Livepeer AI Golang Client Library

Welcome to the Livepeer AI Golang client Library! This library offers a seamless integration with the Livepeer AI API, enabling you to easily incorporate powerful AI capabilities into your Golang applications, whether they run in the browser or on the server side.

Retries

Some of the endpoints in this SDK support retries. If you use the SDK without any configuration, it will fall back to the default retry strategy provided by the API. However, the default retry strategy can be overridden on a per-operation basis, or across the entire SDK.

To change the default retry strategy for a single API call, simply provide a retry.Config object to the call by using the WithRetries option:

package main

import (
	"context"
	livepeeraigo "github.com/livepeer/livepeer-ai-go"
	"github.com/livepeer/livepeer-ai-go/models/components"
	"github.com/livepeer/livepeer-ai-go/retry"
	"log"
	"models/operations"
)

func main() {
	ctx := context.Background()

	s := livepeeraigo.New(
		livepeeraigo.WithSecurity("<YOUR_BEARER_TOKEN_HERE>"),
	)

	res, err := s.Generate.TextToImage(ctx, components.TextToImageParams{
		Prompt: "<value>",
	}, operations.WithRetries(
		retry.Config{
			Strategy: "backoff",
			Backoff: &retry.BackoffStrategy{
				InitialInterval: 1,
				MaxInterval:     50,
				Exponent:        1.1,
				MaxElapsedTime:  100,
			},
			RetryConnectionErrors: false,
		}))
	if err != nil {
		log.Fatal(err)
	}
	if res.ImageResponse != nil {
		// handle response
	}
}

If you'd like to override the default retry strategy for all operations that support retries, you can use the WithRetryConfig option at SDK initialization:

package main

import (
	"context"
	livepeeraigo "github.com/livepeer/livepeer-ai-go"
	"github.com/livepeer/livepeer-ai-go/models/components"
	"github.com/livepeer/livepeer-ai-go/retry"
	"log"
)

func main() {
	ctx := context.Background()

	s := livepeeraigo.New(
		livepeeraigo.WithRetryConfig(
			retry.Config{
				Strategy: "backoff",
				Backoff: &retry.BackoffStrategy{
					InitialInterval: 1,
					MaxInterval:     50,
					Exponent:        1.1,
					MaxElapsedTime:  100,
				},
				RetryConnectionErrors: false,
			}),
		livepeeraigo.WithSecurity("<YOUR_BEARER_TOKEN_HERE>"),
	)

	res, err := s.Generate.TextToImage(ctx, components.TextToImageParams{
		Prompt: "<value>",
	})
	if err != nil {
		log.Fatal(err)
	}
	if res.ImageResponse != nil {
		// handle response
	}
}

Error Handling

Handling errors in this SDK should largely match your expectations. All operations return a response object or an error, they will never return both.

By Default, an API error will return sdkerrors.SDKError. When custom error responses are specified for an operation, the SDK may also return their associated error. You can refer to respective Errors tables in SDK docs for more details on possible error types for each operation.

For example, the TextToImage function may return the following errors:

Example

package main

import (
	"context"
	"errors"
	livepeeraigo "github.com/livepeer/livepeer-ai-go"
	"github.com/livepeer/livepeer-ai-go/models/components"
	"github.com/livepeer/livepeer-ai-go/models/sdkerrors"
	"log"
)

func main() {
	ctx := context.Background()

	s := livepeeraigo.New(
		livepeeraigo.WithSecurity("<YOUR_BEARER_TOKEN_HERE>"),
	)

	res, err := s.Generate.TextToImage(ctx, components.TextToImageParams{
		Prompt: "<value>",
	})
	if err != nil {

		var e *sdkerrors.HTTPError
		if errors.As(err, &e) {
			// handle error
			log.Fatal(e.Error())
		}

		var e *sdkerrors.HTTPValidationError
		if errors.As(err, &e) {
			// handle error
			log.Fatal(e.Error())
		}

		var e *sdkerrors.SDKError
		if errors.As(err, &e) {
			// handle error
			log.Fatal(e.Error())
		}
	}
}

Server Selection

Select Server by Index

You can override the default server globally using the WithServerIndex(serverIndex int) option when initializing the SDK client instance. The selected server will then be used as the default on the operations that use it. This table lists the indexes associated with the available servers:

Example

package main

import (
	"context"
	livepeeraigo "github.com/livepeer/livepeer-ai-go"
	"github.com/livepeer/livepeer-ai-go/models/components"
	"log"
)

func main() {
	ctx := context.Background()

	s := livepeeraigo.New(
		livepeeraigo.WithServerIndex(1),
		livepeeraigo.WithSecurity("<YOUR_BEARER_TOKEN_HERE>"),
	)

	res, err := s.Generate.TextToImage(ctx, components.TextToImageParams{
		Prompt: "<value>",
	})
	if err != nil {
		log.Fatal(err)
	}
	if res.ImageResponse != nil {
		// handle response
	}
}

Override Server URL Per-Client

The default server can also be overridden globally using the WithServerURL(serverURL string) option when initializing the SDK client instance. For example:

package main

import (
	"context"
	livepeeraigo "github.com/livepeer/livepeer-ai-go"
	"github.com/livepeer/livepeer-ai-go/models/components"
	"log"
)

func main() {
	ctx := context.Background()

	s := livepeeraigo.New(
		livepeeraigo.WithServerURL("https://dream-gateway.livepeer.cloud"),
		livepeeraigo.WithSecurity("<YOUR_BEARER_TOKEN_HERE>"),
	)

	res, err := s.Generate.TextToImage(ctx, components.TextToImageParams{
		Prompt: "<value>",
	})
	if err != nil {
		log.Fatal(err)
	}
	if res.ImageResponse != nil {
		// handle response
	}
}

Custom HTTP Client

The Go SDK makes API calls that wrap an internal HTTP client. The requirements for the HTTP client are very simple. It must match this interface:

type HTTPClient interface {
	Do(req *http.Request) (*http.Response, error)
}

The built-in net/http client satisfies this interface and a default client based on the built-in is provided by default. To replace this default with a client of your own, you can implement this interface yourself or provide your own client configured as desired. Here's a simple example, which adds a client with a 30 second timeout.

import (
	"net/http"
	"time"
	"github.com/myorg/your-go-sdk"
)

var (
	httpClient = &http.Client{Timeout: 30 * time.Second}
	sdkClient  = sdk.New(sdk.WithClient(httpClient))
)

This can be a convenient way to configure timeouts, cookies, proxies, custom headers, and other low-level configuration.

Authentication

Per-Client Security Schemes

This SDK supports the following security scheme globally:

You can configure it using the WithSecurity option when initializing the SDK client instance. For example:

package main

import (
	"context"
	livepeeraigo "github.com/livepeer/livepeer-ai-go"
	"github.com/livepeer/livepeer-ai-go/models/components"
	"log"
)

func main() {
	ctx := context.Background()

	s := livepeeraigo.New(
		livepeeraigo.WithSecurity("<YOUR_BEARER_TOKEN_HERE>"),
	)

	res, err := s.Generate.TextToImage(ctx, components.TextToImageParams{
		Prompt: "<value>",
	})
	if err != nil {
		log.Fatal(err)
	}
	if res.ImageResponse != nil {
		// handle response
	}
}

Summary

Livepeer AI Runner: An application to run AI pipelines

Table of Contents

• Livepeer AI Golang Client Library
  • Retries
  • Error Handling
  • Server Selection
  • Custom HTTP Client
  • Authentication
  • Maturity
  • Contributions

Maturity

This SDK is in alpha, and there may be breaking changes between versions without a major version update. Therefore, we recommend pinning usage to a specific package version. This way, you can install the same version each time without breaking changes unless you are intentionally looking for the latest version.

Contributions

While we value open-source contributions to this SDK, this library is generated programmatically. Any manual changes added to internal files will be overwritten on the next generation. We look forward to hearing your feedback. Feel free to open a PR or an issue with a proof of concept and we'll do our best to include it in a future release.