Package Exports

@atmus/nestjs-elevenlabs
@atmus/nestjs-elevenlabs/dist/index.js

This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (@atmus/nestjs-elevenlabs) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

Readme

NestJS OpenAI

Features

Configure and inject the OpenAI API client.

Installation

yarn add @atmus/nestjs-openai

Usage

Settings

`OpenAIModule.register`

Import the module at your module. Configure the OpenAI API client.

import { OpenAIModule } from "@atmus/nestjs-openai";

@Module({
  imports: [
    OpenAIModule.register({
      apiKey: "sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
    }),
  ],
  controllers: [AppController],
  providers: [AppService],
})
export class AppModule {}

`OpenAIModule.registerAsync`

You can also use OpenAIModule.registerAsync to configure it asynchronously. This way you can hide your api key from the code. It's recommended to use this method.

import { OpenAIModule } from "@atmus/nestjs-openai";

@Module({
  imports: [
    OpenAIModule.registerAsync({
      useFactory: (config: ConfigService<EnvVars>) => ({
        apiKey: config.get("OPENAI_API_KEY"),
      }),
      inject: [ConfigService],
    }),
  ],
  controllers: [AppController],
  providers: [AppService],
})
export class AppModule {}

Inject `OpenAIService`

Inject OpenAIService anywhere. Injected service is identical to OpenAI API client.

@Injectable()
export class TextCompletionService {
  constructor(private readonly openai: OpenAIService) {}

  async completion(
    messages: CreateChatCompletionRequest["messages"],
  ): Promise<string> {
    const { data } = await this.openai.createCompletion({
      model: "davinci",
      prompt: "This is a test",
    });
    return data.choices[0].text;
  }
}

@atmus/nestjs-elevenlabs