Unduh openai scala client - Unduh Kode Sumber openai scala client

Openai Scala Client?

Ini adalah klien Async Scala yang tidak masuk akal untuk API OpenAI yang mendukung semua titik akhir dan param yang tersedia termasuk streaming , penyelesaian obrolan terbaru, visi , dan rutinitas suara (sebagaimana didefinisikan di sini), yang disediakan dalam satu, layanan nyaman yang disebut OpenAiservice. Panggilan yang didukung adalah:

Model : Daftar Model, dan RetriEvemodel
Penyelesaian : CreateCompetion
Penyelesaian Obrolan : CreateChatCompletion, CreateChatFunchompletion (Deprecated), dan CreateChattoolCompletion
Sunting : createedit (usang)
Gambar : createImage, createImageDit, dan createImageVariation
Embeddings : CreateMbeddings
Batches : CreateBatch, Retrievebatch, CancelBatch, dan ListBatches
Audio : CreateAdiotranscription, CreateADiotranslation, dan CreateAdiOsPECH
File : ListFiles, UploadFile, DeleteFile, Retrievefile, dan RetrievefileContent
Fine-Tunes : CreateFinetune, ListFinetunes, Retrievefinetune, CancelfInetune, ListFinetuneEvents, ListFinetunecheckPoints, dan DeleteFinetunemodel
Moderasi : CreateModeration
Asisten : Createassistant, ListAssistants, Retrieveassistant, ModifyAssistant, dan Deleteassistant
Threads : CreateThread, Retrievethread, ModifyThread, dan Deletethread
Pesan utas : createThreadMessage, retrievethreadmessage, modifyThreadMessage, listThreadMessage, retrievethreadmessageFile, dan listThreadMessageFiles
Berlari : Createrun, CreateThreadandrun, Listruns, Retrieverun, ModifyRun, SubmittoolOutputs, dan CancelRun
Jalankan langkah : listrunsteps, dan retrieverunstep
Toko Vektor : CreateVectorStore, ListVectorStores, Retrievevectorstore, ModifyVectorStore, dan DeletEvectorStore
File toko vektor : CreateVectorStoreFile, ListVectorStoreFiles, RetrievevectorStoreFile, dan DeletEvectorStoreFile
Batch file toko vektor : CreateVectorStoreFileBatch, RETRIEVEVECTORSTOREFILEBATCH, CancelVectorStoreFileBatch, dan ListVectorStoreBatchFiles

Perhatikan bahwa agar konsisten dengan penamaan API OpenAI, nama fungsi layanan cocok dengan tepat judul/deskripsi titik akhir API dengan CamelCase. Juga, kami mengarahkan Lib untuk mandiri dengan ketergantungan sececepat yang dimungkinkan oleh karena itu kami akhirnya hanya menggunakan dua LIBS play-ahc-ws-standalone dan play-ws-standalone-json (di level atas). Selain itu, jika injeksi ketergantungan diperlukan, kami juga menggunakan Lib scala-guice .

Tidak ada waktu untuk membaca tutorial yang panjang? Tentu, kami mendengarmu! Lihat contoh untuk melihat cara menggunakan lib dalam praktik.

Selain API OpenAI, perpustakaan ini juga mendukung penyedia yang kompatibel dengan API (lihat contoh) seperti:

Azure Openai - Berbasis Cloud, menggunakan model openai tetapi dengan latensi yang lebih rendah
Azure AI-berbasis cloud, menawarkan banyak pilihan model open-source
Antropik - berbasis cloud, pesaing utama untuk OpenAi, menampilkan model -model berpemilik/tertutup seperti Claude3 - Haiku, Sonnet, dan Opus. Baru : Sekarang dengan dukungan cache!
Google Vertex AI-Berbasis Cloud, Fitur Model Sumber Hak Milik/Tertutup seperti Gemini 1.5 Pro dan Flash
Penyedia berbasis cloud Groq, yang dikenal karena inferensi super cepat dengan LPU
GROK ( Baru ) - Penyedia berbasis cloud dari X.Ai
Penyedia kembang api AI - berbasis cloud
Octoai - Penyedia berbasis cloud
Bersama - penyedia berbasis cloud
Cerebras - Penyedia berbasis cloud, superfast (mirip dengan Groq)
Mistral-Cloud berbasis, perusahaan LLM open-source terkemuka
DEEPSEEK ( Baru ) - Penyedia berbasis cloud dari China
Ollama-berjalan secara lokal, berfungsi sebagai payung untuk llms open-source termasuk llama3, dbrx, dan command-r
Fastchat-Berlari secara lokal, berfungsi sebagai payung untuk LLMS open-source seperti Vicuna, Alpaca, dan Fastchat-T5

Untuk informasi latar belakang, baca artikel tentang lib/klien di medium.

Coba juga klien Scala kami untuk database Pinecone Vector, atau gunakan kedua klien bersama -sama! Proyek demo ini menunjukkan cara menghasilkan dan menyimpan embeddings openai (dengan model text-embedding-ada-002 ) ke dalam pinus dan menanyakannya sesudahnya. Kombo OpenAI + Pinecone biasanya digunakan untuk agen AI otonom, seperti babyagi dan autogpt.

✔️ PENTING : Ini adalah perpustakaan "terawat di komunitas" dan, dengan demikian, tidak ada hubungannya dengan perusahaan openai.

Instalasi

Versi Scala yang saat ini didukung adalah 2.12, 2.13 , dan 3 .

Untuk menginstal perpustakaan, tambahkan ketergantungan berikut ke build.sbt Anda

 "io.cequence" %% "openai-scala-client" % "1.1.0"

atau ke pom.xml (jika Anda menggunakan maven)

 <dependency>
    <groupId>io.cequence</groupId>
    <artifactId>openai-scala-client_2.12</artifactId>
    <version>1.1.0</version>
</dependency>

Jika Anda ingin dukungan streaming, gunakan "io.cequence" %% "openai-scala-client-stream" % "1.1.0" sebagai gantinya.

Konfigurasi

Env. Variabel: OPENAI_SCALA_CLIENT_API_KEY dan secara opsional juga OPENAI_SCALA_CLIENT_ORG_ID (jika Anda memilikinya)
File config (default): OpenAi-scala-client.conf

Penggunaan?

I. Mendapatkan OpenAiservice

Pertama, Anda perlu memberikan konteks eksekusi implisit serta AKKA Materizer, misalnya, sebagai

  implicit val ec = ExecutionContext .global
  implicit val materializer = Materializer ( ActorSystem ())

Kemudian Anda dapat memperoleh layanan dengan salah satu cara berikut.

Konfigurasi default (mengharapkan variabel akan ditetapkan sebagaimana didefinisikan dalam bagian Config )

  val service = OpenAIServiceFactory ()

Konfigurasi khusus

  val config = ConfigFactory .load( " path_to_my_custom_config " )
  val service = OpenAIServiceFactory (config)

Tanpa konfigurasi

  val service = OpenAIServiceFactory (
     apiKey = " your_api_key " ,
     orgId = Some ( " your_org_id " ) // if you have one
  )

Untuk Azure dengan Kunci API

  val service = OpenAIServiceFactory .forAzureWithApiKey(
    resourceName = " your-resource-name " ,
    deploymentId = " your-deployment-id " , // usually model name such as "gpt-35-turbo"
    apiVersion = " 2023-05-15 " ,           // newest version
    apiKey = " your_api_key "
  )

Minimal OpenAICoreService Supping listModels , createCompletion , createChatCompletion , dan createEmbeddings Calls - Disediakan misalnya oleh Layanan FastChat yang berjalan di Port 8000

  val service = OpenAICoreServiceFactory ( " http://localhost:8000/v1/ " )

OpenAIChatCompletionService Menyediakan semata -mata createChatCompletion

Azure AI - misalnya model R+

  val service = OpenAIChatCompletionServiceFactory .forAzureAI(
    endpoint = sys.env( " AZURE_AI_COHERE_R_PLUS_ENDPOINT " ),
    region = sys.env( " AZURE_AI_COHERE_R_PLUS_REGION " ),
    accessToken = sys.env( " AZURE_AI_COHERE_R_PLUS_ACCESS_KEY " )
  )

Antropik-Membutuhkan Lib openai-scala-anthropic-client dan ANTHROPIC_API_KEY

  val service = AnthropicServiceFactory .asOpenAI()

Google Vertex AI-Membutuhkan Lib openai-scala-google-vertexai-client dan VERTEXAI_LOCATION + VERTEXAI_PROJECT_ID

  val service = VertexAIServiceFactory .asOpenAI()

Groq - membutuhkan GROQ_API_KEY"

  val service = OpenAIChatCompletionServiceFactory ( ChatProviderSettings .groq)
  // or with streaming
  val service = OpenAIChatCompletionServiceFactory .withStreaming( ChatProviderSettings .groq)

Grok - membutuhkan GROK_API_KEY"

  val service = OpenAIChatCompletionServiceFactory ( ChatProviderSettings .grok)
  // or with streaming
  val service = OpenAIChatCompletionServiceFactory .withStreaming( ChatProviderSettings .grok)

Fireworks AI - membutuhkan FIREWORKS_API_KEY"

  val service = OpenAIChatCompletionServiceFactory ( ChatProviderSettings .fireworks)
  // or with streaming
  val service = OpenAIChatCompletionServiceFactory .withStreaming( ChatProviderSettings .fireworks)

Octo ai - membutuhkan OCTOAI_TOKEN

  val service = OpenAIChatCompletionServiceFactory ( ChatProviderSettings .octoML)
  // or with streaming
  val service = OpenAIChatCompletionServiceFactory .withStreaming( ChatProviderSettings .octoML)

Bersama membutuhkan TOGETHERAI_API_KEY

  val service = OpenAIChatCompletionServiceFactory ( ChatProviderSettings .togetherAI)
  // or with streaming
  val service = OpenAIChatCompletionServiceFactory .withStreaming( ChatProviderSettings .togetherAI)

Cerebras membutuhkan CEREBRAS_API_KEY

  val service = OpenAIChatCompletionServiceFactory ( ChatProviderSettings .cerebras)
  // or with streaming
  val service = OpenAIChatCompletionServiceFactory .withStreaming( ChatProviderSettings .cerebras)

Mistral membutuhkan MISTRAL_API_KEY

  val service = OpenAIChatCompletionServiceFactory ( ChatProviderSettings .mistral)
  // or with streaming
  val service = OpenAIChatCompletionServiceFactory .withStreaming( ChatProviderSettings .mistral)

Ollama

  val service = OpenAIChatCompletionServiceFactory (
    coreUrl = " http://localhost:11434/v1/ "
  )

atau dengan streaming

  val service = OpenAIChatCompletionServiceFactory .withStreaming(
    coreUrl = " http://localhost:11434/v1/ "
  )

Perhatikan bahwa layanan dengan dukungan streaming tambahan- createCompletionStreamed dan createChatCompletionStreamed disediakan oleh OpenAistreamedServiceExtra (memerlukan lib openai-scala-client-stream ))

  import io . cequence . openaiscala . service . StreamedServiceTypes . OpenAIStreamedService
  import io . cequence . openaiscala . service . OpenAIStreamedServiceImplicits . _

  val service : OpenAIStreamedService = OpenAIServiceFactory .withStreaming()

Demikian pula untuk layanan pelengkap obrolan

  import io . cequence . openaiscala . service . OpenAIStreamedServiceImplicits . _

  val service = OpenAIChatCompletionServiceFactory .withStreaming(
    coreUrl = " https://api.fireworks.ai/inference/v1/ " ,
    authHeaders = Seq (( " Authorization " , s " Bearer ${sys.env( " FIREWORKS_API_KEY " )} " ))
  )

atau hanya jika streaming diperlukan

  val service : OpenAIChatCompletionStreamedServiceExtra =
    OpenAIChatCompletionStreamedServiceFactory (
      coreUrl = " https://api.fireworks.ai/inference/v1/ " ,
      authHeaders = Seq (( " Authorization " , s " Bearer ${sys.env( " FIREWORKS_API_KEY " )} " ))
   )

Melalui injeksi ketergantungan (membutuhkan lib openai-scala-guice )

  class MyClass @ Inject () ( openAIService : OpenAIService ) {...}

Ii. Fungsi panggilan

Dokumentasi lengkap dari setiap panggilan dengan input dan pengaturan masing -masing disediakan di OpenAiservice. Karena semua panggilan tidak ada, mereka mengembalikan tanggapan yang dibungkus di Future .

Ada proyek baru openai-scala-klien-contoh di mana Anda dapat menemukan banyak contoh siap pakai!

Daftar model

  service.listModels.map(models =>
    models.foreach(println)
  )

Retrieve Model

  service.retrieveModel( ModelId .text_davinci_003).map(model =>
    println(model.getOrElse( " N/A " ))
  )

Buat penyelesaian

  val text = """ Extract the name and mailing address from this email:
               |Dear Kelly,
               |It was great to talk to you at the seminar. I thought Jane's talk was quite good.
               |Thank you for the book. Here's my address 2111 Ash Lane, Crestview CA 92002
               |Best,
               |Maya
             """ .stripMargin

  service.createCompletion(text).map(completion =>
    println(completion.choices.head.text)
  )

Buat penyelesaian dengan pengaturan khusus

  val text = """ Extract the name and mailing address from this email:
               |Dear Kelly,
               |It was great to talk to you at the seminar. I thought Jane's talk was quite good.
               |Thank you for the book. Here's my address 2111 Ash Lane, Crestview CA 92002
               |Best,
               |Maya
             """ .stripMargin

  service.createCompletion(
    text,
    settings = CreateCompletionSettings (
      model = ModelId .gpt_4o,
      max_tokens = Some ( 1500 ),
      temperature = Some ( 0.9 ),
      presence_penalty = Some ( 0.2 ),
      frequency_penalty = Some ( 0.2 )
    )
  ).map(completion =>
    println(completion.choices.head.text)
  )

Buat penyelesaian dengan streaming dan pengaturan khusus

  val source = service.createCompletionStreamed(
    prompt = " Write me a Shakespeare poem about two cats playing baseball in Russia using at least 2 pages " ,
    settings = CreateCompletionSettings (
      model = ModelId .text_davinci_003,
      max_tokens = Some ( 1500 ),
      temperature = Some ( 0.9 ),
      presence_penalty = Some ( 0.2 ),
      frequency_penalty = Some ( 0.2 )
    )
  )

  source.map(completion => 
    println(completion.choices.head.text)
  ).runWith( Sink .ignore)

Agar ini berfungsi, Anda perlu menggunakan OpenAIServiceStreamedFactory dari openai-scala-client-stream LIB.

Buat penyelesaian obrolan

  val createChatCompletionSettings = CreateChatCompletionSettings (
    model = ModelId .gpt_4o
  )

  val messages = Seq (
    SystemMessage ( " You are a helpful assistant. " ),
    UserMessage ( " Who won the world series in 2020? " ),
    AssistantMessage ( " The Los Angeles Dodgers won the World Series in 2020. " ),
    UserMessage ( " Where was it played? " ),
  )

  service.createChatCompletion(
    messages = messages,
    settings = createChatCompletionSettings
  ).map { chatCompletion =>
    println(chatCompletion.choices.head.message.content)
  }

Buat penyelesaian obrolan untuk fungsi

  val messages = Seq (
    SystemMessage ( " You are a helpful assistant. " ),
    UserMessage ( " What's the weather like in San Francisco, Tokyo, and Paris? " )
  )

  // as a param type we can use "number", "string", "boolean", "object", "array", and "null"
  val tools = Seq (
    FunctionSpec (
      name = " get_current_weather " ,
      description = Some ( " Get the current weather in a given location " ),
      parameters = Map (
        " type " - > " object " ,
        " properties " - > Map (
          " location " - > Map (
            " type " - > " string " ,
            " description " - > " The city and state, e.g. San Francisco, CA "
          ),
          " unit " - > Map (
            " type " - > " string " ,
            " enum " - > Seq ( " celsius " , " fahrenheit " )
          )
        ),
        " required " - > Seq ( " location " )
      )
    )
  )

  // if we want to force the model to use the above function as a response
  // we can do so by passing: responseToolChoice = Some("get_current_weather")`
  service.createChatToolCompletion(
    messages = messages,
    tools = tools,
    responseToolChoice = None , // means "auto"
    settings = CreateChatCompletionSettings ( ModelId .gpt_3_5_turbo_1106)
  ).map { response =>
    val chatFunCompletionMessage = response.choices.head.message
    val toolCalls = chatFunCompletionMessage.tool_calls.collect {
      case (id, x : FunctionCallSpec ) => (id, x)
    }

    println(
      " tool call ids                : " + toolCalls.map(_._1).mkString( " , " )
    )
    println(
      " function/tool call names     : " + toolCalls.map(_._2.name).mkString( " , " )
    )
    println(
      " function/tool call arguments : " + toolCalls.map(_._2.arguments).mkString( " , " )
    )
  }

Buat penyelesaian obrolan dengan output JSON

  val messages = Seq (
    SystemMessage ( " Give me the most populous capital cities in JSON format. " ),
    UserMessage ( " List only african countries " )
  )

  val capitalsSchema = JsonSchema . Object (
    properties = Map (
      " countries " - > JsonSchema . Array (
        items = JsonSchema . Object (
          properties = Map (
            " country " - > JsonSchema . String (
              description = Some ( " The name of the country " )
            ),
            " capital " - > JsonSchema . String (
              description = Some ( " The capital city of the country " )
            )
          ),
          required = Seq ( " country " , " capital " )
        )
      )
    ),
    required = Seq ( " countries " )
  )

  val jsonSchemaDef = JsonSchemaDef (
    name = " capitals_response " ,
    strict = true ,
    structure = schema
  )

  service
    .createChatCompletion(
      messages = messages,
      settings = DefaultSettings .createJsonChatCompletion(jsonSchemaDef)
    )
    .map { response =>
      val json = Json .parse(messageContent(response))
      println( Json .prettyPrint(json))
    }

Hitung Token Bekas yang Diharapkan Sebelum memanggil createChatCompletions atau createChatFunCompletions , ini membantu Anda memilih model yang tepat dan mengurangi biaya. Ini adalah fitur eksperimental dan mungkin tidak berfungsi untuk semua model. Membutuhkan lib openai-scala-count-tokens .

Contoh Cara Menghitung Token Pesan:

 import io . cequence . openaiscala . service . OpenAICountTokensHelper
import io . cequence . openaiscala . domain .{ AssistantMessage , BaseMessage , FunctionSpec , ModelId , SystemMessage , UserMessage }

class MyCompletionService extends OpenAICountTokensHelper {
  def exec = {
    val model = ModelId .gpt_4_turbo_2024_04_09

    // messages to be sent to OpenAI
    val messages : Seq [ BaseMessage ] = Seq (
      SystemMessage ( " You are a helpful assistant. " ),
      UserMessage ( " Who won the world series in 2020? " ),
      AssistantMessage ( " The Los Angeles Dodgers won the World Series in 2020. " ),
      UserMessage ( " Where was it played? " ),
    )

    val tokenCount = countMessageTokens(model, messages)
  }
}

Contoh cara menghitung token pesan saat fungsi terlibat:

 import io . cequence . openaiscala . service . OpenAICountTokensHelper
import io . cequence . openaiscala . domain .{ BaseMessage , FunctionSpec , ModelId , SystemMessage , UserMessage }

class MyCompletionService extends OpenAICountTokensHelper {
  def exec = {
    val model = ModelId .gpt_4_turbo_2024_04_09
    
    // messages to be sent to OpenAI
    val messages : Seq [ BaseMessage ] = 
     Seq (
       SystemMessage ( " You are a helpful assistant. " ),
       UserMessage ( " What's the weather like in San Francisco, Tokyo, and Paris? " )
     )
     
    // function to be called
    val function : FunctionSpec = FunctionSpec (
      name = " getWeather " ,
      parameters = Map (
        " type " - > " object " ,
        " properties " - > Map (
          " location " - > Map (
            " type " - > " string " ,
            " description " - > " The city to get the weather for "
          ),
          " unit " - > Map ( " type " - > " string " , " enum " - > List ( " celsius " , " fahrenheit " ))
        )
      )
    )

    val tokenCount = countFunMessageTokens(model, messages, Seq (function), Some (function.name))
  }
}

✔️ PENTING : Setelah Anda selesai menggunakan layanan, Anda harus menutupnya dengan menelepon service.close . Kalau tidak, sumber daya/utas yang mendasarinya tidak akan dirilis.

AKU AKU AKU. Menggunakan adaptor

Adaptor untuk Layanan OpenAI (penyelesaian obrolan, inti, atau penuh) disediakan oleh OpenAiserviceAdapters. Adaptor digunakan untuk mendistribusikan beban antara beberapa layanan, coba lagi kesalahan sementara, rute, atau memberikan fungsionalitas tambahan. Lihat contoh untuk detail lebih lanjut.

Perhatikan bahwa adaptor dapat digabungkan secara sewenang -wenang/ditumpuk.

Distribusi beban robin bundar

  val adapters = OpenAIServiceAdapters .forFullService

  val service1 = OpenAIServiceFactory ( " your-api-key1 " )
  val service2 = OpenAIServiceFactory ( " your-api-key2 " )

  val service = adapters.roundRobin(service1, service2)

Distribusi beban pesanan acak

  val adapters = OpenAIServiceAdapters .forFullService

  val service1 = OpenAIServiceFactory ( " your-api-key1 " )
  val service2 = OpenAIServiceFactory ( " your-api-key2 " )

  val service = adapters.randomOrder(service1, service2)

Panggilan fungsi logging

  val adapters = OpenAIServiceAdapters .forFullService

  val rawService = OpenAIServiceFactory ()
  
  val service = adapters.log(
    rawService,
    " openAIService " ,
    logger.log
  )

Coba lagi kesalahan transien (misalnya kesalahan batas tingkat)

  val adapters = OpenAIServiceAdapters .forFullService

  implicit val retrySettings : RetrySettings = RetrySettings (maxRetries = 10 ).constantInterval( 10 .seconds)

  val service = adapters.retry(
    OpenAIServiceFactory (),
    Some (println(_)) // simple logging
  )

Coba lagi pada fungsi tertentu menggunakan retryhelpers secara langsung

 class MyCompletionService @ Inject () (
  val actorSystem : ActorSystem ,
  implicit val ec : ExecutionContext ,
  implicit val scheduler : Scheduler
)( val apiKey : String )
  extends RetryHelpers {
  val service : OpenAIService = OpenAIServiceFactory (apiKey)
  implicit val retrySettings : RetrySettings =
    RetrySettings (interval = 10 .seconds)

  def ask ( prompt : String ) : Future [ String ] =
    for {
      completion < - service
        .createChatCompletion(
          List ( MessageSpec ( ChatRole . User , prompt))
        )
        .retryOnFailure
    } yield completion.choices.head.message.content
}

Panggilan penyelesaian obrolan rute berdasarkan model

  val adapters = OpenAIServiceAdapters .forFullService

  // OctoAI
  val octoMLService = OpenAIChatCompletionServiceFactory (
    coreUrl = " https://text.octoai.run/v1/ " ,
    authHeaders = Seq (( " Authorization " , s " Bearer ${sys.env( " OCTOAI_TOKEN " )} " ))
  )

  // Anthropic
  val anthropicService = AnthropicServiceFactory .asOpenAI()

  // OpenAI
  val openAIService = OpenAIServiceFactory ()

  val service : OpenAIService =
    adapters.chatCompletionRouter(
      // OpenAI service is default so no need to specify its models here
      serviceModels = Map (
        octoMLService - > Seq ( NonOpenAIModelId .mixtral_8x22b_instruct),
        anthropicService - > Seq (
          NonOpenAIModelId .claude_2_1,
          NonOpenAIModelId .claude_3_opus_20240229,
          NonOpenAIModelId .claude_3_haiku_20240307
        )
      ),
      openAIService
    )

Adaptor obrolan-ke-lengkap

    val adapters = OpenAIServiceAdapters .forCoreService

    val service = adapters.chatToCompletion(
      OpenAICoreServiceFactory (
        coreUrl = " https://api.fireworks.ai/inference/v1/ " ,
        authHeaders = Seq (( " Authorization " , s " Bearer ${sys.env( " FIREWORKS_API_KEY " )} " ))
      )
    )

FAQ?

Wen Scala 3?
~~Feb 2023. Anda benar; Kami memilih bulan terpendek untuk melakukannya :)~~ Selesai!
Saya mendapat pengecualian timeout. Bagaimana cara mengubah pengaturan batas waktu?
Anda dapat melakukannya dengan memberikan param timeouts ke OpenAIServiceFactory atau, jika Anda menggunakan file konfigurasi sendiri, maka Anda cukup menambahkannya di sana sebagai:

 openai-scala-client {
    timeouts {
        requestTimeoutSec = 200
        readTimeoutSec = 200
        connectTimeoutSec = 5
        pooledConnectionIdleTimeoutSec = 60
    }
}

Saya mendapat pengecualian seperti com.typesafe.config.ConfigException$UnresolvedSubstitution: openai-scala-client.conf @ jar:file:.../io/cequence/openai-scala-client_2.13/0.0.1/openai-scala-client_2.13-0.0.1.jar!/openai-scala-client.conf: 4: Could not resolve substitution to a value: ${OPENAI_SCALA_CLIENT_API_KEY} . Apa yang harus saya lakukan?
Atur env. variabel OPENAI_SCALA_CLIENT_API_KEY . Jika Anda tidak memiliki satu daftar di sini.
Semuanya terlihat keren. Saya ingin mengobrol dengan Anda tentang penelitian dan pengembangan Anda?
Cukup tembak kami email di [email protected].