The Hanzo Kotlin SDK provides convenient access to the Hanzo REST API from applications written in Kotlin.
It is generated with Stainless.
The REST API documentation can be found on docs.hanzo.ai. KDocs are also available on javadoc.io.
implementation("ai.hanzo.api:hanzo-kotlin:0.1.0-alpha.1")
<dependency>
<groupId>ai.hanzo.api</groupId>
<artifactId>hanzo-kotlin</artifactId>
<version>0.1.0-alpha.1</version>
</dependency>
This library requires Java 8 or later.
import ai.hanzo.api.client.HanzoClient
import ai.hanzo.api.client.okhttp.HanzoOkHttpClient
import ai.hanzo.api.models.ClientGetHomeParams
import ai.hanzo.api.models.ClientGetHomeResponse
// Configures using the `HANZO_API_KEY` environment variable
val client: HanzoClient = HanzoOkHttpClient.fromEnv()
val response: ClientGetHomeResponse = client.getHome()
Configure the client using environment variables:
import ai.hanzo.api.client.HanzoClient
import ai.hanzo.api.client.okhttp.HanzoOkHttpClient
// Configures using the `HANZO_API_KEY` environment variable
val client: HanzoClient = HanzoOkHttpClient.fromEnv()
Or manually:
import ai.hanzo.api.client.HanzoClient
import ai.hanzo.api.client.okhttp.HanzoOkHttpClient
val client: HanzoClient = HanzoOkHttpClient.builder()
.apiKey("My API Key")
.build()
Or using a combination of the two approaches:
import ai.hanzo.api.client.HanzoClient
import ai.hanzo.api.client.okhttp.HanzoOkHttpClient
val client: HanzoClient = HanzoOkHttpClient.builder()
// Configures using the `HANZO_API_KEY` environment variable
.fromEnv()
.apiKey("My API Key")
.build()
See this table for the available options:
Setter | Environment variable | Required | Default value |
---|---|---|---|
apiKey |
HANZO_API_KEY |
true | - |
Tip
Don't create more than one client in the same application. Each client has a connection pool and thread pools, which are more efficient to share between requests.
To send a request to the Hanzo API, build an instance of some Params
class and pass it to the corresponding client method. When the response is received, it will be deserialized into an instance of a Kotlin class.
For example, client.getHome(...)
should be called with an instance of ClientGetHomeParams
, and it will return an instance of ClientGetHomeResponse
.
Each class in the SDK has an associated builder or factory method for constructing it.
Each class is immutable once constructed. If the class has an associated builder, then it has a toBuilder()
method, which can be used to convert it back to a builder for making a modified copy.
Because each class is immutable, builder modification will never affect already built class instances.
The default client is synchronous. To switch to asynchronous execution, call the async()
method:
import ai.hanzo.api.client.HanzoClient
import ai.hanzo.api.client.okhttp.HanzoOkHttpClient
import ai.hanzo.api.models.ClientGetHomeParams
import ai.hanzo.api.models.ClientGetHomeResponse
// Configures using the `HANZO_API_KEY` environment variable
val client: HanzoClient = HanzoOkHttpClient.fromEnv()
val response: ClientGetHomeResponse = client.async().getHome()
Or create an asynchronous client from the beginning:
import ai.hanzo.api.client.HanzoClientAsync
import ai.hanzo.api.client.okhttp.HanzoOkHttpClientAsync
import ai.hanzo.api.models.ClientGetHomeParams
import ai.hanzo.api.models.ClientGetHomeResponse
// Configures using the `HANZO_API_KEY` environment variable
val client: HanzoClientAsync = HanzoOkHttpClientAsync.fromEnv()
val response: ClientGetHomeResponse = client.getHome()
The asynchronous client supports the same options as the synchronous one, except most methods are suspending.
The SDK defines methods that accept files.
To upload a file, pass a Path
:
import ai.hanzo.api.models.audio.transcriptions.TranscriptionCreateParams
import ai.hanzo.api.models.audio.transcriptions.TranscriptionCreateResponse
import java.nio.file.Paths
val params: TranscriptionCreateParams = TranscriptionCreateParams.builder()
.file(Paths.get("/path/to/file"))
.build()
val transcription: TranscriptionCreateResponse = client.audio().transcriptions().create(params)
Or an arbitrary InputStream
:
import ai.hanzo.api.models.audio.transcriptions.TranscriptionCreateParams
import ai.hanzo.api.models.audio.transcriptions.TranscriptionCreateResponse
import java.net.URL
val params: TranscriptionCreateParams = TranscriptionCreateParams.builder()
.file(URL("https://example.com//path/to/file").openStream())
.build()
val transcription: TranscriptionCreateResponse = client.audio().transcriptions().create(params)
Or a ByteArray
:
import ai.hanzo.api.models.audio.transcriptions.TranscriptionCreateParams
import ai.hanzo.api.models.audio.transcriptions.TranscriptionCreateResponse
val params: TranscriptionCreateParams = TranscriptionCreateParams.builder()
.file("content".toByteArray())
.build()
val transcription: TranscriptionCreateResponse = client.audio().transcriptions().create(params)
Note that when passing a non-Path
its filename is unknown so it will not be included in the request. To manually set a filename, pass a MultipartField
:
import ai.hanzo.api.core.MultipartField
import ai.hanzo.api.models.audio.transcriptions.TranscriptionCreateParams
import ai.hanzo.api.models.audio.transcriptions.TranscriptionCreateResponse
import java.io.InputStream
import java.net.URL
val params: TranscriptionCreateParams = TranscriptionCreateParams.builder()
.file(MultipartField.builder<InputStream>()
.value(URL("https://example.com//path/to/file").openStream())
.filename("/path/to/file")
.build())
.build()
val transcription: TranscriptionCreateResponse = client.audio().transcriptions().create(params)
The SDK defines methods that deserialize responses into instances of Kotlin classes. However, these methods don't provide access to the response headers, status code, or the raw response body.
To access this data, prefix any HTTP method call on a client or service with withRawResponse()
:
import ai.hanzo.api.core.http.Headers
import ai.hanzo.api.core.http.HttpResponseFor
import ai.hanzo.api.models.ClientGetHomeParams
import ai.hanzo.api.models.ClientGetHomeResponse
val response: HttpResponseFor<ClientGetHomeResponse> = client.withRawResponse().getHome()
val statusCode: Int = response.statusCode()
val headers: Headers = response.headers()
You can still deserialize the response into an instance of a Kotlin class if needed:
import ai.hanzo.api.models.ClientGetHomeResponse
val parsedResponse: ClientGetHomeResponse = response.parse()
The SDK throws custom unchecked exception types:
-
HanzoServiceException
: Base class for HTTP errors. See this table for which exception subclass is thrown for each HTTP status code:Status Exception 400 BadRequestException
401 UnauthorizedException
403 PermissionDeniedException
404 NotFoundException
422 UnprocessableEntityException
429 RateLimitException
5xx InternalServerException
others UnexpectedStatusCodeException
-
HanzoIoException
: I/O networking errors. -
HanzoInvalidDataException
: Failure to interpret successfully parsed data. For example, when accessing a property that's supposed to be required, but the API unexpectedly omitted it from the response. -
HanzoException
: Base class for all exceptions. Most errors will result in one of the previously mentioned ones, but completely generic errors may be thrown using the base class.
The SDK uses the standard OkHttp logging interceptor.
Enable logging by setting the HANZO_LOG
environment variable to info
:
$ export HANZO_LOG=info
Or to debug
for more verbose logging:
$ export HANZO_LOG=debug
The SDK automatically retries 2 times by default, with a short exponential backoff.
Only the following error types are retried:
- Connection errors (for example, due to a network connectivity problem)
- 408 Request Timeout
- 409 Conflict
- 429 Rate Limit
- 5xx Internal
The API may also explicitly instruct the SDK to retry or not retry a response.
To set a custom number of retries, configure the client using the maxRetries
method:
import ai.hanzo.api.client.HanzoClient
import ai.hanzo.api.client.okhttp.HanzoOkHttpClient
val client: HanzoClient = HanzoOkHttpClient.builder()
.fromEnv()
.maxRetries(4)
.build()
Requests time out after 1 minute by default.
To set a custom timeout, configure the method call using the timeout
method:
import ai.hanzo.api.models.ClientGetHomeParams
import ai.hanzo.api.models.ClientGetHomeResponse
val response: ClientGetHomeResponse = client.getHome(RequestOptions.builder().timeout(Duration.ofSeconds(30)).build())
Or configure the default for all method calls at the client level:
import ai.hanzo.api.client.HanzoClient
import ai.hanzo.api.client.okhttp.HanzoOkHttpClient
import java.time.Duration
val client: HanzoClient = HanzoOkHttpClient.builder()
.fromEnv()
.timeout(Duration.ofSeconds(30))
.build()
To route requests through a proxy, configure the client using the proxy
method:
import ai.hanzo.api.client.HanzoClient
import ai.hanzo.api.client.okhttp.HanzoOkHttpClient
import java.net.InetSocketAddress
import java.net.Proxy
val client: HanzoClient = HanzoOkHttpClient.builder()
.fromEnv()
.proxy(Proxy(
Proxy.Type.HTTP, InetSocketAddress(
"https://example.com", 8080
)
))
.build()
The SDK is typed for convenient usage of the documented API. However, it also supports working with undocumented or not yet supported parts of the API.
To set undocumented parameters, call the putAdditionalHeader
, putAdditionalQueryParam
, or putAdditionalBodyProperty
methods on any Params
class:
import ai.hanzo.api.core.JsonValue
import ai.hanzo.api.models.ClientGetHomeParams
val params: ClientGetHomeParams = ClientGetHomeParams.builder()
.putAdditionalHeader("Secret-Header", "42")
.putAdditionalQueryParam("secret_query_param", "42")
.putAdditionalBodyProperty("secretProperty", JsonValue.from("42"))
.build()
These can be accessed on the built object later using the _additionalHeaders()
, _additionalQueryParams()
, and _additionalBodyProperties()
methods.
To set undocumented parameters on nested headers, query params, or body classes, call the putAdditionalProperty
method on the nested class:
import ai.hanzo.api.core.JsonValue
import ai.hanzo.api.models.model.ModelCreateParams
val params: ModelCreateParams = ModelCreateParams.builder()
.llmParams(ModelCreateParams.LlmParams.builder()
.putAdditionalProperty("secretProperty", JsonValue.from("42"))
.build())
.build()
These properties can be accessed on the nested built object later using the _additionalProperties()
method.
To set a documented parameter or property to an undocumented or not yet supported value, pass a JsonValue
object to its setter:
import ai.hanzo.api.models.ClientGetHomeParams
val params: ClientGetHomeParams = ClientGetHomeParams.builder().build()
The most straightforward way to create a JsonValue
is using its from(...)
method:
import ai.hanzo.api.core.JsonValue
// Create primitive JSON values
val nullValue: JsonValue = JsonValue.from(null)
val booleanValue: JsonValue = JsonValue.from(true)
val numberValue: JsonValue = JsonValue.from(42)
val stringValue: JsonValue = JsonValue.from("Hello World!")
// Create a JSON array value equivalent to `["Hello", "World"]`
val arrayValue: JsonValue = JsonValue.from(listOf(
"Hello", "World"
))
// Create a JSON object value equivalent to `{ "a": 1, "b": 2 }`
val objectValue: JsonValue = JsonValue.from(mapOf(
"a" to 1, "b" to 2
))
// Create an arbitrarily nested JSON equivalent to:
// {
// "a": [1, 2],
// "b": [3, 4]
// }
val complexValue: JsonValue = JsonValue.from(mapOf(
"a" to listOf(
1, 2
), "b" to listOf(
3, 4
)
))
To access undocumented response properties, call the _additionalProperties()
method:
import ai.hanzo.api.core.JsonBoolean
import ai.hanzo.api.core.JsonNull
import ai.hanzo.api.core.JsonNumber
import ai.hanzo.api.core.JsonValue
val additionalProperties: Map<String, JsonValue> = client.utils().tokenCounter(params)._additionalProperties()
val secretPropertyValue: JsonValue = additionalProperties.get("secretProperty")
val result = when (secretPropertyValue) {
is JsonNull -> "It's null!"
is JsonBoolean -> "It's a boolean!"
is JsonNumber -> "It's a number!"
// Other types include `JsonMissing`, `JsonString`, `JsonArray`, and `JsonObject`
else -> "It's something else!"
}
To access a property's raw JSON value, which may be undocumented, call its _
prefixed method:
import ai.hanzo.api.core.JsonField
val model: JsonField<String> = client.utils().tokenCounter(params)._model()
if (model.isMissing()) {
// The property is absent from the JSON response
} else if (model.isNull()) {
// The property was set to literal null
} else {
// Check if value was provided as a string
// Other methods include `asNumber()`, `asBoolean()`, etc.
val jsonString: String? = model.asString();
// Try to deserialize into a custom type
val myObject: MyClass = model.asUnknown()!!.convert(MyClass::class.java)
}
In rare cases, the API may return a response that doesn't match the expected type. For example, the SDK may expect a property to contain a String
, but the API could return something else.
By default, the SDK will not throw an exception in this case. It will throw HanzoInvalidDataException
only if you directly access the property.
If you would prefer to check that the response is completely well-typed upfront, then either call validate()
:
import ai.hanzo.api.models.utils.UtilTokenCounterResponse
val response: UtilTokenCounterResponse = client.utils().tokenCounter(params).validate()
Or configure the method call to validate the response using the responseValidation
method:
import ai.hanzo.api.models.ClientGetHomeParams
import ai.hanzo.api.models.ClientGetHomeResponse
val response: ClientGetHomeResponse = client.getHome(RequestOptions.builder().responseValidation(true).build())
Or configure the default for all method calls at the client level:
import ai.hanzo.api.client.HanzoClient
import ai.hanzo.api.client.okhttp.HanzoOkHttpClient
val client: HanzoClient = HanzoOkHttpClient.builder()
.fromEnv()
.responseValidation(true)
.build()
Kotlin enum
classes are not trivially forwards compatible. Using them in the SDK could cause runtime exceptions if the API is updated to respond with a new enum value.
Using JsonField<T>
enables a few features:
- Allowing usage of undocumented API functionality
- Lazily validating the API response against the expected shape
- Representing absent vs explicitly null values
Why don't you use data
classes?
It is not backwards compatible to add new fields to a data class and we don't want to introduce a breaking change every time we add a field to a class.
Checked exceptions are widely considered a mistake in the Java programming language. In fact, they were omitted from Kotlin for this reason.
Checked exceptions:
- Are verbose to handle
- Encourage error handling at the wrong level of abstraction, where nothing can be done about the error
- Are tedious to propagate due to the function coloring problem
- Don't play well with lambdas (also due to the function coloring problem)
This package generally follows SemVer conventions, though certain backwards-incompatible changes may be released as minor versions:
- Changes to library internals which are technically public but not intended or documented for external use. (Please open a GitHub issue to let us know if you are relying on such internals.)
- Changes that we do not expect to impact the vast majority of users in practice.
We take backwards-compatibility seriously and work hard to ensure you can rely on a smooth upgrade experience.
We are keen for your feedback; please open an issue with questions, bugs, or suggestions.