a convenience

Types

type APIError 

type APIError struct {
	StatusCode int    `json:"status_code"`
	Message    string `json:"message"`
	Type       string `json:"type"`
}

APIError represents an error that occurred on an API

func (APIError) Error 

func (e APIError) Error() string

Error returns a string representation of the error

type APIErrorResponse 

type APIErrorResponse struct {
	Error APIError `json:"error"`
}

APIErrorResponse is the full error response that has been returned by an API.

type ChatCompletionRequest 

type ChatCompletionRequest struct {
	// Model is the name of the model to use. If not specified, will default to gpt-3.5-turbo.
	Model string `json:"model"`
	// Messages is a list of messages to use as the context for the chat completion.
	Messages []ChatCompletionRequestMessage `json:"messages"`
	// Temperature is sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random,
	// while lower values like 0.2 will make it more focused and deterministic
	Temperature float32 `json:"temperature,omitempty"`
	// TopP is an alternative to sampling with temperature, called nucleus sampling, where the model considers the results of
	// the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
	TopP float32 `json:"top_p,omitempty"`
	// N is number of responses to generate
	N int `json:"n,omitempty"`
	// Stream is whether to stream responses back as they are generated
	Stream bool `json:"stream,omitempty"`
	// Stop is up to 4 sequences where the API will stop generating further tokens.
	Stop []string `json:"stop,omitempty"`
	// MaxTokens is the maximum number of tokens to return.
	MaxTokens int `json:"max_tokens,omitempty"`
	// PresencePenalty (-2, 2) penalize tokens that haven't appeared yet in the history.
	PresencePenalty float32 `json:"presence_penalty,omitempty"`
	// FrequencyPenalty (-2, 2) penalize tokens that appear too frequently in the history.
	FrequencyPenalty float32 `json:"frequency_penalty,omitempty"`
	// LogitBias modify the probability of specific tokens appearing in the completion.
	LogitBias map[string]float32 `json:"logit_bias,omitempty"`
	// User can be used to identify an end-user
	User string `json:"user,omitempty"`
}

ChatCompletionRequest is a request for the chat completion API

type ChatCompletionRequestMessage 

type ChatCompletionRequestMessage struct {
	// Role is the role is the role of the message. Can be "system", "user", or "assistant"
	Role string `json:"role"`
	// Content is the content of the message
	Content string `json:"content"`
}

ChatCompletionRequestMessage is a message to use as the context for the chat completion API

type ChatCompletionResponse 

type ChatCompletionResponse struct {
	ID      string                         `json:"id"`
	Object  string                         `json:"object"`
	Created int                            `json:"created"`
	Model   string                         `json:"model"`
	Choices []ChatCompletionResponseChoice `json:"choices"`
	Usage   ChatCompletionsResponseUsage   `json:"usage"`
}

ChatCompletionResponse is the full response from a request to the Chat Completions API

type ChatCompletionResponseChoice 

type ChatCompletionResponseChoice struct {
	Index        int                           `json:"index"`
	FinishReason string                        `json:"finish_reason"`
	Message      ChatCompletionResponseMessage `json:"message"`
}

ChatCompletionResponseChoice is one of the choices returned in the response to the Chat Completions API

type ChatCompletionResponseMessage 

type ChatCompletionResponseMessage struct {
	Role    string `json:"role"`
	Content string `json:"content"`
}

ChatCompletionResponseMessage is a message returned in the response to the Chat Completions API

type ChatCompletionStreamResponse 

type ChatCompletionStreamResponse struct {
	ID      string                               `json:"id"`
	Object  string                               `json:"object"`
	Created int                                  `json:"created"`
	Model   string                               `json:"model"`
	Choices []ChatCompletionStreamResponseChoice `json:"choices"`
	Usage   ChatCompletionsResponseUsage         `json:"usage"`
}

type ChatCompletionStreamResponseChoice 

type ChatCompletionStreamResponseChoice struct {
	Index        int                           `json:"index"`
	FinishReason string                        `json:"finish_reason"`
	Delta        ChatCompletionResponseMessage `json:"delta"`
}

ChatCompletionStreamResponseChoice is one of the choices returned in the response to the Chat Completions API

type ChatCompletionsResponseUsage 

type ChatCompletionsResponseUsage struct {
	PromptTokens     int `json:"prompt_tokens"`
	CompletionTokens int `json:"completion_tokens"`
	TotalTokens      int `json:"total_tokens"`
}

ChatCompletionsResponseUsage is the object that returns how many tokens the completion's request used

type Client 

type Client interface {
	// Engines lists the currently available engines, and provides basic information about each
	// option such as the owner and availability.
	Engines(ctx context.Context) (*EnginesResponse, error)

	// Engine retrieves an engine instance, providing basic information about the engine such
	// as the owner and availability.
	Engine(ctx context.Context, engine string) (*EngineObject, error)

	// ChatCompletion creates a completion with the Chat completion endpoint which
	// is what powers the ChatGPT experience.
	ChatCompletion(ctx context.Context, request *ChatCompletionRequest) (*ChatCompletionResponse, error)

	// ChatCompletionStream creates a completion with the Chat completion endpoint which
	// is what powers the ChatGPT experience.
	ChatCompletionStream(ctx context.Context, request *ChatCompletionRequest, onData func(*ChatCompletionStreamResponse)) error

	// Completion creates a completion with the default engine. This is the main endpoint of the API
	// which auto-completes based on the given prompt.
	Completion(ctx context.Context, request *CompletionRequest) (*CompletionResponse, error)

	// CompletionStream creates a completion with the default engine and streams the results through
	// multiple calls to onData.
	CompletionStream(ctx context.Context, request *CompletionRequest, onData func(*CompletionResponse)) error

	// CompletionWithEngine is the same as Completion except allows overriding the default engine on the client
	CompletionWithEngine(ctx context.Context, request *CompletionRequest) (*CompletionResponse, error)

	// CompletionStreamWithEngine is the same as CompletionStream allows overriding the default engine on the client
	CompletionStreamWithEngine(ctx context.Context, request *CompletionRequest, onData func(*CompletionResponse)) error

	// Edits is given a prompt and an instruction, the model will return an edited version of the prompt.
	Edits(ctx context.Context, request *EditsRequest) (*EditsResponse, error)

	// Search performs a semantic search over a list of documents with the default engine.
	Search(ctx context.Context, request *SearchRequest) (*SearchResponse, error)

	// SearchWithEngine performs a semantic search over a list of documents with the specified engine.
	SearchWithEngine(ctx context.Context, engine string, request *SearchRequest) (*SearchResponse, error)

	// Embeddings Returns an embedding using the provided request.
	Embeddings(ctx context.Context, request *EmbeddingsRequest) (*EmbeddingsResponse, error)

	// Image returns an image using the provided request.
	Image(ctx context.Context, request *ImageRequest) (*ImageResponse, error)
}

Client is an API client to communicate with the OpenAI gpt-3 APIs

func NewClient 

func NewClient(apiKey string, options ...ClientOption) Client

NewClient returns a new OpenAI GPT-3 API client. An APIKey is required to use the client

type ClientOption 

type ClientOption func(*client) *client

ClientOption are options that can be passed when creating a new client

func WithBaseURL 

func WithBaseURL(baseURL string) ClientOption

WithBaseURL is a client option that allows you to override the default base url of the client. The default base url is "https://api.openai.com/v1"

func WithDefaultEngine 

func WithDefaultEngine(engine string) ClientOption

WithDefaultEngine is a client option that allows you to override the default engine of the client

func WithHTTPClient 

func WithHTTPClient(httpClient *http.Client) ClientOption

WithHTTPClient allows you to override the internal http.Client used

func WithOrg 

func WithOrg(id string) ClientOption

WithOrg is a client option that allows you to override the organization ID

func WithTimeout 

func WithTimeout(timeout time.Duration) ClientOption

WithTimeout is a client option that allows you to override the default timeout duration of requests for the client. The default is 30 seconds. If you are overriding the http client as well, just include the timeout there.

func WithUserAgent 

func WithUserAgent(userAgent string) ClientOption

WithUserAgent is a client option that allows you to override the default user agent of the client

type CompletionRequest 

type CompletionRequest struct {
	Model string `json:"model"`
	// Prompt sets a list of string prompts to use.
	Prompt []string `json:"prompt,omitempty"`
	// Suffix comes after a completion of inserted text.
	Suffix string `json:"suffix,omitempty"`
	// MaxTokens sets how many tokens to complete up to. Max of 512
	MaxTokens int `json:"max_tokens,omitempty"`
	// Temperature sets sampling temperature to use
	Temperature float32 `json:"temperature,omitempty"`
	// TopP sets alternative to temperature for nucleus sampling
	TopP *float32 `json:"top_p,omitempty"`
	// N sets how many choice to create for each prompt
	N *int `json:"n"`
	// Stream sets whether to stream back results or not. Don't set this value in the request yourself
	// as it will be overridden depending on if you use CompletionStream or Completion methods.
	Stream bool `json:"stream,omitempty"`
	// LogProbs sets include the probabilities of most likely tokens
	LogProbs *int `json:"logprobs"`
	// Echo sets back the prompt in addition to the completion
	Echo bool `json:"echo"`
	// Stop sets up to 4 sequences where the API will stop generating tokens. Response will not contain the stop sequence.
	Stop []string `json:"stop,omitempty"`
	// PresencePenalty sets number between 0 and 1 that penalizes tokens that have already appeared in the text so far.
	PresencePenalty float32 `json:"presence_penalty"`
	// FrequencyPenalty number between 0 and 1 that penalizes tokens on existing frequency in the text so far.
	FrequencyPenalty float32 `json:"frequency_penalty"`
	// BestOf sets how many of the n best completions to return. Defaults to 1.
	BestOf int `json:"best_of,omitempty"`
	// LogitBias sets modify the probability of specific tokens appearing in the completion.
	LogitBias map[string]float32 `json:"logit_bias,omitempty"`
	// User sets an end-user identifier. Can be used to associate completions generated by a specific user.
	User string `json:"user,omitempty"`
}

CompletionRequest is a request for the completions API

type CompletionResponse 

type CompletionResponse struct {
	ID      string                     `json:"id"`
	Object  string                     `json:"object"`
	Created int                        `json:"created"`
	Model   string                     `json:"model"`
	Choices []CompletionResponseChoice `json:"choices"`
	Usage   CompletionResponseUsage    `json:"usage"`
}

CompletionResponse is the full response from a request to the completions API

type CompletionResponseChoice 

type CompletionResponseChoice struct {
	Text         string        `json:"text"`
	Index        int           `json:"index"`
	LogProbs     LogProbResult `json:"logprobs"`
	FinishReason string        `json:"finish_reason"`
}

CompletionResponseChoice is one of the choices returned in the response to the Completions API

type CompletionResponseUsage 

type CompletionResponseUsage struct {
	PromptTokens     int `json:"prompt_tokens"`
	CompletionTokens int `json:"completion_tokens"`
	TotalTokens      int `json:"total_tokens"`
}

CompletionResponseUsage is the object that returns how many tokens the completion's request used

type EditsRequest 

type EditsRequest struct {
	// Model is ID of the model to use. You can use the List models API to see all of your available models,
	// or see our Model overview for descriptions of them.
	Model string `json:"model"`
	// Input is the input text to use as a starting point for the edit.
	Input string `json:"input,omitempty"`
	// Instruction is the instruction that tells the model how to edit the prompt.
	Instruction string `json:"instruction"`
	// N is how many edits to generate for the input and instruction. Defaults to 1
	N *int `json:"n,omitempty"`
	// Temperature is sampling temperature to use
	Temperature *float32 `json:"temperature,omitempty"`
	// TopP is alternative to temperature for nucleus sampling
	TopP *float32 `json:"top_p,omitempty"`
}

EditsRequest is a request for the edits API

type EditsResponse 

type EditsResponse struct {
	Object  string                `json:"object"`
	Created int                   `json:"created"`
	Choices []EditsResponseChoice `json:"choices"`
	Usage   EditsResponseUsage    `json:"usage"`
}

EditsResponse is the full response from a request to the edits API

type EditsResponseChoice 

type EditsResponseChoice struct {
	Text  string `json:"text"`
	Index int    `json:"index"`
}

EditsResponseChoice is one of the choices returned in the response to the Edits API

type EditsResponseUsage 

type EditsResponseUsage struct {
	PromptTokens     int `json:"prompt_tokens"`
	CompletionTokens int `json:"completion_tokens"`
	TotalTokens      int `json:"total_tokens"`
}

EditsResponseUsage is a structure used in the response from a request to the edits API

type EmbeddingsRequest 

type EmbeddingsRequest struct {
	// Input text to get embeddings for, encoded as a string or array of tokens. To get embeddings
	// for multiple inputs in a single request, pass an array of strings or array of token arrays.
	// Each input must not exceed 2048 tokens in length.
	Input []string `json:"input"`
	// Model is ID of the model to use
	Model string `json:"model"`
	// User is the request user is an optional parameter meant to be used to trace abusive requests
	// back to the originating user. OpenAI states:
	// "The [user] IDs should be a string that uniquely identifies each user. We recommend hashing
	// their username or email address, in order to avoid sending us any identifying information.
	// If you offer a preview of your product to non-logged in users, you can send a session ID
	// instead."
	User string `json:"user,omitempty"`
}

EmbeddingsRequest is a request for the Embeddings API

type EmbeddingsResponse 

type EmbeddingsResponse struct {
	Object string             `json:"object"`
	Data   []EmbeddingsResult `json:"data"`
	Usage  EmbeddingsUsage    `json:"usage"`
}

EmbeddingsResponse is the response from a create embeddings request. See: https://beta.openai.com/docs/api-reference/embeddings/create

type EmbeddingsResult 

type EmbeddingsResult struct {
	// The type of object returned (e.g., "list", "object")
	Object string `json:"object"`
	// The embedding data for the input
	Embedding []float64 `json:"embedding"`
	Index     int       `json:"index"`
}

EmbeddingsResult The inner result of a create embeddings request, containing the embeddings for a single input.

type EmbeddingsUsage 

type EmbeddingsUsage struct {
	// The number of tokens used by the prompt
	PromptTokens int `json:"prompt_tokens"`
	// The total tokens used
	TotalTokens int `json:"total_tokens"`
}

EmbeddingsUsage The usage stats for an embeddings response

type EngineObject 

type EngineObject struct {
	ID     string `json:"id"`
	Object string `json:"object"`
	Owner  string `json:"owner"`
	Ready  bool   `json:"ready"`
}

EngineObject contained in an engine repose

type EnginesResponse 

type EnginesResponse struct {
	Data   []EngineObject `json:"data"`
	Object string         `json:"object"`
}

EnginesResponse is returned from the Engines API

type ImageRequest added in v0.0.2 

type ImageRequest struct {
	Prompt         string `json:"prompt,omitempty"`
	N              int    `json:"n,omitempty"`
	Size           string `json:"size,omitempty"`
	ResponseFormat string `json:"response_format,omitempty"`
	User           string `json:"user,omitempty"`
}

ImageRequest represents the request structure for the image API.

type ImageResponse added in v0.0.2 

type ImageResponse struct {
	Created int64                    `json:"created,omitempty"`
	Data    []ImageResponseDataInner `json:"data,omitempty"`
}

ImageResponse represents a response structure for image API.

type ImageResponseDataInner added in v0.0.2 

type ImageResponseDataInner struct {
	URL     string `json:"url,omitempty"`
	B64JSON string `json:"b64_json,omitempty"`
}

ImageResponseDataInner represents a response data structure for image API.

type LogProbResult 

type LogProbResult struct {
	Tokens        []string             `json:"tokens"`
	TokenLogProbs []float32            `json:"token_logprobs"`
	TopLogProbs   []map[string]float32 `json:"top_logprobs"`
	TextOffset    []int                `json:"text_offset"`
}

LogProbResult represents logprob result of Choice

type Option 

type Option interface {
	// contains filtered or unexported methods
}

Option sets gpt-3 Client option values.

type SearchData 

type SearchData struct {
	Document int     `json:"document"`
	Object   string  `json:"object"`
	Score    float64 `json:"score"`
}

SearchData is a single search result from the document search API

type SearchRequest 

type SearchRequest struct {
	Documents []string `json:"documents"`
	Query     string   `json:"query"`
}

SearchRequest is a request for the document search API

type SearchResponse 

type SearchResponse struct {
	Data   []SearchData `json:"data"`
	Object string       `json:"object"`
}

SearchResponse is the full response from a request to the document search API

Source Files

View all Source files

Directories

Path Synopsis
example module

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL
go.dev uses cookies from Google to deliver and enhance the quality of its services and to analyze traffic. Learn more.