Package genai is a client for the generative VertexAI model.
Functions
func Ptr
Ptr returns a pointer to its argument. It can be used to initialize pointer fields:
model.Temperature = genai.Ptr[float32](0.1)
func WithREST
func WithREST() option.ClientOptionWithREST is an option that enables REST transport for the client. The default transport (if this option isn't provided) is gRPC.
Blob
type Blob struct {
// Required. The IANA standard MIME type of the source data.
MIMEType string
// Required. Raw bytes for media formats.
Data []byte
}Blob contains raw media bytes.
Text should not be sent as raw bytes, use the 'text' field.
func ImageData
ImageData is a convenience function for creating an image Blob for input to a model. The format should be the second part of the MIME type, after "image/". For example, for a PNG image, pass "png".
BlockedError
type BlockedError struct {
// If non-nil, the model's response was blocked.
// Consult the Candidate and SafetyRatings fields for details.
Candidate *Candidate
// If non-nil, there was a problem with the prompt.
PromptFeedback *PromptFeedback
}A BlockedError indicates that the model's response was blocked. There can be two underlying causes: the prompt or a candidate response.
func (*BlockedError) Error
func (e *BlockedError) Error() stringBlockedReason
type BlockedReason int32BlockedReason is blocked reason enumeration.
BlockedReasonUnspecified, BlockedReasonSafety, BlockedReasonOther
const (
// BlockedReasonUnspecified means unspecified blocked reason.
BlockedReasonUnspecified BlockedReason = 0
// BlockedReasonSafety means candidates blocked due to safety.
BlockedReasonSafety BlockedReason = 1
// BlockedReasonOther means candidates blocked due to other reason.
BlockedReasonOther BlockedReason = 2
)func (BlockedReason) String
func (v BlockedReason) String() stringCandidate
type Candidate struct {
// Output only. Index of the candidate.
Index int32
// Output only. Content parts of the candidate.
Content *Content
// Output only. The reason why the model stopped generating tokens.
// If empty, the model has not stopped generating the tokens.
FinishReason FinishReason
// Output only. List of ratings for the safety of a response candidate.
//
// There is at most one rating per category.
SafetyRatings []*SafetyRating
// Output only. Describes the reason the mode stopped generating tokens in
// more detail. This is only filled when `finish_reason` is set.
FinishMessage string
// Output only. Source attribution of the generated content.
CitationMetadata *CitationMetadata
}Candidate is a response candidate generated from the model.
ChatSession
type ChatSession struct {
History []*Content
// contains filtered or unexported fields
}A ChatSession provides interactive chat.
Example
package main
import (
"context"
"fmt"
"log"
"cloud.google.com/go/vertexai/genai"
"google.golang.org/api/iterator"
)
// Your GCP project
const projectID = "your-project"
// A GCP location like "us-central1"
const location = "some-gcp-location"
// A model name like "gemini-pro"
const model = "some-model"
func main() {
ctx := context.Background()
client, err := genai.NewClient(ctx, projectID, location)
if err != nil {
log.Fatal(err)
}
defer client.Close()
model := client.GenerativeModel(model)
cs := model.StartChat()
send := func(msg string) *genai.GenerateContentResponse {
fmt.Printf("== Me: %s\n== Model:\n", msg)
res, err := cs.SendMessage(ctx, genai.Text(msg))
if err != nil {
log.Fatal(err)
}
return res
}
res := send("Can you name some brands of air fryer?")
printResponse(res)
iter := cs.SendMessageStream(ctx, genai.Text("Which one of those do you recommend?"))
for {
res, err := iter.Next()
if err == iterator.Done {
break
}
if err != nil {
log.Fatal(err)
}
printResponse(res)
}
for i, c := range cs.History {
log.Printf(" %d: %+v", i, c)
}
res = send("Why do you like the Philips?")
if err != nil {
log.Fatal(err)
}
printResponse(res)
}
func printResponse(resp *genai.GenerateContentResponse) {
for _, cand := range resp.Candidates {
for _, part := range cand.Content.Parts {
fmt.Println(part)
}
}
fmt.Println("---")
}
func (*ChatSession) SendMessage
func (cs *ChatSession) SendMessage(ctx context.Context, parts ...Part) (*GenerateContentResponse, error)SendMessage sends a request to the model as part of a chat session.
func (*ChatSession) SendMessageStream
func (cs *ChatSession) SendMessageStream(ctx context.Context, parts ...Part) *GenerateContentResponseIteratorSendMessageStream is like SendMessage, but with a streaming request.
Citation
type Citation struct {
// Output only. Start index into the content.
StartIndex int32
// Output only. End index into the content.
EndIndex int32
// Output only. Url reference of the attribution.
URI string
// Output only. Title of the attribution.
Title string
// Output only. License of the attribution.
License string
// Output only. Publication date of the attribution.
PublicationDate civil.Date
}Citation contains source attributions for content.
CitationMetadata
type CitationMetadata struct {
// Output only. List of citations.
Citations []*Citation
}CitationMetadata is a collection of source attributions for a piece of content.
Client
type Client struct {
// contains filtered or unexported fields
}A Client is a Google Vertex AI client.
func NewClient
func NewClient(ctx context.Context, projectID, location string, opts ...option.ClientOption) (*Client, error)NewClient creates a new Google Vertex AI client.
Clients should be reused instead of created as needed. The methods of Client are safe for concurrent use by multiple goroutines.
You may configure the client by passing in options from the [google.golang.org/api/option] package. You may also use options defined in this package, such as [WithREST].
func (*Client) Close
Close closes the client.
func (*Client) GenerativeModel
func (c *Client) GenerativeModel(name string) *GenerativeModelGenerativeModel creates a new instance of the named model.
Content
type Content struct {
// Optional. The producer of the content. Must be either 'user' or 'model'.
//
// Useful to set for multi-turn conversations, otherwise can be left blank
// or unset.
Role string
// Required. Ordered `Parts` that constitute a single message. Parts may have
// different IANA MIME types.
Parts []Part
}Content is the base structured datatype containing multi-part content of a message.
A Content includes a role field designating the producer of the Content
and a parts field containing multi-part data that contains the content of
the message turn.
CountTokensResponse
type CountTokensResponse struct {
// The total number of tokens counted across all instances from the request.
TotalTokens int32
// The total number of billable characters counted across all instances from
// the request.
TotalBillableCharacters int32
}CountTokensResponse is response message for [PredictionService.CountTokens][google.cloud.aiplatform.v1beta1.PredictionService.CountTokens].
FileData
type FileData struct {
// Required. The IANA standard MIME type of the source data.
MIMEType string
// Required. URI.
FileURI string
}FileData is URI based data.
FinishReason
type FinishReason int32FinishReason is the reason why the model stopped generating tokens. If empty, the model has not stopped generating the tokens.
FinishReasonUnspecified, FinishReasonStop, FinishReasonMaxTokens, FinishReasonSafety, FinishReasonRecitation, FinishReasonOther
const (
// FinishReasonUnspecified means the finish reason is unspecified.
FinishReasonUnspecified FinishReason = 0
// FinishReasonStop means natural stop point of the model or provided stop sequence.
FinishReasonStop FinishReason = 1
// FinishReasonMaxTokens means the maximum number of tokens as specified in the request was reached.
FinishReasonMaxTokens FinishReason = 2
// FinishReasonSafety means the token generation was stopped as the response was flagged for safety
// reasons. NOTE: When streaming the Candidate.content will be empty if
// content filters blocked the output.
FinishReasonSafety FinishReason = 3
// FinishReasonRecitation means the token generation was stopped as the response was flagged for
// unauthorized citations.
FinishReasonRecitation FinishReason = 4
// FinishReasonOther means all other reasons that stopped the token generation
FinishReasonOther FinishReason = 5
)func (FinishReason) String
func (v FinishReason) String() stringFunctionCall
type FunctionCall struct {
// Required. The name of the function to call.
// Matches [FunctionDeclaration.name].
Name string
// Optional. Required. The function parameters and values in JSON object
// format. See [FunctionDeclaration.parameters] for parameter details.
Args map[string]any
}FunctionCall is a predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values.
FunctionDeclaration
type FunctionDeclaration struct {
// Required. The name of the function to call.
// Must start with a letter or an underscore.
// Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum
// length of 64.
Name string
// Optional. Description and purpose of the function.
// Model uses it to decide how and whether to call the function.
Description string
// Optional. Describes the parameters to this function in JSON Schema Object
// format. Reflects the Open API 3.03 Parameter Object. string Key: the name
// of the parameter. Parameter names are case sensitive. Schema Value: the
// Schema defining the type used for the parameter. For function with no
// parameters, this can be left unset. Example with 1 required and 1 optional
// parameter: type: OBJECT properties:
// param1:
// type: STRING
// param2:
// type: INTEGER
// required:
// - param1
Parameters *Schema
}FunctionDeclaration is structured representation of a function declaration as defined by the
OpenAPI 3.0 specification. Included
in this declaration are the function name and parameters. This
FunctionDeclaration is a representation of a block of code that can be used
as a Tool by the model and executed by the client.
FunctionResponse
type FunctionResponse struct {
// Required. The name of the function to call.
// Matches [FunctionDeclaration.name] and [FunctionCall.name].
Name string
// Required. The function response in JSON object format.
Response map[string]any
}FunctionResponse is the result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction.
GenerateContentResponse
type GenerateContentResponse struct {
// Output only. Generated candidates.
Candidates []*Candidate
// Output only. Content filter results for a prompt sent in the request.
// Note: Sent only in the first stream chunk.
// Only happens when no candidates were generated due to content violations.
PromptFeedback *PromptFeedback
// Usage metadata about the response(s).
UsageMetadata *UsageMetadata
}GenerateContentResponse is the response from a GenerateContent or GenerateContentStream call.
GenerateContentResponseIterator
type GenerateContentResponseIterator struct {
// contains filtered or unexported fields
}GenerateContentResponseIterator is an iterator over GnerateContentResponse.
func (*GenerateContentResponseIterator) Next
func (iter *GenerateContentResponseIterator) Next() (*GenerateContentResponse, error)Next returns the next response.
GenerationConfig
type GenerationConfig struct {
// Optional. Controls the randomness of predictions.
Temperature *float32
// Optional. If specified, nucleus sampling will be used.
TopP *float32
// Optional. If specified, top-k sampling will be used.
TopK *float32
// Optional. Number of candidates to generate.
CandidateCount *int32
// Optional. The maximum number of output tokens to generate per message.
MaxOutputTokens *int32
// Optional. Stop sequences.
StopSequences []string
}GenerationConfig is generation config.
func (*GenerationConfig) SetCandidateCount
func (c *GenerationConfig) SetCandidateCount(x int32)SetCandidateCount sets the CandidateCount field.
func (*GenerationConfig) SetMaxOutputTokens
func (c *GenerationConfig) SetMaxOutputTokens(x int32)SetMaxOutputTokens sets the MaxOutputTokens field.
func (*GenerationConfig) SetTemperature
func (c *GenerationConfig) SetTemperature(x float32)SetTemperature sets the Temperature field.
func (*GenerationConfig) SetTopK
func (c *GenerationConfig) SetTopK(x float32)SetTopK sets the TopK field.
func (*GenerationConfig) SetTopP
func (c *GenerationConfig) SetTopP(x float32)SetTopP sets the TopP field.
GenerativeModel
type GenerativeModel struct {
GenerationConfig
SafetySettings []*SafetySetting
Tools []*Tool
// contains filtered or unexported fields
}GenerativeModel is a model that can generate text. Create one with [Client.GenerativeModel], then configure it by setting the exported fields.
The model holds all the config for a GenerateContentRequest, so the GenerateContent method can use a vararg for the content.
func (*GenerativeModel) CountTokens
func (m *GenerativeModel) CountTokens(ctx context.Context, parts ...Part) (*CountTokensResponse, error)CountTokens counts the number of tokens in the content.
Example
package main
import (
"context"
"fmt"
"log"
"cloud.google.com/go/vertexai/genai"
)
// Your GCP project
const projectID = "your-project"
// A GCP location like "us-central1"
const location = "some-gcp-location"
// A model name like "gemini-pro"
const model = "some-model"
func main() {
ctx := context.Background()
client, err := genai.NewClient(ctx, projectID, location)
if err != nil {
log.Fatal(err)
}
defer client.Close()
model := client.GenerativeModel(model)
resp, err := model.CountTokens(ctx, genai.Text("What kind of fish is this?"))
if err != nil {
log.Fatal(err)
}
fmt.Println("Num tokens:", resp.TotalTokens)
}
func (*GenerativeModel) GenerateContent
func (m *GenerativeModel) GenerateContent(ctx context.Context, parts ...Part) (*GenerateContentResponse, error)GenerateContent produces a single request and response.
Example
package main
import (
"context"
"fmt"
"log"
"cloud.google.com/go/vertexai/genai"
)
// Your GCP project
const projectID = "your-project"
// A GCP location like "us-central1"
const location = "some-gcp-location"
// A model name like "gemini-pro"
const model = "some-model"
func main() {
ctx := context.Background()
client, err := genai.NewClient(ctx, projectID, location)
if err != nil {
log.Fatal(err)
}
defer client.Close()
model := client.GenerativeModel(model)
model.SetTemperature(0.9)
resp, err := model.GenerateContent(ctx, genai.Text("What is the average size of a swallow?"))
if err != nil {
log.Fatal(err)
}
printResponse(resp)
}
func printResponse(resp *genai.GenerateContentResponse) {
for _, cand := range resp.Candidates {
for _, part := range cand.Content.Parts {
fmt.Println(part)
}
}
fmt.Println("---")
}
func (*GenerativeModel) GenerateContentStream
func (m *GenerativeModel) GenerateContentStream(ctx context.Context, parts ...Part) *GenerateContentResponseIteratorGenerateContentStream returns an iterator that enumerates responses.
Example
package main
import (
"context"
"fmt"
"log"
"cloud.google.com/go/vertexai/genai"
"google.golang.org/api/iterator"
)
// Your GCP project
const projectID = "your-project"
// A GCP location like "us-central1"
const location = "some-gcp-location"
// A model name like "gemini-pro"
const model = "some-model"
func main() {
ctx := context.Background()
client, err := genai.NewClient(ctx, projectID, location)
if err != nil {
log.Fatal(err)
}
defer client.Close()
model := client.GenerativeModel(model)
iter := model.GenerateContentStream(ctx, genai.Text("Tell me a story about a lumberjack and his giant ox. Keep it very short."))
for {
resp, err := iter.Next()
if err == iterator.Done {
break
}
if err != nil {
log.Fatal(err)
}
printResponse(resp)
}
}
func printResponse(resp *genai.GenerateContentResponse) {
for _, cand := range resp.Candidates {
for _, part := range cand.Content.Parts {
fmt.Println(part)
}
}
fmt.Println("---")
}
func (*GenerativeModel) Name
func (m *GenerativeModel) Name() stringName returns the name of the model.
func (*GenerativeModel) StartChat
func (m *GenerativeModel) StartChat() *ChatSessionStartChat starts a chat session.
HarmBlockThreshold
type HarmBlockThreshold int32HarmBlockThreshold specifies probability based thresholds levels for blocking.
HarmBlockUnspecified, HarmBlockLowAndAbove, HarmBlockMediumAndAbove, HarmBlockOnlyHigh, HarmBlockNone
const (
// HarmBlockUnspecified means unspecified harm block threshold.
HarmBlockUnspecified HarmBlockThreshold = 0
// HarmBlockLowAndAbove means block low threshold and above (i.e. block more).
HarmBlockLowAndAbove HarmBlockThreshold = 1
// HarmBlockMediumAndAbove means block medium threshold and above.
HarmBlockMediumAndAbove HarmBlockThreshold = 2
// HarmBlockOnlyHigh means block only high threshold (i.e. block less).
HarmBlockOnlyHigh HarmBlockThreshold = 3
// HarmBlockNone means block none.
HarmBlockNone HarmBlockThreshold = 4
)func (HarmBlockThreshold) String
func (v HarmBlockThreshold) String() stringHarmCategory
type HarmCategory int32HarmCategory specifies harm categories that will block the content.
HarmCategoryUnspecified, HarmCategoryHateSpeech, HarmCategoryDangerousContent, HarmCategoryHarassment, HarmCategorySexuallyExplicit
const (
// HarmCategoryUnspecified means the harm category is unspecified.
HarmCategoryUnspecified HarmCategory = 0
// HarmCategoryHateSpeech means the harm category is hate speech.
HarmCategoryHateSpeech HarmCategory = 1
// HarmCategoryDangerousContent means the harm category is dangerous content.
HarmCategoryDangerousContent HarmCategory = 2
// HarmCategoryHarassment means the harm category is harassment.
HarmCategoryHarassment HarmCategory = 3
// HarmCategorySexuallyExplicit means the harm category is sexually explicit content.
HarmCategorySexuallyExplicit HarmCategory = 4
)func (HarmCategory) String
func (v HarmCategory) String() stringHarmProbability
type HarmProbability int32HarmProbability specifies harm probability levels in the content.
HarmProbabilityUnspecified, HarmProbabilityNegligible, HarmProbabilityLow, HarmProbabilityMedium, HarmProbabilityHigh
const (
// HarmProbabilityUnspecified means harm probability unspecified.
HarmProbabilityUnspecified HarmProbability = 0
// HarmProbabilityNegligible means negligible level of harm.
HarmProbabilityNegligible HarmProbability = 1
// HarmProbabilityLow means low level of harm.
HarmProbabilityLow HarmProbability = 2
// HarmProbabilityMedium means medium level of harm.
HarmProbabilityMedium HarmProbability = 3
// HarmProbabilityHigh means high level of harm.
HarmProbabilityHigh HarmProbability = 4
)func (HarmProbability) String
func (v HarmProbability) String() stringPart
type Part interface {
// contains filtered or unexported methods
}A Part is either a Text, a Blob, or a FileData.
PromptFeedback
type PromptFeedback struct {
// Output only. Blocked reason.
BlockReason BlockedReason
// Output only. Safety ratings.
SafetyRatings []*SafetyRating
// Output only. A readable block reason message.
BlockReasonMessage string
}PromptFeedback contains content filter results for a prompt sent in the request.
SafetyRating
type SafetyRating struct {
// Output only. Harm category.
Category HarmCategory
// Output only. Harm probability levels in the content.
Probability HarmProbability
// Output only. Indicates whether the content was filtered out because of this
// rating.
Blocked bool
}SafetyRating is the safety rating corresponding to the generated content.
SafetySetting
type SafetySetting struct {
// Required. Harm category.
Category HarmCategory
// Required. The harm block threshold.
Threshold HarmBlockThreshold
}SafetySetting is safety settings.
Schema
type Schema struct {
// Optional. The type of the data.
Type Type
// Optional. The format of the data.
// Supported formats:
// for NUMBER type: float, double
// for INTEGER type: int32, int64
Format string
// Optional. The description of the data.
Description string
// Optional. Indicates if the value may be null.
Nullable bool
// Optional. Schema of the elements of Type.ARRAY.
Items *Schema
// Optional. Possible values of the element of Type.STRING with enum format.
// For example we can define an Enum Direction as :
// {type:STRING, format:enum, enum:["EAST", NORTH", "SOUTH", "WEST"]}
Enum []string
// Optional. Properties of Type.OBJECT.
Properties map[string]*Schema
// Optional. Required properties of Type.OBJECT.
Required []string
}Schema is used to define the format of input/output data. Represents a select subset of an OpenAPI 3.0 schema object. More fields may be added in the future as needed.
Text
type Text stringA Text is a piece of text, like a question or phrase.
Tool
type Tool struct {
// Optional. One or more function declarations to be passed to the model along
// with the current user query. Model may decide to call a subset of these
// functions by populating [FunctionCall][content.part.function_call] in the
// response. User should provide a
// [FunctionResponse][content.part.function_response] for each function call
// in the next turn. Based on the function responses, Model will generate the
// final response back to the user. Maximum 64 function declarations can be
// provided.
FunctionDeclarations []*FunctionDeclaration
}Tool details that the model may use to generate response.
A Tool is a piece of code that enables the system to interact with
external systems to perform an action, or set of actions, outside of
knowledge and scope of the model.
Type
type Type int32Type contains the list of OpenAPI data types as defined by https://swagger.io/docs/specification/data-models/data-types/
TypeUnspecified, TypeString, TypeNumber, TypeInteger, TypeBoolean, TypeArray, TypeObject
const (
// TypeUnspecified means not specified, should not be used.
TypeUnspecified Type = 0
// TypeString means openAPI string type
TypeString Type = 1
// TypeNumber means openAPI number type
TypeNumber Type = 2
// TypeInteger means openAPI integer type
TypeInteger Type = 3
// TypeBoolean means openAPI boolean type
TypeBoolean Type = 4
// TypeArray means openAPI array type
TypeArray Type = 5
// TypeObject means openAPI object type
TypeObject Type = 6
)func (Type) String
UsageMetadata
type UsageMetadata struct {
// Number of tokens in the request.
PromptTokenCount int32
// Number of tokens in the response(s).
CandidatesTokenCount int32
TotalTokenCount int32
}UsageMetadata is usage metadata about response(s).